Session data processing method and device, search method and device, and electronic equipment

Abstract

The present disclosure relates to a session data processing method and device, a search method and device, an electronic device, a computer readable storage medium and a computer program product, and relates to the technical field of computers. The session data processing method comprises: clustering session content of a plurality of session turns between a user and an agent to obtain at least one session, wherein each session comprises at least one session turn in which the session content belongs to the same session topic; generating key information of each session according to the session content of at least one session turn in each session, wherein the key information of each session represents the session topic of each session; and displaying the key information of the at least one session to the user on a historical session display interface between the user and the agent. According to the present disclosure, the efficiency of the user viewing the historical conversation between the user and the agent can be improved, the historical conversation is more convenient and fast to trace back, and the user experience is improved.

Description

Technical Field

[0001] This disclosure relates to the field of computer technology, and in particular to session data processing methods and apparatus, search methods and apparatus, electronic devices, computer-readable storage media, and computer program products. Background Technology

[0002] With the development of artificial intelligence technology, related applications have permeated all aspects of our lives, such as intelligent dialogue.

[0003] In related technologies, users can view their historical conversations with an intelligent agent by swiping. Summary of the Invention

[0004] This summary section is provided to briefly introduce the concepts, which will be described in detail in the detailed description section below. This summary section is not intended to identify key or essential features of the claimed technical solution, nor is it intended to limit the scope of the claimed technical solution.

[0005] According to a first aspect of some embodiments of this disclosure, a session data processing method is provided, including:

[0006] Cluster the conversation content between the user and the agent in multiple conversation rounds to obtain at least one conversation, wherein each conversation includes at least one conversation round in which the conversation content belongs to the same conversation topic;

[0007] Based on the conversation content of at least one session round in each session, key information for each session is generated, wherein the key information for each session represents the conversation topic of each session;

[0008] On the interface displaying the user's and the agent's historical conversations, key information from at least one conversation is displayed to the user.

[0009] According to a second aspect of some embodiments of this disclosure, a search method is provided, comprising:

[0010] Receive search keywords input by the user;

[0011] On the historical session display interface, at least one key piece of information matching the search keyword is displayed to the user. The at least one key piece of information is at least a portion of the key information of at least one session displayed to the user in the session data processing method of any embodiment of this disclosure.

[0012] According to a third aspect of some embodiments of the present disclosure, a session data processing apparatus is provided, comprising:

[0013] The clustering module is configured to cluster the conversation content between the user and the agent in multiple conversation rounds to obtain at least one conversation, wherein each conversation includes at least one conversation round in which the conversation content belongs to the same conversation topic;

[0014] The generation module is configured to generate key information for each session based on the session content of at least one session round in each session, wherein the key information for each session characterizes the session topic of each session;

[0015] The display module is configured to display key information of at least one session to the user on the historical session display interface between the user and the agent.

[0016] According to a fourth aspect of some embodiments of the present disclosure, a search apparatus is provided, comprising:

[0017] The receiving module is configured to receive search keywords input by the user;

[0018] The display module is configured to display at least one key piece of information matching the search keyword to the user on the historical session display interface, wherein the at least one key piece of information is at least a portion of the key piece of information of at least one session displayed to the user in the session data processing method of any embodiment of this disclosure.

[0019] According to a fifth aspect of some embodiments of the present disclosure, an electronic device is provided, comprising: a memory; and a processor coupled to the memory, the processor being configured to perform a session data processing method or search method of any embodiment of the present disclosure based on instructions stored in the memory.

[0020] According to a sixth aspect of some embodiments of the present disclosure, a computer-readable storage medium is provided having a computer program stored thereon that, when executed by a processor, performs a session data processing method or a search method according to any embodiment of the present disclosure.

[0021] According to a seventh aspect of some embodiments of the present disclosure, a computer program product is provided that, when the computer program product is run on a computer, causes the computer to implement the session data processing method or search method of any of the embodiments.

[0022] Other features, aspects, and advantages of this disclosure will become clear from the following detailed description of exemplary embodiments with reference to the accompanying drawings. Attached Figure Description

[0023] Preferred embodiments of the present disclosure are described below with reference to the accompanying drawings. The accompanying drawings, which are included to provide a further understanding of the present disclosure, and which, together with the following detailed description, are incorporated in and form a part of this specification and are used to explain the present disclosure. It should be understood that the drawings described below only relate to some embodiments of the present disclosure and are not intended to limit the present disclosure. In the drawings:

[0024] Figure 1 This is a schematic flowchart illustrating a session data processing method according to some embodiments of the present disclosure;

[0025] Figure 2 This is a schematic flowchart illustrating a session data processing method according to other embodiments of the present disclosure;

[0026] Figure 3 This is a schematic flowchart illustrating a session data processing method according to other embodiments of the present disclosure;

[0027] Figure 4 This is a schematic flowchart illustrating a session processing method according to other embodiments of the present disclosure;

[0028] Figure 5 This is a schematic flowchart illustrating a session data processing method according to other embodiments of the present disclosure;

[0029] Figure 6 This is a schematic flowchart illustrating a session data processing method according to other embodiments of the present disclosure;

[0030] Figure 7 This is a schematic flowchart illustrating a session data processing method according to other embodiments of the present disclosure;

[0031] Figure 8 This is a schematic flowchart illustrating a session data processing method according to other embodiments of the present disclosure;

[0032] Figure 9 This is a schematic flowchart illustrating a session data processing method according to other embodiments of the present disclosure;

[0033] Figure 10 This is a schematic flowchart illustrating a session data processing method according to other embodiments of the present disclosure;

[0034] Figure 11 This is a schematic flowchart illustrating a session data processing method according to other embodiments of the present disclosure;

[0035] Figure 12 This is a schematic flowchart illustrating a session data processing method according to other embodiments of the present disclosure;

[0036] Figure 13This is a schematic flowchart illustrating a search method according to some embodiments of the present disclosure;

[0037] Figure 14 This is a schematic diagram illustrating a historical session display interface according to some embodiments of the present disclosure;

[0038] Figure 15 This is a schematic diagram illustrating a history session display interface according to other embodiments of the present disclosure;

[0039] Figure 16 This is a block diagram illustrating a session data processing apparatus according to some embodiments of the present disclosure;

[0040] Figure 17 This is a block diagram illustrating a search apparatus according to some embodiments of the present disclosure;

[0041] Figure 18 This is a block diagram illustrating an electronic device according to some embodiments of the present disclosure;

[0042] Figure 19 Block diagrams of electronic devices according to other embodiments of the present disclosure are shown.

[0043] It should be understood that, for ease of description, the dimensions of the various parts shown in the accompanying drawings are not necessarily drawn to actual scale. The same or similar reference numerals are used in the various drawings to denote the same or similar parts. Therefore, once an item is defined in one drawing, it may not be discussed further in subsequent drawings. Detailed Implementation

[0044] The technical solutions of the embodiments of this disclosure will be clearly and completely described below with reference to the accompanying drawings. However, it is obvious that the described embodiments are only some embodiments of this disclosure, and not all embodiments. The following description of the embodiments is merely illustrative and is in no way intended to limit this disclosure or its application or use. It should be understood that this disclosure can be implemented in various forms and should not be construed as limited to the embodiments set forth herein.

[0045] It should be understood that the various steps described in the method embodiments of this disclosure may be performed in different orders and / or in parallel. Furthermore, method embodiments may include additional steps and / or omit the steps shown. The scope of this disclosure is not limited in this respect. Unless otherwise specifically stated, the relative arrangement, numerical expressions, and values ​​of components and steps set forth in these embodiments should be interpreted as merely exemplary and do not limit the scope of this disclosure.

[0046] As used in this disclosure, the term "comprising" and its variations are open-ended terms that include at least the following elements / features but do not exclude other elements / features, i.e., "including but not limited to". Furthermore, as used in this disclosure, the term "including" and its variations are open-ended terms that include at least the following elements / features but do not exclude other elements / features, i.e., "including but not limited to". Therefore, "comprising" and "including" are synonymous. The term "based on" means "at least partially based on".

[0047] Throughout this specification, the terms "one embodiment," "some embodiments," or "embodiment" mean that a specific feature, structure, or characteristic described in connection with an embodiment is included in at least one embodiment of the invention. For example, the term "one embodiment" means "at least one embodiment"; the term "another embodiment" means "at least one additional embodiment"; and the term "some embodiments" means "at least some embodiments." Furthermore, the appearance of the phrases "in one embodiment," "in some embodiments," or "in an embodiment" in various places throughout the specification does not necessarily refer to the same embodiment, but may refer to the same embodiment.

[0048] It should be noted that the concepts of "first," "second," etc., used in this disclosure are used only to distinguish different devices, modules, or units, and are not intended to define the order of functions performed by these devices, modules, or units or their interdependencies. Unless otherwise specified, the concepts of "first," "second," etc., are not intended to imply that the objects described herein must be in a given temporal, spatial, rank, or any other given order.

[0049] It should be noted that the terms "a" and "a plurality of" used in this disclosure are illustrative rather than restrictive, and those skilled in the art should understand that, unless otherwise expressly indicated in the context, they should be understood as "one or more".

[0050] The names of messages or information exchanged between multiple devices in the embodiments of this disclosure are for illustrative purposes only and are not intended to limit the scope of such messages or information.

[0051] The embodiments of this disclosure are described in detail below with reference to the accompanying drawings; however, this disclosure is not limited to these specific embodiments. These specific embodiments can be combined with each other, and the same or similar concepts or processes may not be described again in some embodiments. Furthermore, in one or more embodiments, specific features, structures, or characteristics can be combined in any suitable manner that will be apparent to those skilled in the art from this disclosure.

[0052] In related technologies, it is difficult for users to quickly view the user's historical conversations with the intelligent agent.

[0053] This disclosure provides a technical solution that can improve the efficiency of users viewing historical dialogues between users and intelligent agents, making historical dialogue retrieval more convenient and faster, and enhancing the user experience.

[0054] Figure 1 This is a schematic flowchart illustrating a session data processing method according to some embodiments of the present disclosure.

[0055] like Figure 1 As shown, the conversation data processing method includes: step S101, clustering the conversation content between the user and the agent in multiple conversation rounds to obtain at least one conversation, wherein each conversation includes at least one conversation round where the conversation content belongs to the same conversation topic; step S102, generating key information for each conversation based on the conversation content of at least one conversation round in each conversation, wherein the key information for each conversation represents the conversation topic of each conversation; and step S103, displaying the key information of the at least one conversation to the user on the historical conversation display interface between the user and the agent.

[0056] A conversation round consists of a message from the user and a response message from the agent. For example, when a user asks a question to the agent, and the agent provides an answer, this process constitutes a complete conversation round. Different conversation rounds can be identified and distinguished using different round numbers.

[0057] A conversation typically begins when the user sends the first message and ends when the user explicitly indicates the end of the conversation or when the agent determines that the user's problem has been resolved and the user has no further intention to interact. For example, different conversations can be distinguished by different conversation identifiers.

[0058] In some embodiments, the length of the key information for each session is less than a preset length threshold, such as keywords. The key information for each session can be used as the title of each session.

[0059] The same conversation topic can include, for example, the same subject.

[0060] In this embodiment, by clustering the conversation content of multiple conversation rounds, at least one conversation is obtained. Each conversation includes at least one conversation round whose content belongs to the same conversation topic. Key information is then generated for each conversation to characterize its topic, and this key information is displayed to the user. This approach allows users to easily view their historical conversations with the agent upon entering the historical conversation display interface. Historical conversation retrieval is more convenient and faster, improving the efficiency of viewing historical conversations and enhancing the user experience.

[0061] The following will combine Figures 2 to 12The session data processing methods in other embodiments of this disclosure are described in detail.

[0062] Figure 2 This is a schematic flowchart illustrating a session data processing method according to other embodiments of the present disclosure. Figure 2 and Figure 1 The difference is that, Figure 2 Steps S104 to S105 of the session data processing method are shown. Only the following descriptions will be provided. Figure 2 and Figure 1 The differences are minor, while the similarities will not be elaborated upon.

[0063] like Figure 2 As shown, in step S104, the key information of the at least one session is clustered to obtain at least one cluster name, wherein each cluster name is used to summarize the key information of sessions that have common characteristics.

[0064] In step S105, on the historical conversation display interface between the user and the agent, at least one cluster name is displayed to the user, wherein each cluster name corresponds to key information of one or more conversations.

[0065] Cluster names reflect the common characteristics of key information from one or more sessions corresponding to that cluster name. For example, a cluster name might be a cluster title. A cluster name is a higher-level summary of the key information from one or more sessions corresponding to that cluster name. For example, if the key information for the first session is "food at location A" and the key information for the second session is "scenery at location A," then the key information from the first and second sessions are clustered into one session category, with the cluster name "Tourism at Location A."

[0066] In this embodiment, key information of at least one session is clustered so that key information of sessions with common characteristics are clustered into a single cluster name. This allows for the unified display of key information of sessions with common characteristics, further improving the convenience of historical dialogue retrieval, increasing the efficiency of users viewing historical dialogues, and enhancing the user experience.

[0067] Clustering key information can organize conversation content into a directory-like guide to facilitate user searches. However, as users interact with the agent, the conversation content may gradually increase, and the amount of content under a particular cluster name may also increase. When there is too much content under a cluster name, even if the user locates the cluster name, it may be difficult to find the information they want. Therefore, the "directory" may lose its meaning. For example, a user initially discusses football and basketball with the agent a few times, and these conversations are categorized under the cluster name "Sports". As the chat content increases, the content related to football and basketball may become very large, or content about volleyball and table tennis may also be added. At this point, it may be difficult for the user to find the information they want using the cluster name.

[0068] To make cluster names more effective, in some embodiments, the hierarchy of cluster names can be adjusted based on the amount of content in the sessions associated with those cluster names. For example, let any cluster name be a first-level item, and the key information corresponding to any cluster name be a second-level item of that first-level item. In response to a cluster name having a session content exceeding a threshold, the first-level item corresponding to that cluster name is deleted, and the key information of one or more sessions corresponding to that cluster name is determined as a new first-level item. That is, if the original cluster name is considered a first-level item in a directory, and the key information is considered a second-level item (i.e., a sub-item of the first-level item), then the above embodiment can be considered as canceling the original first-level item and determining the second-level items under the canceled first-level item as a new first-level directory. This dynamic adjustment method can adapt to changes in conversation content, allowing cluster names to more accurately help users trace back, further improving the efficiency of users viewing historical conversations and enhancing the user experience.

[0069] Those skilled in the art should understand that the “level 1” mentioned above does not necessarily refer to the first level in a directory structure; it can be any level.

[0070] Furthermore, the session content involved in the new first-level project can be clustered to obtain at least one session corresponding to the new first-level project. For each session in the at least one session corresponding to the new first-level project, key information of the session is generated based on the session content of at least one session round in that session, serving as a second-level project of the new first-level project. Accordingly, if the new first-level project involves multiple sessions, multiple second-level projects will be generated under the new first-level project. Thus, for the new first-level project, second-level projects can continue to be generated through clustering, and the second-level projects are sub-projects of the first-level projects. In this way, the new first-level project can have a structure similar to other first-level projects.

[0071] Figure 3This is a schematic flowchart illustrating a session data processing method according to other embodiments of the present disclosure. Figure 3 and Figure 2 The difference is that, Figure 3 Step S106 is also shown. Only the following description will be provided. Figure 3 and Figure 2 The differences are minor, while the similarities will not be elaborated upon.

[0072] like Figure 3 As shown, in step S106, in response to the user clicking any cluster name on the historical session display interface, key information of one or more sessions corresponding to any cluster name is displayed to the user on the historical session display interface.

[0073] Cluster names can be displayed on clickable controls in the history session display interface to facilitate user clicks.

[0074] For example, in the historical session display interface, the relationship between cluster names and key session information can be displayed in the form of folders. For instance, by clicking on a cluster name, a user can enter the folder corresponding to that cluster name to view the key information of one or more sessions corresponding to that cluster name.

[0075] For example, in the historical conversation display interface, the relationship between cluster names and key conversation information can be displayed in a list. For instance, by clicking on a cluster name, a user can view the key information of one or more conversations corresponding to that cluster name through a drop-down menu.

[0076] In this embodiment, the cluster name is associated with or linked to key information of one or more sessions corresponding to that cluster name, which further improves the convenience of tracing back historical conversations, increases the efficiency of users viewing historical conversations, and enhances the user experience.

[0077] Figure 4 This is a schematic flowchart illustrating a session processing method according to other embodiments of the present disclosure. Figure 4 and Figure 3 The difference is that, Figure 4 Steps S107 to S109 in some embodiments of this disclosure are shown. Only the following descriptions will be provided. Figure 4 and Figure 3 The differences are minor, while the similarities will not be elaborated upon.

[0078] like Figure 4 As shown, in step S107, the user's request to modify any cluster name is received.

[0079] In step S108, the modification component is displayed to the user, the modification component including input controls.

[0080] In step S109, the name of any cluster is modified according to the user's input in the input control.

[0081] For example, a user can initiate a modification request for any cluster name by long-pressing or double-clicking it. Alternatively, the input control could be an input box where the user can enter the desired cluster name to update any cluster name.

[0082] In this embodiment, users can modify any cluster name to make the cluster name more in line with user habits, realizing personalized settings, further improving the convenience of historical conversation review, increasing the efficiency of users viewing historical conversations, and enhancing the user experience.

[0083] Figure 5 This is a schematic flowchart illustrating a session data processing method according to other embodiments of the present disclosure. Figure 5 and Figure 1 The difference is that, Figure 5 Steps S110 to S111 of the session data processing method in some embodiments of this disclosure are also shown. They will be described below only. Figure 5 and Figure 4 The differences are minor, while the similarities will not be elaborated upon.

[0084] like Figure 5 As shown, in step S110, in response to the user clicking on the key information of any session on the historical session display interface, the user is redirected from the historical session display interface to the session interface between the user and the agent.

[0085] In step S111, on the session interface, the user is shown the session content of at least one session round included in any session.

[0086] In this embodiment, users can access any key information of any conversation by manipulating the historical conversation display interface, and then jump to the conversation interface to view the content of that conversation. This further enhances the convenience of tracing back historical conversations, improves the efficiency of users viewing historical conversations, and enhances the user experience.

[0087] Figure 6 This is a schematic flowchart illustrating a session data processing method according to other embodiments of the present disclosure. Figure 6 and Figure 5 The difference is that, Figure 6 Step S1111 is Figure 5 One implementation of step S111 is described below. Figure 6 and Figure 5 The differences are minor, while the similarities will not be elaborated upon.

[0088] like Figure 6 As shown, in step S1111, when any session includes multiple session rounds, the session content of the session round that occurred earliest is displayed first on the session interface.

[0089] For example, the first session consists of two session rounds, and the content of the first session round is shown to the user first.

[0090] In this embodiment, the conversation content of the earliest conversation round is displayed first, which makes it convenient for users to view from the beginning of the conversation, further improving the convenience and efficiency of historical conversation retrieval and enhancing the user experience.

[0091] Figure 7 This is a schematic flowchart illustrating a session data processing method according to other embodiments of the present disclosure. Figure 7 and Figure 5 The difference is that, Figure 7 In step S1112 is Figure 5 One implementation of step S111 is described below. Figure 7 and Figure 5 The differences are minor, while the similarities will not be elaborated upon.

[0092] like Figure 7 As shown, in step S1112, a summary of the conversation content of at least one conversation round included in any of the conversations is generated and displayed.

[0093] A summary of a session can be, for example, a summary of the content of at least one session round included in the session.

[0094] In this embodiment, by displaying a summary of the conversation to the user, the convenience and efficiency of historical conversation retrieval can be further improved, thereby enhancing the user experience.

[0095] Figure 8 This is a schematic flowchart illustrating a session data processing method according to other embodiments of the present disclosure. Figure 8 and Figure 5 The difference is that, Figure 8 Step S1113 in the diagram is Figure 5 One implementation of step S111 is described below. Figure 8 and Figure 5 The differences are minor, while the similarities will not be elaborated upon.

[0096] like Figure 8 As shown, in step S1113, the conversation content of at least one conversation round in any given conversation that is associated with the conversation topic of any given conversation is displayed.

[0097] In this embodiment, during a conversation with the agent, the user may generate content unrelated to the topic of the conversation. For example, the agent might guide the user to elaborate on their question to clarify their needs or correct typos. This type of content unrelated to the topic is generally not of interest to the user. By displaying only conversation content relevant to the topic, a higher density of information can be ensured, further improving the convenience and efficiency of historical conversation retrieval and enhancing the user experience.

[0098] In some embodiments, the session content of at least one session round included in any session that is associated with the session topic of any session can be displayed in the following manner.

[0099] The content of the conversation rounds that are related to the conversation topic of any given conversation is displayed by deleting or hiding the conversation content of at least one conversation round that is not associated with the conversation topic of any given conversation.

[0100] Figure 9 This is a schematic flowchart illustrating a session data processing method according to other embodiments of the present disclosure. Figure 9 and Figure 1 The difference is that, Figure 9 Steps S1011 to S1012 are Figure 1 One implementation of step S101 is described below. Figure 9 and Figure 1 The differences are minor, while the similarities will not be elaborated upon.

[0101] like Figure 9 As shown, in step S1011, the session topic and session time of the session content for each session round are obtained.

[0102] In step S1012, the conversation content of the multiple conversation rounds is clustered according to the conversation topic and conversation time of the conversation content of each conversation round to obtain at least one conversation, wherein each conversation includes at least one conversation round in which the conversation content belongs to the same conversation topic and the conversation time meets a preset time condition.

[0103] For example, no other session rounds occur within the session time range of at least one session round in each session; that is, the session time of at least one session round in each session is continuous and uninterrupted.

[0104] In this embodiment, the conversation content of multiple conversation rounds is clustered based on the conversation topic and conversation time to obtain at least one conversation. This ensures that the conversation rounds included in each conversation belong to the same conversation topic and the conversation time meets the time condition, thereby improving the accuracy of conversation clustering. This further enhances the convenience, efficiency, and accuracy of historical dialogue retrieval and improves the user experience.

[0105] Figure 10 This is a schematic flowchart illustrating a session data processing method according to other embodiments of the present disclosure. Figure 10 and Figure 1 The difference is that, Figure 10 Steps S104' to S106' of a session data processing method according to some embodiments of this disclosure are shown. Only the following descriptions will be provided. Figure 10 and Figure 1 The differences are minor, while the similarities will not be elaborated upon.

[0106] like Figure 10 As shown, in step S104', the user's request to modify key information for any session is received.

[0107] In step S105', the modification component is displayed to the user, the modification component including input controls.

[0108] In step S106', the key information of any session is modified according to the user's input content in the input control.

[0109] For example, a user can initiate a modification request for any key information by long-pressing or double-clicking it. For instance, the input control could be an input box, where the user can enter the key information they wish to modify to update any key information.

[0110] In this embodiment, users can modify key information of any conversation, making the key information of the conversation more in line with user habits, realizing personalized settings, further improving the convenience of historical conversation review, improving the efficiency of users viewing historical conversations, and enhancing user experience.

[0111] Figure 11 This is a schematic flowchart illustrating a session data processing method according to other embodiments of the present disclosure. Figure 11 and Figure 1 The difference is that, Figure 11 Steps S1021 and S1023 are Figure 1 One implementation of step S102 will be described below. Figure 11 and Figure 1 The differences are minor, while the similarities will not be elaborated upon.

[0112] like Figure 11 As shown, in step S1021, the time information of each session is determined according to the occurrence time of each session.

[0113] In step S1023, the user is shown key information and time information of the at least one session.

[0114] For example, time information is displayed as a timestamp.

[0115] In this embodiment, key information of each session is displayed to the user, along with the time information of each session. This makes the process of tracing back historical conversations clearer and more concise, further improving the convenience and efficiency of tracing back historical conversations, increasing the efficiency of users viewing historical conversations, and enhancing the user experience.

[0116] Figure 12 This is a schematic flowchart illustrating a session data processing method according to other embodiments of the present disclosure. Figure 12 and Figure 1 The difference is that, Figure 12 Steps S1022 and S1024 are Figure 1 One implementation of step S102 will be described below. Figure 12 and Figure 1 The differences are minor, while the similarities will not be elaborated upon.

[0117] like Figure 12 As shown, in step S1022, the display order of key information of the at least one session is determined based on the occurrence time of the at least one session and / or the number of at least one session rounds included in each session.

[0118] In step S1024, key information of the at least one session is displayed to the user according to the display order.

[0119] For example, key information from conversations that occurred later can be prioritized. Alternatively, key information from conversations with a larger number of rounds can be prioritized. Or, both the occurrence time and the number of rounds can be considered together.

[0120] In this embodiment, adjusting the display order of key information of at least one session according to the occurrence time of the session and / or the number of session rounds included in the session can further improve the convenience and efficiency of historical dialogue retrieval, increase the efficiency of users viewing historical dialogues, and enhance the user experience.

[0121] In some embodiments, different agents correspond to different historical conversation display interfaces for the user. For example, different agents' historical conversations correspond to different threads. For example, in the management of the conversation list of this disclosure, different agents are at the same level, and each agent corresponds to a historical conversation display interface. For example, the main agent and the content generating agent are at the same level.

[0122] The above are some embodiments of the session data processing method provided in this disclosure. The following will be combined with... Figure 13 The search methods in some embodiments of this disclosure are described.

[0123] Figure 13 This is a flowchart illustrating a search method according to some embodiments of the present disclosure.

[0124] like Figure 13 As shown, the search method includes: step S201, receiving search keywords input by a user; and step S202, displaying at least one key piece of information matching the search keywords to the user on a historical session display interface. The at least one key piece of information is at least a portion of the key information of at least one session displayed to the user in any embodiment of the session data processing method of this disclosure.

[0125] In this embodiment, users can also use search keywords to search for key information that matches the search keywords from the key information of at least one conversation displayed to the user based on the conversation data processing method in any embodiment of this disclosure. When the amount of key information data is large, the convenience and efficiency of historical conversation retrieval can be further improved, the efficiency of users viewing historical conversations can be increased, and the user experience can be enhanced.

[0126] The above are some search methods provided by embodiments of this disclosure. The following will combine... Figures 14-15 This disclosure describes the key information display and search methods for sessions in some embodiments.

[0127] Figure 14 This is a schematic diagram illustrating a historical session display interface according to some embodiments of the present disclosure.

[0128] like Figure 14 As shown, the user's historical conversation display interface with an intelligent agent includes key information 31 and key information 32 displayed to the user using the conversation data processing method in this embodiment of the disclosure. For example, key information 31 is "anime" and key information 32 is "historical drama".

[0129] In some embodiments, the historical session display interface may further include a cluster name 33 displayed to the user using the session data processing method described in the embodiments. For example, the cluster name 33 is "Location A Tourism". By performing a specific operation on the cluster name 33, the user can trigger the historical session display interface to display one or more key information corresponding to the cluster name 33.

[0130] In some embodiments, the historical session display interface may further include a search box 34. Users can enter search keywords in the search box, and based on the search method in this embodiment, the historical session display interface can display search results to the user. There are many ways to display search results, such as displaying search results in a search dropdown, highlighting search results, or emphasizing search results; this disclosure does not limit this approach.

[0131] Figure 15 This is a schematic diagram illustrating a history session display interface according to other embodiments of the present disclosure.

[0132] like Figure 15 As shown, users can trigger the historical session display interface by performing a specific operation on cluster name 33, which displays key information 331 and key information 332 corresponding to cluster name 33. For example, key information 331 is "food at location A", and key information 332 is "scenery at location A".

[0133] Figure 15 This is merely a way of displaying a cluster name and the key information corresponding to that cluster name, and does not constitute a specific limitation on this disclosure.

[0134] For example, the historical session display interface disclosed herein can be triggered by a control located in the settings interface of the agent, and the search entry can also be found on the settings page.

[0135] The above is a schematic diagram of the display and search methods in the embodiments of this disclosure. The following will combine... Figure 16 The present disclosure describes a session data processing apparatus in some embodiments.

[0136] Figure 16 This is a block diagram illustrating a session data processing apparatus according to some embodiments of the present disclosure.

[0137] like Figure 16 As shown, the session data processing device 16 includes a clustering module 161, a generation module 162, and a display module 163.

[0138] Clustering module 161 is configured to cluster the conversation content between the user and the agent in multiple conversation rounds to obtain at least one conversation, wherein each conversation includes at least one conversation round in which the conversation content belongs to the same conversation topic.

[0139] The generation module 162 is configured to generate key information for each session based on the session content of at least one session round in each session, wherein the key information for each session characterizes the session topic of each session.

[0140] The display module 163 is configured to display key information of at least one session to the user on the historical session display interface between the user and the agent.

[0141] Session data processing device 16 can be used to perform Figure 1 Steps S101 to S103. In some embodiments, the session data processing device 16 may also perform steps such as Figures 2 to 12 Any of the steps shown.

[0142] The above describes the session data processing apparatus in this disclosure embodiment. The following will be combined with... Figure 17 The search apparatus in some embodiments of this disclosure is described.

[0143] Figure 17 This is a block diagram illustrating a search apparatus according to some embodiments of the present disclosure.

[0144] like Figure 17 As shown, the search device 17 includes a receiving module 171 and a display module 172.

[0145] The receiving module 171 is configured to receive search keywords input by the user.

[0146] The display module 172 is configured to display at least one key piece of information matching the search keyword to the user in the historical session display interface. The at least one key piece of information is at least a portion of the key information of at least one session displayed to the user in the session data processing method of any embodiment of this disclosure.

[0147] It should be noted that the modules in any of the above devices are merely logical modules divided according to their specific functions, and are not used to limit the specific implementation method. For example, they can be implemented in software, hardware, or a combination of both. In actual implementation, the above modules can be implemented as independent physical entities, or they can be implemented by a single entity (e.g., a processor (CPU or DSP, etc.), integrated circuit, etc.). Furthermore, the modules shown in the accompanying drawings with dashed lines indicate that these modules may not actually exist, and the operations / functions they perform can be implemented by the processing circuitry itself.

[0148] The search apparatus described above is one of the embodiments of this disclosure.

[0149] Figure 18 This is a block diagram illustrating an electronic device according to some embodiments of the present disclosure.

[0150] like Figure 18 As shown, the electronic device 18 includes: a memory 181; and a processor 182 coupled to the memory 181, the processor 182 being configured to execute the session data processing method or search method described in any of the foregoing embodiments based on instructions stored in the memory 181.

[0151] Memory 181 is used to store one or more computer-readable instructions. Memory 181 may include any combination of various forms of computer-readable storage media, such as volatile memory and / or non-volatile memory, including but not limited to random access memory (RAM), dynamic random access memory (DRAM), static random access memory (SRAM), read-only memory (ROM), and flash memory. Memory 181 may, for example, store operating systems, application programs, bootloaders, databases, and other programs, as well as various application programs and various data.

[0152] The processor 182 is configured to execute computer-readable instructions to implement the session data processing method or search method described in any of the foregoing embodiments. Specific implementations of each step of the session data processing method or search method can be found in the above embodiments; repeated details will not be elaborated upon here.

[0153] The processor 182 and the memory 181 can communicate with each other directly or indirectly. For example, the processor 182 and the memory 181 can communicate via a network. The network can include a wireless network, a wired network, and / or any combination of wireless and wired networks. The processor 182 and the memory 181 can also communicate with each other via a system bus, which is not limited in this disclosure.

[0154] It should be noted that Figure 18 The components of the electronic device 18 shown are merely exemplary and not limiting; the electronic device 18 may also have other components as needed for the actual application. The processor 182 may use other components in the electronic device 18 to perform the desired functions.

[0155] The electronic device can be implemented by software, firmware and / or hardware, and can be integrated into an electronic device with the relevant application installed.

[0156] The above are some embodiments of electronic devices disclosed herein.

[0157] Figure 19 Block diagrams of electronic devices according to other embodiments of the present disclosure are shown.

[0158] Figure 19The electronic device 19 shown can be a computer system with a dedicated hardware structure, which can perform corresponding functions when the relevant application is installed.

[0159] Electronic devices include, but are not limited to, mobile terminals such as smartphones, laptops, personal digital assistants (PDAs), tablet PCs, portable multimedia players (PMPs), in-vehicle terminals (such as in-vehicle navigation terminals), wearable devices, and fixed terminals such as digital televisions and desktop computers.

[0160] like Figure 19 As shown, the Central Processing Unit (CPU) 191 performs various processes based on a program stored in the Read-Only Memory (ROM) 192 or a program loaded from the Storage Section 198 into the Random Access Memory (RAM) 193. The RAM 193 stores data required as needed when the CPU 191 performs various processes, etc. The CPU is merely exemplary; it could also be other types of processors, such as the various processors described above. The ROM 192, RAM 193, and Storage Section 198 can be various forms of computer-readable storage media. It should be noted that although... Figure 19 The diagram shows ROM 192, RAM 193 and storage section 198, but one or more of them may be combined or located in the same or different memory or storage modules.

[0161] CPU 191, ROM 192 and RAM 193 are interconnected via bus 194. Input / output interface 195 is also connected to bus 194.

[0162] The following components are connected to the input / output interface 195: input section 196, such as a touchscreen, touchpad, keyboard, mouse, image sensor, microphone, accelerometer, gyroscope, etc.; output section 197, including displays such as cathode ray tube (CRT), liquid crystal display (LCD), speakers, vibrators, etc.; storage section 198, including hard disk, magnetic tape, etc.; and communication section 199, including network interface cards such as LAN cards, modems, etc. The communication section 199 allows communication processing to be performed via a network such as the Internet. It is easy to understand that, although... Figure 19 The various devices or modules in the electronic device 19 shown communicate via bus 194, but they may also communicate via a network or other means, wherein the network may include a wireless network, a wired network, and / or any combination of wireless and wired networks.

[0163] As needed, drive 1910 is also connected to input / output interface 195. Removable media 1911, such as disks, optical disks, magneto-optical disks, semiconductor memories, etc., are installed on drive 1910 as needed, so that computer programs read from them can be installed into storage section 198 as needed.

[0164] When the above series of processes are implemented through software, the program constituting the software can be installed from a network such as the Internet or a storage medium such as a removable medium 1911.

[0165] According to embodiments of this disclosure, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, some embodiments of this disclosure include a computer program product that, when run on a computer, causes the computer to implement the session data processing method or search method described in any of the foregoing embodiments. The computer program product includes a computer program carried on a computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via communication section 199, or installed from storage section 198, or installed from ROM 192. When the computer program is executed by CPU 191, the session data processing method or search method of the embodiments of this disclosure is performed.

[0166] It should be noted that, in the context of this disclosure, a computer-readable medium can be a tangible medium that may contain or store programs for use by or in conjunction with an instruction execution system, apparatus, or device.

[0167] A computer-readable medium may be a computer-readable storage medium, a computer-readable signal medium, or any combination thereof.

[0168] Computer-readable storage media include, but are not limited to, systems, apparatuses, or devices that are electrical, magnetic, optical, electromagnetic, infrared, or semiconductor, or any combination thereof. More specific examples of computer-readable storage media may include, but are not limited to, electrical connections having one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof. In this disclosure, a computer-readable storage medium can be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. A computer program is stored on the computer-readable storage medium that, when executed by a processor, implements the session data processing method or search method described in any of the foregoing embodiments.

[0169] Computer-readable signal media may include data signals propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. Computer-readable signal media may also be any computer-readable medium other than computer-readable storage media, capable of sending, propagating, or transmitting programs for use by or in connection with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium may be transmitted using any suitable medium, including but not limited to: wires, optical fibers, RF (radio frequency), etc., or any suitable combination thereof.

[0170] The aforementioned computer-readable medium may be included in the aforementioned electronic device; or it may exist independently and not assembled into the electronic device.

[0171] In some embodiments, a computer program product is also provided, which, when run on a computer, causes the computer to implement the session data processing method or search method described in any of the above embodiments.

[0172] In some embodiments, a computer program is also provided, comprising: instructions that, when executed by a processor, cause the processor to perform the session data processing method or search method of any of the above embodiments. For example, the instructions may be embodied in computer program code.

[0173] In embodiments of this disclosure, computer program code for performing the operations of this disclosure can be written in one or more programming languages ​​or a combination thereof. These programming languages ​​include, but are not limited to, object-oriented programming languages ​​such as Java, Smalltalk, and C++, as well as conventional procedural programming languages ​​such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network (including a local area network (LAN) or a wide area network (WAN)), or it can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0174] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this disclosure. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0175] The functions described above can be performed, at least in part, by one or more hardware logic components. For example, without limitation, exemplary hardware logic components that can be used include: Field Programmable Gate Arrays (FPGAs), Application-Specific Integrated Circuits (ASICs), Application Standard Products (ASSPs), System-on-Chip (SoCs), Complex Programmable Logic Devices (CPLDs), and so on.

[0176] While specific embodiments of this disclosure have been described in detail by way of example, those skilled in the art should understand that the examples are for illustrative purposes only and not intended to limit the scope of this disclosure. Those skilled in the art should understand that modifications can be made to the above embodiments without departing from the scope and spirit of this disclosure. The scope of this disclosure is defined by the appended claims.

Claims

1. A method for processing session data, characterized in that, include: Cluster the conversation content between the user and the agent in multiple conversation rounds to obtain at least one conversation, wherein each conversation includes at least one conversation round in which the conversation content belongs to the same conversation topic; Based on the conversation content of at least one session round in each session, key information for each session is generated, wherein the key information for each session represents the conversation topic of each session; On the historical conversation display interface between the user and the intelligent agent, key information and cluster names of at least one conversation are displayed to the user. Each cluster name corresponds to key information of one or more conversations. The cluster name is obtained by clustering the key information of at least one conversation. Any cluster name is a first-level item, and the key information corresponding to any cluster name is a second-level item of the first-level item. For cluster names whose content volume of the involved sessions exceeds the threshold, delete the first-level items corresponding to the cluster name, and determine the key information of one or more sessions corresponding to the cluster name as new first-level items; The new secondary items are displayed, which are generated by clustering the new primary items.

2. The session data processing method according to claim 1, characterized in that, Each cluster name is used to summarize key information about sessions that share common characteristics.

3. The session data processing method according to claim 2, characterized in that, Also includes: In response to the user clicking on any cluster name on the historical session display interface, the historical session display interface displays key information of one or more sessions corresponding to the any cluster name to the user.

4. The session data processing method according to claim 1, characterized in that, Also includes: Cluster the session content involved in the new first-level project to obtain at least one session corresponding to the new first-level project; For each session in at least one session corresponding to the new primary project, key information of the session is generated based on the session content of at least one session round in the session, and used as a secondary project of the new primary project.

5. The session data processing method according to claim 2, characterized in that, Also includes: Receive the user's request to modify any cluster name; The modification component is displayed to the user, and the modification component includes an input control; Modify any cluster name based on the user's input in the input control.

6. The session data processing method according to any one of claims 1-5, characterized in that, Also includes: In response to the user clicking on key information of any session in the historical session display interface, the user is redirected from the historical session display interface to the session interface between the user and the agent. The session interface displays the session content of at least one session round included in any session to the user.

7. The session data processing method according to claim 6, characterized in that, In the conversation interface, the conversation content of at least one conversation round included in any one conversation is displayed to the user, including: If any of the sessions includes multiple session rounds, the session content of the session round that occurred earliest will be displayed first on the session interface; or Generate and display a summary of the conversation content for at least one session round included in any of the sessions; or Display the conversation content of at least one conversation round that is associated with the conversation topic of any given conversation.

8. The session data processing method according to claim 7, characterized in that, The session content displayed includes at least one session round within any given session that is associated with the topic of that given session, and includes: The content of the conversation rounds that are related to the conversation topic of any given conversation is displayed by deleting or hiding the conversation content of at least one conversation round that is not associated with the conversation topic of any given conversation.

9. The session data processing method according to any one of claims 1-5, characterized in that, Clustering the conversation content between the user and the agent across multiple session rounds yields at least one session including: Retrieve the topic and duration of the conversation content for each session round; Based on the conversation topic and conversation time of the conversation content in each conversation round, the conversation content of the multiple conversation rounds is clustered to obtain at least one conversation, wherein each conversation includes at least one conversation round in which the conversation content belongs to the same conversation topic and the conversation time meets a preset time condition.

10. The session data processing method according to any one of claims 1-5, characterized in that, Also includes: Receive the user's request to modify key information for any session; The modification component is displayed to the user, and the modification component includes an input control; Based on the user's input in the input control, modify the key information of any session.

11. The session data processing method according to any one of claims 1-5, characterized in that, The key information of the at least one session shown to the user includes: The time information of each session is determined based on the occurrence time of each session; The user is shown key information and time information of the at least one session.

12. The session data processing method according to any one of claims 1-5, characterized in that, The key information of the at least one session shown to the user includes: The order in which key information of the at least one session is displayed is determined based on the occurrence time of the at least one session and / or the number of at least one session rounds included in each session; According to the display order, key information of the at least one session is displayed to the user.

13. The session data processing method according to claim 1, characterized in that, For the user, different intelligent agents correspond to different historical session display interfaces.

14. A search method, characterized in that, include: Receive search keywords input by the user; On the historical session display interface, at least one key piece of information and at least one cluster name matching the search keyword are displayed to the user. The at least one key piece of information is at least a portion of the key piece of information of at least one session displayed to the user in the session data processing method as described in any one of claims 1 to 13, and the at least one cluster name is at least a portion of the cluster name of the at least one key piece of information displayed to the user in the session data processing method as described in any one of claims 1 to 13.

15. A session data processing apparatus, characterized in that, include: The clustering module is configured to cluster the conversation content between the user and the agent in multiple conversation rounds to obtain at least one conversation, wherein each conversation includes at least one conversation round in which the conversation content belongs to the same conversation topic; The generation module is configured to generate key information for each session based on the session content of at least one session round in each session, wherein the key information for each session characterizes the session topic of each session; The display module is configured to display key information and cluster names of at least one session to the user on the historical session display interface between the user and the agent. Each cluster name corresponds to key information of one or more sessions. The cluster name is obtained by clustering the key information of the at least one session. Any cluster name is a first-level item, and the key information corresponding to any cluster name is a second-level item of the first-level item. For cluster names whose content volume of the involved sessions exceeds a threshold, the first-level item corresponding to the cluster name is deleted, and the key information of one or more sessions corresponding to the cluster name is determined as a new first-level item. The new second-level item is displayed. The new second-level item is generated by clustering the new first-level item.

16. A search device, characterized in that, include: The receiving module is configured to receive search keywords input by the user; The display module is configured to display, on the historical session display interface, at least one key piece of information and at least one cluster name that matches the search keyword to the user, wherein the at least one key piece of information is at least a portion of the key piece of information of at least one session displayed to the user in the session data processing method as described in any one of claims 1 to 13, and the at least one cluster name is at least a portion of the cluster name of the at least one key piece of information displayed to the user in the session data processing method as described in any one of claims 1 to 13.

17. An electronic device, characterized in that, include: Memory; as well as A processor coupled to the memory, the processor being configured to execute the session data processing method as described in any one of claims 1 to 13 or the search method as described in claim 14, based on instructions stored in the memory.

18. A computer-readable storage medium, characterized in that, It stores computer program instructions that, when executed by a processor, implement the session data processing method as described in any one of claims 1 to 13 or the search method as described in claim 14.

19. A computer program product, characterized in that, Includes a computer program that, when executed by a processor, implements the session data processing method as described in any one of claims 1 to 13 or the search method as described in claim 14.

Images