Interactive content generation method and device, electronic equipment, storage medium and program product

Abstract

The embodiment of the invention provides an interactive content generation method and device, electronic equipment, a storage medium and a program product. The method comprises the following steps: acquiring target business content information, wherein the target business content information is associated with a target user; extracting a first business keyword based on the target business content information to obtain a first business keyword set; and according to the first service keyword set and preset interaction content attribute information, generating service interaction content corresponding to the target user. According to the embodiment of the invention, by utilizing the technical scheme, the generation modes of knowledge interaction contents in an enterprise can be enriched.

Description

Technical Field

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

[0002] Currently, in some applications, recommended interactive content can be displayed for users to interact based on the displayed interactive content. However, the generation method of the recommended interactive content is relatively simple. Summary of the invention

[0003] The embodiments of the present disclosure provide a method, device, electronic device, storage medium and program product for generating interactive content, so as to enrich the generation mode of interactive content.

[0004] In a first aspect, an embodiment of the present disclosure provides a method for generating interactive content, comprising:

[0005] Acquire target business content information, where the target business content information is associated with a target user;

[0006] Extracting first business keywords based on the target business content information to obtain a first business keyword set;

[0007] Business interactive content corresponding to the target user is generated according to the first business keyword set and preset interactive content attribute information.

[0008] In a second aspect, the embodiments of the present disclosure further provide a device for generating interactive content, including:

[0009] A first information acquisition module, used to acquire target service content information, wherein the target service content information is associated with a target user;

[0010] A keyword extraction module, configured to extract first business keywords based on the target business content information to obtain a first business keyword set;

[0011] The interactive content generation module is used to generate business interactive content corresponding to the target user according to the first business keyword set and preset interactive content attribute information.

[0012] In a third aspect, an embodiment of the present disclosure further provides an electronic device, including:

[0013] one or more processors;

[0014] a memory for storing one or more programs,

[0015] When the one or more programs are executed by the one or more processors, the one or more processors implement the method for generating interactive content as described in the embodiment of the present disclosure.

[0016] In a fourth aspect, the embodiments of the present disclosure further provide a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the method for generating interactive content as described in the embodiments of the present disclosure.

[0017] In a fifth aspect, the embodiments of the present disclosure further provide a computer program product. When the computer program product is executed by a computer, the computer implements the method for generating interactive content as described in the embodiments of the present disclosure.

[0018] The interactive content generation method, device, electronic device, storage medium and program product provided by the embodiments of the present disclosure generate business interactive content based on preset interactive content attribute information after extracting business keywords. Compared with the technical solution of directly inputting target business content information into a model and allowing the model to generate business interactive content based on the input target interactive information, it can enrich the generation method of business interactive content, improve the accuracy and practicality of the generated business interactive content, avoid the situation where the business interactive content does not support subsequent interactions, such as enriching the generation method of knowledge interactive content within an enterprise, avoiding the situation where accurate reply content of business interactive content cannot be generated, and improving the interactive effect based on business interactive content. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] The above and other features, advantages and aspects of the embodiments of the present disclosure will become more apparent with reference to the following detailed description in conjunction with the accompanying drawings. Throughout the accompanying drawings, the same or similar reference numerals represent the same or similar elements. It should be understood that the drawings are schematic and the originals and elements are not necessarily drawn to scale.

[0020] Figure 1 A flowchart of a method for generating interactive content provided by an embodiment of the present disclosure;

[0021] Figure 2 A schematic diagram of a flow chart of another method for generating interactive content provided by an embodiment of the present disclosure;

[0022] Figure 3 A schematic diagram of a process for obtaining key project words provided in an embodiment of the present disclosure;

[0023] Figure 4 A structural block diagram of a device for generating interactive content provided by an embodiment of the present disclosure;

[0024] Figure 5 A schematic diagram of the structure of an electronic device provided in an embodiment of the present disclosure. DETAILED DESCRIPTION

[0025] Embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although certain embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be construed as being limited to the embodiments described herein, which are instead provided for a more thorough and complete understanding of the present disclosure. It should be understood that the drawings and embodiments of the present disclosure are only for exemplary purposes and are not intended to limit the scope of protection of the present disclosure.

[0026] It should be understood that the various steps described in the method embodiments of the present disclosure may be performed in different orders and / or in parallel. In addition, the method embodiments may include additional steps and / or omit the steps shown. The scope of the present disclosure is not limited in this respect.

[0027] The term "including" and its variations used herein are open inclusions, i.e., "including but not limited to". The term "based on" means "based at least in part on". The term "one embodiment" means "at least one embodiment"; the term "another embodiment" means "at least one additional embodiment"; the term "some embodiments" means "at least some embodiments". The relevant definitions of other terms will be given in the following description.

[0028] It should be noted that the concepts such as "first" and "second" mentioned in the present disclosure are only used to distinguish different devices, modules or units, and are not used to limit the order or interdependence of the functions performed by these devices, modules or units.

[0029] It should be noted that the modifications of "one" and "plurality" mentioned in the present disclosure are illustrative rather than restrictive, and those skilled in the art should understand that unless otherwise clearly indicated in the context, it should be understood as "one or more".

[0030] The names of the messages or information exchanged between multiple devices in the embodiments of the present disclosure are only used for illustrative purposes and are not used to limit the scope of these messages or information.

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

[0032] Figure 1A flowchart of a method for generating interactive content provided in an embodiment of the present disclosure. The method can be executed by a device for generating interactive content, wherein the device can be implemented by software and / or hardware and can be configured in an electronic device, typically a computer, a mobile phone or a tablet computer. The method for generating interactive content provided in an embodiment of the present disclosure is suitable for generating interactive content of enterprise knowledge corresponding to the current user, such as generating interactive questions of enterprise knowledge corresponding to the current user. Figure 1 As shown, the method for generating interactive content provided in this embodiment may include:

[0033] S101: Acquire target service content information, where the target service content information is associated with a target user.

[0034] The target user may be the current user, such as the user for whom business interaction content corresponding to the target user is currently required to be generated. The target business content information may be understood as business content information associated with the target user, such as business content information of the business in which the target user has participated in the most recent preset time period. This business content information may be understood as transaction content information of the transaction (such as a project, etc.) handled by the target user, such as the work content information of the target user, etc.

[0035] Specifically, business content information associated with the target user can be obtained. For example, the business content information of the target user can be determined based on the target user's interactive event information, such as determining the target user's business content information based on the target user's interactive event information of at least two types of interactive events, so as to further improve the comprehensiveness of the determined business content information.

[0036] The target user's interactive events may include, but are not limited to, session events, meeting events, and / or document editing events, etc. For example, at least part of session information of a session in which the target user participates, at least part of meeting information of a meeting in which the target user attends, and / or at least part of document information of a document edited by the target user may be obtained as the target business content information associated with the target user.

[0037] In this embodiment, when acquiring the target business content information, part or all of the business content information of the target user may be acquired as the target business content information associated with the target user. Considering that the business handled by the target user may change over time, in some examples, the business content information of the target user within a recent preset time length may be acquired as the target business content information of the target user, so as to generate business interaction content associated with the business recently handled by the target user based on this target business content information, thereby improving the relevance between the generated business interaction content and the business recently handled by the target user.

[0038] In some embodiments, after obtaining the business content information associated with the target user, the business content information may not be pre-processed such as information filtering, and the obtained business content information may be directly used as the target business content information, and business interaction content corresponding to the target user may be subsequently generated based on the target business content information to increase the speed of generating business interaction content.

[0039] In some embodiments, after obtaining the business content information associated with the target user, the business content information can be further pre-processed such as information filtering, and the pre-processed business content information can be used as the target business content information. Subsequently, business interaction content corresponding to the target user is generated based on the pre-processed target business content information, so as to further improve the correlation between the generated business interaction content and the business handled by the target user, and avoid generating business interaction content that is unrelated to the business handled by the target user.

[0040] Optionally, obtaining the target business content information includes: obtaining original business content information within a recent preset time length, the original business content information including at least one of session information, meeting information and document information; extracting business content information associated with the target user's participated business from the original business content information as the target business content information of the target user.

[0041] Among them, the original business content information can be understood as the business content information of the target user that is initially obtained within the most recent preset time length, such as the session information, meeting information and / or document information of the target user that is initially obtained within the most recent preset time length. The target business content information can be understood as the business content information associated with the target user's participated business within the most recent preset time length, which is obtained based on the original business content information. The preset time length can be flexibly set as needed. For example, the preset time length can be set to 7 days, 14 days or 30 days, etc. The participated business can be understood as the business that has been participated in. In some examples, the participated business can be the business in which the target user participates and is already in the execution stage. The following is explained using this case as an example.

[0042] Exemplarily, at least one of the target user's session information within a recent preset time length, meeting information of meetings participated in by the target user within a recent preset time length, and / or document information of documents edited by the target user within a recent preset time length can be obtained as the target user's original business content information within the recent preset time length.

[0043] After obtaining the original business content information of the target user within the most recent preset time length, the original business content information can be pre-processed, such as filtering the original business content information to filter out content that is not related to the business and / or content that is associated with the business that has not yet been started, and obtain business content information associated with the business that the target user has participated in within the most recent preset time length as the target business content information.

[0044] When acquiring the session information of the target user within the most recent preset time length, illustratively, the message content of each session message sent by the target user within the most recent preset time length may be acquired as the session information of the target user within the most recent preset time length, the message content of the session message of each session in which the target user is located within the most recent preset time length may be acquired as the session information of the target user within the most recent preset time length, or the message content of the session message of the target session in which the target user is located within the most recent preset time length may be acquired as the session information of the target user within the most recent preset time length, etc. The target session may be understood as a session in which the target user is located and in which the target user participates within the most recent preset time length, such as a session in which the target user has sent a session message within the most recent preset time length.

[0045] In some implementations, the session summary information of the target session within the most recent preset time length may be obtained as the session information of the target user, so as to reduce the amount of session information required to be obtained and the amount of calculation required to generate business interaction content based on the obtained session information, thereby increasing the speed of generating business interaction information. At this time, optionally, the session information includes the session summary information of the target session, and the target session is a session in which the target user sends a session message within the most recent preset time length.

[0046] The conversation summary information can be understood as the summary information obtained by summarizing the conversation content information of the target conversation within the most recent preset time length. Exemplarily, in the case where the conversation summary information of the target conversation has been pre-generated, the pre-generated conversation summary information of the target conversation within the most recent preset time length can be directly obtained; in the case where the conversation summary information of the target conversation does not exist in advance, the conversation summary information of the target conversation within the most recent preset time length can be generated based on the conversation content information of the target conversation within the most recent preset time length, such as inputting the conversation content information of the target conversation within the most recent preset time length into the information summary model obtained by pre-training, and summarizing the conversation content information of the target conversation within the most recent preset time length through this information summary model to obtain the conversation summary information of the target conversation within the most recent preset time length.

[0047] When obtaining the meeting information of the target user within the most recent preset time length, illustratively, at least part of the meeting content information of the meeting in which the target user participated within the most recent preset time length can be obtained as the meeting information of the target user within the most recent preset time length. Among them, the meeting content information can be understood as the content information of the meeting, such as the voice content information of each participant in the meeting or the text information generated by voice recognition of the voice content information. The at least part of the meeting content information obtained may include but is not limited to the meeting content information corresponding to the target user, such as the voice content information of the target user in the meeting or the text information generated by voice recognition of the voice content information.

[0048] In some implementations, the meeting summary information of the meetings that the target user has participated in within a recent preset time period can be obtained as the meeting information of the target user, so as to reduce the amount of meeting information required to be obtained and the amount of calculation required to generate business interaction content based on the obtained meeting information, thereby increasing the speed of generating business interaction information. At this time, optionally, the meeting information includes the meeting summary information of the meetings that the target user has participated in.

[0049] Among them, the meeting summary information of a certain meeting can be the summary information obtained by summarizing the meeting content of this meeting. Exemplarily, in the case where the meeting summary information has been pre-generated for the meeting participated by the target user, the pre-generated meeting summary information of the meeting participated by the target user within the most recent preset time length can be directly obtained; in the case where there is no pre-generated meeting summary information for the meeting participated by the target user, the session summary information of the meeting participated by the target user within the most recent preset time length can be generated based on the meeting content information of the meeting participated by the target user within the most recent preset time length, such as inputting the meeting content information of the meeting participated by the target user within the most recent preset time length into the information summary model obtained by pre-training, and summarizing the meeting content information of the meeting participated by the target user within the most recent preset time length through this information summary model, so as to obtain the meeting summary information of each meeting participated by the target user within the most recent preset time length.

[0050] When acquiring the document information of the target user within a recent preset time length, illustratively, at least a portion of the document content information of the document edited by the target user within a recent preset time length may be acquired as the document information of the target user.

[0051] In some embodiments, the document identification information of the document edited by the target user within the most recent preset time length and / or the edited content information of the target user in the document can be obtained as the document information of the target user within the most recent preset time length, so as to reduce the amount of document information required to be obtained and the amount of calculation required to generate business interaction content based on the obtained document information, thereby improving the generation speed of business interaction information. At this time, optionally, the document information includes the document identification information and / or edited content information of the document edited by the target user. Among them, the document identification information can be understood as the identification information of the document. Considering that the title of the document can reflect the theme of the document to a certain extent, optionally, this document identification information can include but is not limited to the title of the document. The edited content information can be understood as the content information of the content edited by the target user in the document, such as the content of the text line edited by the target user in the document. In order to ensure the semantic integrity of the edited content information, the edited content information can further include the content of the adjacent text lines of the text line edited by the target user in the document.

[0052] It should be noted that the information obtained by the embodiment of the present disclosure (such as the target business content information) is obtained under the premise of full authorization by the relevant user. For example, only when the target user authorizes the acquisition of the target business content information associated with it, such as when the target user's acquisition authorization information for the target business content information associated with it is obtained, the embodiment of the present disclosure will obtain the target business content information associated with the target user, so as to generate the business interaction content corresponding to the target user based on this target business content information; and when the target user is not authorized to obtain the target business content information associated with it, the embodiment of the present disclosure will not obtain the target business content information associated with the target user. At this time, optionally, before the acquisition of the target business content information, it also includes: obtaining the target user's acquisition authorization information for the target business content information. Among them, the acquisition authorization information for the target business content information can be understood as the authorization information for obtaining the target business content.

[0053] S102: Extract first business keywords based on the target business content information to obtain a first business keyword set.

[0054] The first business keyword may be a business keyword extracted from the target business content information. The business keyword may be understood as a keyword of the business, which may include but is not limited to a business name and / or a business key description word, etc. The first business keyword set may be a set of extracted first business keywords, and the first business keyword set may include at least one first business keyword.

[0055] Exemplarily, after the target service content information of the target user is acquired, the first service keyword may be extracted from the target service content information of the target user, and a first service keyword set including the first service keywords extracted from the target service content information is generated.

[0056] In this embodiment, the method for extracting the first business keyword is not limited.

[0057] In some embodiments, considering that the business keywords of the business in which the target user participates generally appear repeatedly in the business content information of the target user, the words and / or short sentences that meet the preset conditions and are associated with the business can be obtained from the target business content information as the first business keyword of the target user. For example, the words and / or short sentences with the highest number of occurrences and a set number of words and / or short sentences associated with the business can be obtained from the target business content information as the first business keyword; or the words and / or short sentences that are associated with the business and have a number of occurrences greater than or equal to a preset number threshold can be obtained from the target business content information as the first business keyword, and so on. The set number and the preset number threshold can be set as needed, and this embodiment does not limit this.

[0058] In some embodiments, a business keyword extraction model for extracting business keywords can be pre-trained. Thus, after obtaining the target business content information associated with the target user, the first business keyword in the target business content information can be extracted through this business keyword extraction model, such as inputting the target business content information into the pre-trained business keyword extraction model, and obtaining the business keyword output by the business keyword extraction model as the first business keyword, so as to further improve the accuracy of the extracted business keywords. At this time, optionally, the first business keyword extracted based on the target business content information includes: inputting the target business content information into the business keyword extraction model, and extracting the first business keyword in the target business content information through the business keyword extraction model. Among them, the business keyword extraction model can be understood as a model for extracting business keywords. The training method and type of the business keyword extraction model are not limited. Exemplarily, the business keyword extraction model can include but is not limited to a large model.

[0059] S103: Generate business interactive content corresponding to the target user according to the first business keyword set and preset interactive content attribute information.

[0060] Among them, the business interaction content can be understood as the interactive content associated with the business in which the target user participates. The business interaction content can be used for the target user to interact with the business in which the target user participates. For example, the business interaction content can be a candidate interactive message to be sent, so that the target user can interact with the message based on one or more candidate interactive messages displayed; and / or, the business interaction content can contain questions associated with the business in which the target user participates, so that the target user can interact by answering the questions contained in the business interaction content, or by obtaining answers to the questions contained in the business interaction content, and so on.

[0061] The pre-set interactive content attribute information can be understood as the attribute information that the business interactive content to be generated must have. The interactive content attribute information can be set as needed, and this embodiment does not limit this. Exemplarily, the interactive content attribute information may include sentence information of the business interactive content to be generated, such as candidate suffixes of the business interactive content to be generated, and so on. The pre-set interactive content attribute information can be configured in the form of text information; it can also be configured in the form of an interactive content template, such as pre-configuring one or more interactive content templates that meet this interactive content attribute information, and presenting the pre-set interactive content attribute information in the form of an interactive content template. The following takes this case as an example for explanation.

[0062] Exemplarily, business interaction content corresponding to the target user can be generated based on the first business keyword set and pre-selected interactive content attribute information. For example, for each first business keyword in the first business keyword set, the first business keyword can be added to the corresponding position of each interactive content template to obtain business interaction content generated based on the first business keyword.

[0063] After obtaining the business interaction content corresponding to the target user, the generated business interaction content can be stored, and when the preset display conditions of the business interaction content are met, the stored one or more business interaction content can be displayed to the target user. For example, when it is detected that the page currently viewed by the target user is a preset page containing a target area, such as when a page display request for the preset page is received from the target user, a set number of business interaction content can be obtained from the stored business interaction content corresponding to the target user, and when the preset page is displayed, the business interaction content is displayed in the target area of ​​the preset page, so that the target user can interact based on the displayed business interaction content.

[0064] In this embodiment, the interactive mode based on the displayed business interactive content is not limited. Optionally, the business content generation method may also include: displaying the business interactive content in a target area, the business interactive content including questions related to the business; and generating reply content corresponding to the question in response to a triggering operation on the business interactive content.

[0065] The target area can be understood as an area for displaying the generated business interaction content, that is, a display area for the business interaction content. The preset page where the target area is located is not limited. Optionally, the target area is located in at least one of the conversation page of the instant messaging tool, the search page of the instant messaging tool, the online document page and the conference page. For example, the target area can be set in the conversation page of the instant messaging tool, the search page of the instant messaging tool, the online document page and / or the conference page, so that the business interaction content is displayed in the target area of ​​the above page when the above page is displayed. The instant messaging tool can be a tool for instant messaging, such as an application or program module for instant messaging. The conversation page of the instant messaging tool can be understood as a page where users view and send conversation messages, such as a conversation page of one or more conversations where the target user is located. The search page of the instant messaging tool can be understood as a page used for searching in the instant messaging tool, and the content supported by this search page is not limited. The online document page can be a page associated with an online document, such as a display page of an online document, etc. The conversation page can be a page associated with a conference, such as a video conference page and / or an audio conference page, etc. The reply content corresponding to a question can be understood as the content used to reply to this question, so the reply content can include the answer to this question.

[0066] Exemplarily, when displaying a page with a target area, such as when displaying a conversation page of an instant messaging tool, a search page of an instant messaging tool, an online document page and / or a conversation page, business interaction content containing questions related to the business can be displayed in the target area of ​​the currently displayed page; when a trigger operation for this business interaction content is received, such as when it is detected that a target user triggers a certain business interaction content that is displayed, reply content corresponding to the questions contained in this business interaction content can be generated for the target user to view.

[0067] In the above implementation, the business interaction content may include questions related to the business, such as questions related to the business in which the target account participates, such as business progress questions. Therefore, the reply content generated based on the business interaction content can be used to reply to the questions included in the business interaction content. Taking the business interaction content as a business progress question as an example, it can support users to quickly obtain the progress of the corresponding business by triggering the business interaction information displayed in the target area, without the need for user input, so as to simplify the operations required by users to obtain the business progress of the business they participate in.

[0068] In this embodiment, the method of generating the reply content corresponding to the question contained in the business interaction content is not limited. Optionally, generating the reply content corresponding to the question includes: generating a reply window in the page currently displaying the business interaction content, and displaying the reply content in the reply window; or calling up a target session window in an instant messaging tool, and generating the reply content in the target session window.

[0069] In some examples, when a trigger operation is received from a target user for a business interaction content, a reply window may be displayed on the page currently displaying the business interaction content, and reply content corresponding to the question contained in the business interaction content may be displayed in the reply window.

[0070] In some examples, when a target user triggers a certain business interaction content, a target conversation window of an instant messaging tool associated with the currently displayed page can be called up, and the reply content corresponding to the question contained in the business interaction content can be displayed in the target conversation window. For example, a conversation window between a target user and a virtual object in an instant messaging tool can be called up, and the business interaction content triggered by the target user can be displayed in the conversation window in the form of a conversation message sent by the target user, and, in response to the display of the business interaction content in the conversation window, the reply content message corresponding to the question contained in the business interaction content can be displayed in the conversation window in the form of a conversation message sent by the virtual object. The virtual object can be, for example, an intelligent assistant, a conversation robot, or a virtual contact.

[0071] The interactive content generation method provided in this embodiment obtains target business content information associated with the target user; extracts a first business keyword based on the target business content information to obtain a first business keyword set; generates business interactive content corresponding to the target user based on the first business keyword set and the pre-set interactive content attribute information. This embodiment utilizes the above technical solution to generate business interactive content based on the pre-set interactive content attribute information after extracting the business keywords. Compared with the technical solution of directly inputting the target business content information into the model and having the model generate business interactive content based on the input target interactive information, it can enrich the generation method of business interactive content, improve the accuracy and practicality of the generated business interactive content, avoid the situation where the business interactive content does not support subsequent interactions, such as enriching the generation method of knowledge interactive content within the enterprise, avoiding the situation where accurate reply content of business interactive content cannot be generated, and improving the interactive effect based on business interactive content.

[0072] Figure 2 A flow chart of another method for generating interactive content provided for an embodiment of the present disclosure. The scheme in this embodiment can be combined with one or more optional schemes in the above-mentioned embodiments. Optionally, generating business interactive content corresponding to the target user according to the first business keyword set and pre-set interactive content attribute information includes: obtaining the union of the first business keyword set and the second business keyword set as the third business keyword set of the target user, the second business keyword set being a set of second business keywords of associated businesses, and the associated businesses having a preset association relationship with the target user; generating business interactive content corresponding to the target user according to the third business keyword set and pre-set interactive content attribute information.

[0073] Correspondingly, such as Figure 2 As shown, the method for generating interactive content provided in this embodiment may include:

[0074] S201: Acquire target service content information, where the target service content information is associated with a target user.

[0075] S202: Extract first business keywords based on the target business content information to obtain a first business keyword set.

[0076] S203: Obtain a union of the first business keyword set and the second business keyword set as a third business keyword set for the target user, wherein the second business keyword set is a set of second business keywords for associated services, and the associated services have a preset association relationship with the target user.

[0077] Among them, the second business keyword can be understood as a business keyword of the target user's associated business, such as the business name of the target user's associated business. The target user's associated business can be understood as a business that has a preset association relationship with the target user. This preset association relationship is not limited. For example, this preset association relationship may include a follow relationship, a subscription relationship, and / or a favorite relationship, etc. Taking the preset association relationship as a subscription relationship as an example, the target user's associated business may be a business subscribed by the target user; the second business keyword may be a business keyword of the business subscribed by the target user, such as the business name of the business subscribed by the target user, etc.

[0078] The second business keyword set can be understood as a set of second business keywords. The second business keyword set can include at least one second business keyword. The third business keyword set can be understood as the union of the first business keyword set and the second business keyword set, such as the set of the first business keyword and the second business keyword.

[0079] Exemplarily, after extracting the first business keyword set of the target user, you can further obtain the union of this first business keyword set and the second business keyword set of the target user's associated business as the third business keyword set of the target user, such as obtaining each first business keyword in the first business keyword set and each second business keyword in the second business keyword set to constitute the third business keyword set of the target user.

[0080] S204: Generate business interactive content corresponding to the target user according to the third business keyword set and preset interactive content attribute information.

[0081] In this embodiment, after obtaining the third business keyword set of the target user, business interaction content with the target user object can be generated based on the third business keyword set and the pre-set interactive content attribute information. For example, for each business keyword in the third business keyword set, this business keyword can be added to the corresponding position of each pre-set interactive content template to obtain the business interaction content generated based on this business keyword.

[0082] In some implementations, after extracting the first business keyword set of the target user, the first business keyword can also be deduplicated to avoid the situation where duplicate business keywords exist in the third business keyword set based on which the business interaction content of the target user is generated, thereby avoiding the situation where duplicate business interaction content is generated. At this time, optionally, before obtaining the union of the first business keyword set and the second business keyword set, it also includes: deduplicating the first business keyword in the first business keyword set.

[0083] In the above implementation, the deduplication processing method for the first business keyword in the first business keyword set is not limited. For example, for each first business keyword in the first business keyword set, based on other first business keywords other than the first business keyword in the first business keyword set, each second business keyword in the second business keyword set, and / or the associated keywords of each second business keyword, deduplication processing can be performed on the first business keyword to remove the repeated first business keywords in the first business keyword set and / or remove the first business keywords that are repeated with the second business keywords in the second business keyword set or the associated keywords of the second business keywords.

[0084] Optionally, the deduplication processing of the first business keywords in the first business keyword set includes at least one of the following: deduplication processing of the first business keywords based on the similarity between different first business keywords in the first business keyword set; deduplication processing of the first business keywords in the first business keyword set based on the similarity between the first business keywords in the first business keyword set and each second business keyword in the second business keyword set; deduplication processing of the first business keywords in the first business keyword set based on the similarity between the first business keywords in the first business keyword set and the associated keywords of the second business keywords.

[0085] The associated keywords of the second business keyword can be understood as business keywords associated with the second business keyword, such as keywords corresponding to the same business as the second business keyword. Taking the second business keyword as the business name of the associated business with a preset association relationship with the target user as an example, the associated keywords of the second business keyword can include an alias of the associated business corresponding to the second business keyword or a key description of the associated business, etc.

[0086] Exemplarily, for each first business keyword in the first business keyword set, the similarity between the first business keyword and each other first business keyword in the first business keyword set except the first business keyword, each second business keyword in the second business keyword set and / or the associated keywords of each second business keyword can be calculated respectively, and when there are other first business keywords, second business keywords or associated keywords whose similarity meets the preset similarity condition, it is determined that the first business keyword is a duplicate of them, and the first business keyword is deleted from the first business keyword set.

[0087] The method for determining the similarity between two keywords (such as the first business keyword, the second business keyword, or the associated keyword) is not limited. In some examples, the similarity can be characterized by similarity, and this similarity can be calculated based on the edit distance and / or semantic similarity between the two keywords, etc., which is not limited in this embodiment. Taking the similarity as an example of characterizing the similarity, illustratively, when the similarity between the two keywords is greater than a preset similarity threshold, the two keywords are determined to be duplicate keywords.

[0088] The interactive content generation method provided in this embodiment generates business interactive content with a target user object based on the union of the extracted first business keyword set and the second business keyword set of the target user's associated business. This can further improve the comprehensiveness of the business keywords used when generating business interactive content, thereby further enriching the generated business interactive content.

[0089] Figure 3 A schematic diagram of a key project word acquisition process provided by an embodiment of the present disclosure. In an optional embodiment, the target business content information is work content information, the business interaction content is project progress issues, and the business keyword extraction model is a large model. Figure 3 As shown, this embodiment can identify key project words (i.e., business keywords) to determine key project words such as the project name of the project that the user (i.e., the user corresponding to the target user) is following. After obtaining the key project words, a pre-set suffix (i.e., interactive content attribute information) can be added after the key project words, and combined into project progress questions (i.e., business interactive content) for sending, so that users can quickly learn about the progress of the corresponding project by triggering the pre-generated project progress questions. This pre-set suffix can be flexibly set as needed. For example, this suffix can include but is not limited to "What is the latest progress?", "What changes have occurred in data indicators recently?", "What risks are there in the near future?", "What are the main goals?" and / or "What are the benefits?", etc.

[0090] In this embodiment, considering that the key projects that users are concerned about usually appear repeatedly in the user's daily work information, the key project words can be extracted through the pre-trained model, and project progress questions can be generated based on the extracted keywords for display. Figure 3 As shown, in this embodiment, the process of obtaining key item words can be described as follows:

[0091] A1. Obtain work information (i.e., original business content information) associated with the target user, including the target user's session summary information (i.e., session information), meeting summary information (i.e., meeting information), and edited document information (i.e., document information) within the last N days (i.e., a preset time length).

[0092] The session summary information may be the summary information of the session messages of all the sessions (i.e., the target session) in which the target user has been active in the last N days, which may further include the identification information of the sender of each session message. The meeting summary information may be the summary information of the meeting content of the meetings that the target user has participated in the last N days. The edited document information may be the document content edited by the target user in the last N days, and the document content edited by different users in the same document may be different.

[0093] In this embodiment, in the stage of obtaining input data, information can be filtered according to the operations of the target user, for example, only the session summary information of the target user's active sessions, the document content edited by the target user, and the meeting summary information of the meetings in which the target user has participated are obtained, so that the subsequent large model can identify key project words. Other weakly related ones, such as documents that have not been edited after the target user has displayed them, and the session summary information of the target user in inactive sessions, will not be sent to the large model, so as to characterize the work characteristics of the target user and filter out the work content that the user corresponding to the target user is concerned about.

[0094] When acquiring work information, for example, the work information of the target user may be acquired once every M days or more. For example, when a target user's interface display request for a preset interface is received and the time from the last acquisition of the target user's work information is greater than or equal to M days, the work information of the target user is acquired and sent to the large model to identify key project words after filtering. When acquiring the work information of the target user, considering that only M days of work information are acquired, the work information may be relatively small, resulting in insufficient context, so for example, the work information of the target user for the most recent N days may be acquired each time, and N may be greater than M.

[0095] A2. Preprocess the user work information obtained above, including data filtering and / or unifying the format, etc., to obtain preprocessed data (ie, target business content information).

[0096] Among them, when filtering data, the content that is not related to the work and / or the content that is planned to be completed later but has not yet made progress (ToDo items, such as work plans and / or content related to projects that have not yet been started, etc.) in the obtained work information can be filtered to remove interference items. When unifying the format, for example, data from different data sources (i.e., work information) can be unified into the same format to facilitate the understanding of the large model. In some examples, preprocessing of the obtained work information can be achieved by a preset processing method or a preprocessing model obtained by pre-training, without the need for preprocessing by the large model, so as to reduce the cost of preprocessing.

[0097] A3. Input the processed data into the big model and obtain the key words extracted by the big model.

[0098] Exemplarily, the processed data and the task requirement information (such as prompt information) of this keyword extraction task can be input into the big model, and the key project words input into the big model can be obtained.

[0099] A4. Remove duplicates from the extracted key words.

[0100] For example, the extracted key project words can be deduplicated; the extracted key project words and project words to which the target user has subscribed (i.e., the second business keyword) can be deduplicated; and / or, key description words or aliases (i.e., associated keywords) of the project words can be extracted from the project information of the project words to which the target user has subscribed (such as a project weekly report), and the key description words or aliases can be used to assist in deduplicating the extracted key project words.

[0101] A5. Save the deduplicated key project words and the project words subscribed by the target user as key project words (i.e., save the third business keyword set), and when the target user has a display demand for project progress questions, obtain at least one of the saved project words, generate a project progress question and push it to the target user for display.

[0102] By adopting the above-mentioned technical solution, compared with the technical solution of directly inputting the session information of the target user as work information into the big model and generating project progress questions by the big model, this embodiment can avoid the situation where project progress questions are generated for projects with no progress or the situation where project progress questions with no answers are generated, and can improve the comprehensiveness and accuracy of the generated project progress questions and improve the interactive effect of the generated project progress questions.

[0103] Figure 4 This is a structural block diagram of an interactive content generation device provided by an embodiment of the present disclosure. The device can be implemented by software and / or hardware, and can be configured in an electronic device, typically a computer, a mobile phone, or a tablet computer, and can generate business interactive content corresponding to the current user by executing the interactive content generation method, such as generating a business question corresponding to the current user. Figure 4 As shown, the interactive content generation device provided in this embodiment may include: a first information acquisition module 401, a keyword extraction module 402 and an interactive content generation module 403, wherein:

[0104] The first information acquisition module 401 is used to acquire target service content information, where the target service content information is associated with a target user;

[0105] A keyword extraction module 402, configured to extract first business keywords based on the target business content information to obtain a first business keyword set;

[0106] The interactive content generating module 403 is used to generate business interactive content corresponding to the target user according to the first business keyword set and preset interactive content attribute information.

[0107] The interactive content generation device provided in this embodiment obtains target business content information associated with the target user through a first information acquisition module; extracts a first business keyword based on the target business content information through a keyword extraction module to obtain a first business keyword set; generates business interactive content corresponding to the target user through an interactive content generation module based on the first business keyword set and pre-set interactive content attribute information. This embodiment utilizes the above technical solution to generate business interactive content based on pre-set interactive content attribute information after extracting the business keywords. Compared with the technical solution of directly inputting the target business content information into the model and generating business interactive content based on the input target interactive information by the model, it can enrich the generation method of business interactive content, improve the accuracy and practicality of the generated business interactive content, avoid the situation where the business interactive content does not support subsequent interactions, such as enriching the generation method of knowledge interactive content within the enterprise, avoiding the situation where accurate reply content of business interactive content cannot be generated, and improving the interactive effect based on business interactive content.

[0108] Optionally, the first information acquisition module 401 can be specifically used to: obtain original business content information within a recent preset time length, the original business content information including at least one of session information, meeting information and document information; extract business content information associated with the target user's participated business from the original business content information as the target business content information of the target user.

[0109] Optionally, the session information includes session summary information of the target session, where the target session is a session in which the target user sends session messages within a recent preset time length; the meeting information includes meeting summary information of the meeting in which the target user participates; and the document information includes document identification information and / or editing content information of the document edited by the target user.

[0110] Optionally, the keyword extraction module 402 may be specifically configured to: input the target business content information into a business keyword extraction model, and extract a first business keyword from the target business content information through the business keyword extraction model.

[0111] Optionally, the interactive content generation module 403 can be specifically used to: obtain the union of the first business keyword set and the second business keyword set as the third business keyword set of the target user, the second business keyword set is a set of second business keywords of related businesses, and the related businesses have a preset association relationship with the target user; generate business interactive content corresponding to the target user according to the third business keyword set and pre-set interactive content attribute information.

[0112] Furthermore, the interactive content generation device may further include: a deduplication processing module, configured to perform deduplication processing on the first business keyword in the first business keyword set before obtaining the union of the first business keyword set and the second business keyword set.

[0113] Optionally, the deduplication processing module can be specifically used to perform at least one of the following: deduplication processing of the first business keywords based on the similarity between different first business keywords in the first business keyword set; deduplication processing of the first business keywords in the first business keyword set based on the similarity between the first business keywords in the first business keyword set and each second business keyword in the second business keyword set; deduplication processing of the first business keywords in the first business keyword set based on the similarity between the first business keywords in the first business keyword set and the associated keywords of the second business keywords.

[0114] Furthermore, the interactive content generation device may also include: a content display module, used to display the business interactive content in a target area, the business interactive content including questions related to the business; and a reply content generation module, used to generate reply content corresponding to the question in response to a triggering operation on the business interactive content.

[0115] Optionally, the reply content generation module can be specifically used to: generate a reply window in the page currently displaying the business interaction content, and display the reply content in the reply window; or, call up a target session window in an instant messaging tool, and generate the reply content in the target session window.

[0116] Optionally, the target area is located in at least one of a conversation page of an instant messaging tool, a search page of an instant messaging tool, an online document page, and a conference page.

[0117] Furthermore, the interactive content generation device may further include: a second information acquisition module, which is used to acquire the target user's authorization information for the target business content information before acquiring the target business content information.

[0118] The interactive content generation device provided in the embodiment of the present disclosure can execute the interactive content generation method provided in any embodiment of the present disclosure, and has the functional modules and beneficial effects corresponding to the interactive content generation method. For technical details not described in detail in this embodiment, please refer to the interactive content generation method provided in any embodiment of the present disclosure.

[0119] Reference below Figure 5 , which shows a schematic diagram of the structure of an electronic device (such as a terminal device or a server) 500 suitable for implementing the embodiment of the present disclosure. The terminal device in the embodiment of the present disclosure may include but is not limited to mobile terminals such as mobile phones, notebook computers, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), vehicle-mounted terminals (such as vehicle-mounted navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc. Figure 5 The electronic device shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present disclosure.

[0120] like Figure 5 As shown, the electronic device 500 may include a processing device (e.g., a central processing unit, a graphics processing unit, etc.) 501, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 502 or a program loaded from a storage device 508 into a random access memory (RAM) 503. In the RAM 503, various programs and data required for the operation of the electronic device 500 are also stored. The processing device 501, the ROM 502, and the RAM 503 are connected to each other via a bus 504. An input / output (I / O) interface 505 is also connected to the bus 504.

[0121] Typically, the following devices may be connected to the I / O interface 505: an input device 506 including, for example, a touch screen, a touch pad, a keyboard, a mouse, a camera, a microphone, an accelerometer, a gyroscope, etc.; an output device 507 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; a storage device 508 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 509. The communication device 509 may allow the electronic device 500 to communicate with other devices wirelessly or by wire to exchange data. Although Figure 5 The electronic device 500 is shown with various devices, but it should be understood that it is not required to implement or possess all the devices shown. More or fewer devices may be implemented or possessed instead.

[0122] In particular, according to an embodiment of the present disclosure, the process described above with reference to the flowchart can be implemented as a computer software program. For example, an embodiment of the present disclosure includes a computer program product, which includes a computer program carried on a non-transitory computer-readable medium, and the computer program contains program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network through a communication device 509, or installed from a storage device 508, or installed from a ROM 502. When the computer program is executed by the processing device 501, the above-mentioned functions defined in the method of the embodiment of the present disclosure are executed.

[0123] It should be noted that the computer-readable medium disclosed above may be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present disclosure, a computer-readable storage medium may be any tangible medium containing or storing a program that may be used by or in combination with an instruction execution system, device or device. In the present disclosure, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, in which a computer-readable program code is carried. This propagated data signal may take a variety of forms, including but not limited to an electromagnetic signal, an optical signal, or any suitable combination of the above. The computer readable signal medium may also be any computer readable medium other than a computer readable storage medium, which may send, propagate or transmit a program for use by or in conjunction 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 cables, RF (radio frequency), etc., or any suitable combination of the above.

[0124] In some embodiments, the client and the server may communicate using any currently known or future developed network protocol such as HTTP (HyperText Transfer Protocol), and may be interconnected with any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include a local area network ("LAN"), a wide area network ("WAN"), an internet (e.g., the Internet), and a peer-to-peer network (e.g., an ad hoc peer-to-peer network), as well as any currently known or future developed network.

[0125] The computer-readable medium may be included in the electronic device, or may exist independently without being incorporated into the electronic device.

[0126] The above-mentioned computer-readable medium carries one or more programs. When the above-mentioned one or more programs are executed by the electronic device, the electronic device: obtains target business content information, where the target business content information is associated with a target user; extracts a first business keyword based on the target business content information to obtain a first business keyword set; and generates business interaction content corresponding to the target user based on the first business keyword set and pre-set interactive content attribute information.

[0127] Computer program code for performing the operations of the present disclosure may be written in one or more programming languages ​​or a combination thereof, including, but not limited to, object-oriented programming languages, such as Java, Smalltalk, C++, and conventional procedural programming languages, such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate 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 a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., through the Internet using an Internet service provider).

[0128] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present disclosure. In this regard, each square box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some implementations as replacements, the functions marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two square boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0129] The units involved in the embodiments described in the present disclosure may be implemented by software or hardware, wherein the name of a module does not, in some cases, constitute a limitation on the unit itself.

[0130] The functions described above herein may be performed at least in part by one or more hardware logic components. For example, without limitation, exemplary types of hardware logic components that may be used include: field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), complex programmable logic devices (CPLDs), and the like.

[0131] In the context of the present disclosure, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, device, or equipment. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or equipment, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0132] According to one or more embodiments of the present disclosure, Example 1 provides a method for generating interactive content, including:

[0133] Acquire target business content information, where the target business content information is associated with a target user;

[0134] Extracting first business keywords based on the target business content information to obtain a first business keyword set;

[0135] Business interactive content corresponding to the target user is generated according to the first business keyword set and preset interactive content attribute information.

[0136] According to one or more embodiments of the present disclosure, Example 2 is a method according to Example 1, wherein obtaining target business content information includes:

[0137] Acquire original service content information within a recent preset time length, wherein the original service content information includes at least one of session information, meeting information, and document information;

[0138] The business content information associated with the business in which the target user has participated is extracted from the original business content information as the target business content information of the target user.

[0139] According to one or more embodiments of the present disclosure, Example 3 is a method according to Example 2, wherein the session information includes session summary information of a target session, and the target session is a session in which the target user sends a session message within a recent preset time length;

[0140] The meeting information includes meeting summary information of the meeting in which the target user participates;

[0141] The document information includes document identification information and / or edited content information of the document edited by the target user.

[0142] According to one or more embodiments of the present disclosure, Example 4 is the method according to Example 1, wherein extracting the first business keyword based on the target business content information includes:

[0143] The target business content information is input into a business keyword extraction model, and the first business keyword in the target business content information is extracted by the business keyword extraction model.

[0144] According to one or more embodiments of the present disclosure, Example 5 is the method according to Example 1, wherein generating business interaction content corresponding to the target user according to the first business keyword set and preset interactive content attribute information includes:

[0145] Acquire a union of the first service keyword set and the second service keyword set as a third service keyword set for the target user, wherein the second service keyword set is a set of second service keywords for associated services, and the associated services have a preset association relationship with the target user;

[0146] Business interactive content corresponding to the target user is generated according to the third business keyword set and preset interactive content attribute information.

[0147] According to one or more embodiments of the present disclosure, Example 6 is the method according to Example 5, and before obtaining the union of the first business keyword set and the second business keyword set, further includes:

[0148] Deduplication processing is performed on the first business keyword in the first business keyword set.

[0149] According to one or more embodiments of the present disclosure, Example 7 is the method according to Example 6, wherein the deduplication processing of the first business keyword in the first business keyword set includes at least one of the following:

[0150] performing deduplication processing on the first business keywords according to similarities between different first business keywords in the first business keyword set;

[0151] Deduplication processing is performed on the first business keyword in the first business keyword set according to the similarity between the first business keyword in the first business keyword set and each second business keyword in the second business keyword set;

[0152] According to the similarity between the first business keyword in the first business keyword set and the associated keyword of the second business keyword, the first business keyword in the first business keyword set is deduplicated.

[0153] According to one or more embodiments of the present disclosure, Example 8 is a method according to any one of Examples 1-7, further comprising:

[0154] Displaying the business interaction content in the target area, wherein the business interaction content includes questions related to the business;

[0155] In response to a triggering operation on the business interaction content, a reply content corresponding to the question is generated.

[0156] According to one or more embodiments of the present disclosure, Example 9 is the method according to Example 8, wherein generating a reply content corresponding to the question includes:

[0157] generating a reply window in the page currently displaying the business interaction content, and displaying the reply content in the reply window; or,

[0158] The target conversation window in the instant messaging tool is called up, and the reply content is generated in the target conversation window.

[0159] According to one or more embodiments of the present disclosure, Example 10 is based on the method described in Example 8, wherein the target area is located within at least one of a conversation page of an instant messaging tool, a search page of an instant messaging tool, an online document page, and a conference page.

[0160] According to one or more embodiments of the present disclosure, Example 11 is a method according to any one of Examples 1 to 7, and before acquiring the target service content information, further includes:

[0161] Obtain the target user's authorization information for target business content information.

[0162] According to one or more embodiments of the present disclosure, Example 12 provides a device for generating interactive content, including:

[0163] A first information acquisition module, used to acquire target service content information, wherein the target service content information is associated with a target user;

[0164] A keyword extraction module, configured to extract first business keywords based on the target business content information to obtain a first business keyword set;

[0165] The interactive content generation module is used to generate business interactive content corresponding to the target user according to the first business keyword set and preset interactive content attribute information.

[0166] According to one or more embodiments of the present disclosure, Example 13 provides an electronic device, including:

[0167] one or more processors;

[0168] a memory for storing one or more programs,

[0169] When the one or more programs are executed by the one or more processors, the one or more processors implement the method for generating interactive content as described in any one of Examples 1-11.

[0170] According to one or more embodiments of the present disclosure, Example 14 provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the method for generating interactive content as described in any one of Examples 1-11.

[0171] According to one or more embodiments of the present disclosure, Example 15 provides a computer program product. When the computer program product is executed by a computer, the computer implements the method for generating interactive content as described in any one of Examples 1-11.

[0172] The above description is only a preferred embodiment of the present disclosure and an explanation of the technical principles used. Those skilled in the art should understand that the scope of disclosure involved in the present disclosure is not limited to the technical solutions formed by a specific combination of the above technical features, but should also cover other technical solutions formed by any combination of the above technical features or their equivalent features without departing from the above disclosed concept. For example, the above features are replaced with the technical features with similar functions disclosed in the present disclosure (but not limited to) by each other to form a technical solution.

[0173] In addition, although each operation is described in a specific order, this should not be understood as requiring these operations to be performed in the specific order shown or in a sequential order. Under certain circumstances, multitasking and parallel processing may be advantageous. Similarly, although some specific implementation details are included in the above discussion, these should not be interpreted as limiting the scope of the present disclosure. Some features described in the context of a separate embodiment can also be implemented in a single embodiment in combination. On the contrary, the various features described in the context of a single embodiment can also be implemented in multiple embodiments individually or in any suitable sub-combination mode.

[0174] Although the subject matter has been described in language specific to structural features and / or methodological logical actions, it should be understood that the subject matter defined in the appended claims is not necessarily limited to the specific features or actions described above. On the contrary, the specific features and actions described above are merely example forms of implementing the claims.

Claims

1. A method for generating interactive content, characterized in that: include: Acquire target business content information, where the target business content information is associated with a target user; Extracting first business keywords based on the target business content information to obtain a first business keyword set; Business interactive content corresponding to the target user is generated according to the first business keyword set and preset interactive content attribute information.

2. The method according to claim 1, characterized in that The obtaining of target business content information includes: Acquire original service content information within a recent preset time length, wherein the original service content information includes at least one of session information, meeting information, and document information; The business content information associated with the business in which the target user has participated is extracted from the original business content information as the target business content information of the target user.

3. The method according to claim 2, characterized in that The session information includes session summary information of a target session, where the target session is a session in which the target user sends session messages within a recent preset time length; The meeting information includes meeting summary information of the meeting in which the target user participates; The document information includes document identification information and / or edited content information of the document edited by the target user.

4. The method according to claim 1, characterized in that: The extracting the first business keyword based on the target business content information includes: The target business content information is input into a business keyword extraction model, and the first business keyword in the target business content information is extracted by the business keyword extraction model.

5. The method according to claim 1, characterized in that The generating of business interactive content corresponding to the target user according to the first business keyword set and preset interactive content attribute information includes: Acquire a union of the first service keyword set and the second service keyword set as a third service keyword set for the target user, wherein the second service keyword set is a set of second service keywords for associated services, and the associated services have a preset association relationship with the target user; Business interactive content corresponding to the target user is generated according to the third business keyword set and preset interactive content attribute information.

6. The method according to claim 5, characterized in that Before obtaining the union of the first service keyword set and the second service keyword set, the method further includes: Deduplication processing is performed on the first business keyword in the first business keyword set.

7. The method according to claim 6, characterized in that The performing deduplication processing on the first business keyword in the first business keyword set includes at least one of the following: performing deduplication processing on the first business keywords according to similarities between different first business keywords in the first business keyword set; Deduplication processing is performed on the first business keyword in the first business keyword set according to the similarity between the first business keyword in the first business keyword set and each second business keyword in the second business keyword set; According to the similarity between the first business keyword in the first business keyword set and the associated keyword of the second business keyword, the first business keyword in the first business keyword set is deduplicated.

8. The method according to any one of claims 1 to 7, characterized in that: Also includes: Displaying the business interaction content in the target area, wherein the business interaction content includes questions related to the business; In response to a triggering operation on the business interaction content, a reply content corresponding to the question is generated.

9. The method according to claim 8, characterized in that The generating of the reply content corresponding to the question includes: generating a reply window in the page currently displaying the business interaction content, and displaying the reply content in the reply window; or, The target conversation window in the instant messaging tool is called up, and the reply content is generated in the target conversation window.

10. The method according to claim 8, characterized in that The target area is located in at least one of a conversation page of an instant messaging tool, a search page of an instant messaging tool, an online document page, and a conference page.

11. The method according to any one of claims 1 to 7, characterized in that: Before obtaining the target service content information, the method further includes: Obtain the target user's authorization information for target business content information.

12. A device for generating interactive content, characterized in that: include: A first information acquisition module, used to acquire target service content information, wherein the target service content information is associated with a target user; A keyword extraction module, configured to extract first business keywords based on the target business content information to obtain a first business keyword set; The interactive content generation module is used to generate business interactive content corresponding to the target user according to the first business keyword set and preset interactive content attribute information.

13. An electronic device, characterized in that: include: at least one processor; as well as a memory communicatively connected to the at least one processor; wherein, The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the method for generating interactive content according to any one of claims 1 to 11.

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

15. A computer program product, characterized in that The computer program product comprises a computer program, and when the computer program is executed by a processor, the method for generating interactive content according to any one of claims 1 to 11 is implemented.

Images