Information interaction method and device, electronic equipment and storage medium

Abstract

The invention provides an information interaction method, and relates to the technical field of artificial intelligence, in particular to the technical fields of deep learning, large models, generative models and the like. According to the specific implementation scheme, in response to received input information from an object, first intention recognition is conducted on the input information, and the first intention recognition is used for determining whether the intention of the object is entering a news display page or not; in response to the intention of the object to enter the news display page, performing second intention recognition on the input information according to the historical news list, the second intention recognition being used for determining whether the sub-intention of the object is the news content of the target event; and pushing one of the news content of the target event or the new news list according to the sub-intention of the object. The invention further provides an information interaction device, electronic equipment and a storage medium.

Description

Technical Field

[0001] The present disclosure relates to the field of artificial intelligence technology, and in particular to the technical fields of deep learning, large models, generative models, etc. More specifically, the present disclosure provides an information interaction method, device, electronic device, storage medium, and computer program product. Background Art

[0002] The current news generation and distribution system mainly relies on manual editing and preset templates to generate news content, and uses simple keyword matching or rule-based recommendation algorithms to push news to users. Summary of the invention

[0003] The present disclosure provides an information interaction method, device, electronic device, storage medium and computer program product.

[0004] According to a first aspect, an information interaction method is provided, the method comprising: in response to receiving input information from an object, performing a first intent recognition on the input information, the first intent recognition being used to determine whether the object's intention is to enter a news display page; in response to the object's intention being to enter the news display page, performing a second intent recognition on the input information based on a historical news list, the second intent recognition being used to determine whether the object's sub-intention is to obtain news content of a target event; and according to the object's sub-intention, pushing the news content of the target event or one of the new news lists.

[0005] According to a second aspect, an information interaction device is provided, which includes: a first intention recognition module, which is used to perform a first intention recognition on the input information in response to receiving input information from an object, and the first intention recognition is used to determine whether the object's intention is to enter a news display page; a second intention recognition module, which is used to perform a second intention recognition on the input information according to a historical news list in response to the object's intention of entering the news display page, and the second intention recognition is used to determine whether the object's sub-intention is to obtain news content of a target event; and a first push module, which is used to push the news content of the target event or one of the new news lists according to the object's sub-intention.

[0006] According to a third aspect, an electronic device is provided, comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the method provided according to the present disclosure.

[0007] According to a fourth aspect, a non-transitory computer-readable storage medium storing computer instructions is provided, wherein the computer instructions are used to cause a computer to execute the method provided according to the present disclosure.

[0008] According to a fifth aspect, a computer program product is provided, comprising a computer program, wherein the computer program is stored on at least one of a readable storage medium and an electronic device, and wherein the computer program implements the method provided according to the present disclosure when executed by a processor.

[0009] It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present disclosure, nor is it intended to limit the scope of the present disclosure. Other features of the present disclosure will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] The accompanying drawings are used to better understand the present solution and do not constitute a limitation of the present disclosure.

[0011] Figure 1 is a schematic diagram of an exemplary system architecture to which the information interaction method and apparatus can be applied according to an embodiment of the present disclosure;

[0012] Figure 2 is a flow chart of an information interaction method according to an embodiment of the present disclosure;

[0013] Figure 3 is a schematic diagram of an information interaction method according to an embodiment of the present disclosure;

[0014] Figure 4 is a flow chart of an information interaction method according to another embodiment of the present disclosure;

[0015] Figure 5 is a schematic diagram of a news display page according to an embodiment of the present disclosure;

[0016] Figure 6 is a block diagram of an information interaction device according to an embodiment of the present disclosure; and

[0017] Figure 7 It is a block diagram of an electronic device according to an information interaction method of an embodiment of the present disclosure. DETAILED DESCRIPTION

[0018] The following is a description of exemplary embodiments of the present disclosure in conjunction with the accompanying drawings, including various details of the embodiments of the present disclosure to facilitate understanding, which should be considered as merely exemplary. Therefore, it should be recognized by those of ordinary skill in the art that various changes and modifications may be made to the embodiments described herein without departing from the scope and spirit of the present disclosure. Similarly, for the sake of clarity and conciseness, descriptions of well-known functions and structures are omitted in the following description.

[0019] The current news generation and distribution system usually presents news in a "send-click" manner, with a single user interaction method, and when a user clicks on a news event, the news content presented is fixed.

[0020] Users are increasingly viewing news on mobile terminals. The current news generation and distribution system has obvious deficiencies in user interaction experience and personalized generation on mobile terminals, making it difficult to meet the dynamic needs of mobile terminal users. Specifically, it includes the following aspects.

[0021] Single news format: Traditional news information is simple in form, weakly structured, lacks extensibility, and cannot meet the growing demand for information complexity.

[0022] Poor interactive experience: The user's interaction with the system on the mobile terminal is single, lacking in-depth participation and personalized feedback mechanisms, resulting in poor user experience. For example, the event content displayed by clicking on a specific event is fixed, and users cannot obtain personalized news content.

[0023] Poor real-time performance: News content is updated and recommended slowly, and cannot respond to changes in user interests in real time, resulting in information lag.

[0024] Low recommendation accuracy: Rule-based recommendation algorithms cannot fully capture user interests, and the recommended news content often lacks relevance and appeal.

[0025] In the technical solution of the present disclosure, the collection, storage, use, processing, transmission, provision and disclosure of user personal information involved are in compliance with the provisions of relevant laws and regulations and do not violate public order and good morals.

[0026] In the technical solution of the present disclosure, the user's authorization or consent is obtained before obtaining or collecting the user's personal information.

[0027] Figure 1 is a schematic diagram of an exemplary system architecture to which the information interaction method and device can be applied according to an embodiment of the present disclosure. It should be noted that: Figure 1 What is shown is merely an example of a system architecture to which the embodiments of the present disclosure can be applied, in order to help those skilled in the art understand the technical content of the present disclosure, but it does not mean that the embodiments of the present disclosure cannot be used in other devices, systems, environments or scenarios.

[0028] like Figure 1 As shown, the system architecture 100 according to this embodiment may include terminal devices 101, 102, 103, a network 104 and a server 105. The network 104 is used to provide a medium for communication links between the terminal devices 101, 102, 103 and the server 105. The network 104 may include various connection types, such as wired and / or wireless communication links, etc.

[0029] Users can use terminal devices 101, 102, 103 to interact with server 105 through network 104 to receive or send messages, etc. Terminal devices 101, 102, 103 can be various electronic devices, including but not limited to smart phones, tablet computers, laptops, etc.

[0030] The information interaction method provided in the embodiment of the present disclosure can generally be executed by the server 105. Accordingly, the information interaction device provided in the embodiment of the present disclosure can generally be set in the server 105. The information interaction method provided in the embodiment of the present disclosure can also be executed by a server or server cluster that is different from the server 105 and can communicate with the terminal devices 101, 102, 103 and / or the server 105. Accordingly, the information interaction device provided in the embodiment of the present disclosure can also be set in a server or server cluster that is different from the server 105 and can communicate with the terminal devices 101, 102, 103 and / or the server 105.

[0031] Figure 2 It is a flowchart of an information interaction method according to an embodiment of the present disclosure.

[0032] like Figure 2 As shown, the information interaction method 200 includes operations S210 to S230.

[0033] In operation S210, in response to receiving input information from an object, first intent recognition is performed on the input information.

[0034] For example, the object may be a user, and the user may use a mobile terminal to input an instruction in an input box on a page displayed by an application program, and the instruction may be text or voice.

[0035] The first intent recognition is used to recognize whether the user's intention is to enter the news display page based on the instruction input by the user. For example, the user can input an instruction on any page displayed by the application of the mobile terminal, and the first intent recognition can recognize whether the user's intention is to switch from the current page to the news display page.

[0036] For example, the above application can be an application based on a big model, which can provide a variety of functional modules based on the big model, such as hot news, search, image generation, video generation, long article writing, document summary and other functional modules.

[0037] On the page of any function module, the user can switch the current page to the page of another function module by entering information related to the other function module.

[0038] For example, if the user inputs news-related information, through intent recognition, it can be identified that the user has the intention to enter the news display page, and in response to the input information, the current page can be switched to the news display page.

[0039] The news display page can display the news content of a specific event or a news list. The input information can be further identified by a second intent to determine the display content required by the user.

[0040] In operation S220, in response to the object's intention of entering a news display page, a second intention recognition is performed on the input information according to the historical news list.

[0041] When it is determined that the user's intention is to enter the news display page, the input information is subjected to second intention recognition, and the second intention recognition is used to identify whether the user wants to obtain news content of a specific target event. Specifically, it can be used to identify whether the user wants to obtain news content of a specific target event or a news list.

[0042] For example, a historical news list generated by a hot news function module may be obtained, and a second intent recognition may be performed on the input information based on the historical news list. The second intent recognition is performed when it is determined that the user has entered a news display page, and the recognized intent may be referred to as the user's sub-intent.

[0043] The above historical news list can be a generated news list provided by the news module based on the big model. The news module can obtain the news list by aggregating news from the entire network, and the news module can also update the news list according to a certain period or in response to user input instructions.

[0044] For example, you can get the most recently updated news list, match the most recently updated news list with the user input information, and determine whether the user input information hits the event information in the news list. If it hits the target event information, you can determine that the user's sub-intention is to obtain the specific news content of the target event.

[0045] If the user input information does not hit any event information in the historical news list, it can be determined that the user's sub-intention is to obtain a news list.

[0046] In operation S230, one of the news content of the target event or a new news list is pushed according to the sub-intent of the object.

[0047] In the case where the user's sub-intent is to obtain news content of the target event, event information from multiple sources can be searched based on the user input information. Based on the event information from multiple sources, the generation capability of the large model can be used to regenerate the news content of the target event through summarization, generalization and correction. The generated news content of the target event can be pushed to the terminal so as to be displayed on the terminal page.

[0048] If the user's sub-intention is to obtain a news list, a new news list can be generated based on the user input information, pushed to the terminal, and displayed on the terminal. The new news list can be updated based on the user input information by the news module based on the large model.

[0049] For example, the historical news list shows the hot news events of the past week. The user inputs information such as "what news is there today". Based on this input information, the news module based on the big model can re-search and aggregate to obtain a new news list, which can mainly show the hot news event information of the day.

[0050] The embodiments of the present disclosure interact with users on news information in the form of dialogue, the interactive forms are more diverse, and the news list and news content are updated in real time based on the user's instant input information, thereby meeting the user's needs for obtaining personalized news and improving the user experience.

[0051] Compared with the related art, in which news is presented in a single interactive mode of "send-click", and the presented news content is fixed, the embodiments of the present disclosure interact in the form of dialogue, which can improve user participation, and generate personalized news content based on user-defined input information, providing a personalized feedback mechanism to meet the dynamic needs of users.

[0052] Figure 3 It is a schematic diagram of an information interaction method according to an embodiment of the present disclosure.

[0053] like Figure 3 As shown, this embodiment provides pages 301-302. Pages 301-302 may be pages of an application (APP) based on a large model displayed on a user's mobile terminal. Pages 301-302 each include an input box, in which a user may input text, voice, or other instructions.

[0054] The above-mentioned application based on the big model can provide multiple functional modules based on the big model, as shown in page 301, and the multiple functional modules may include hot news, AI search, long text writing, image or video generation, etc., among which long text writing, image generation and video generation all belong to the creation module. It should be noted that the above-mentioned functional modules are only examples. According to the actual application scenarios, the application based on the big model can also provide other functional modules, such as document summarization, intelligent translation, etc.

[0055] Page 301 shows the controls of each functional module, providing an entry to each functional module page. For example, a user clicks on any functional module on page 301 to jump to the page under the functional module. Page 302 can be any page under the application, for example, page 302 can be the same page as page 301, or it can be a page under any functional module.

[0056] This embodiment provides two paths to enter the news display page. One path is to click the hot news control on page 301. In response to the click operation, a news list 303 can be displayed. The user clicks on an event in the news list, or the user enters the serial number of an event in the news list in the input box, and then jumps from the news list display page to the news content display page. The news content display page can display specific news content 304, which can include text pictures, text, timeline, citation sources, links to citation sources, and other information.

[0057] Another path to enter the news display page is to enter an instruction in the input box on page 302. The first intention recognition module 310 performs a first intention recognition on the instruction entered by the user to identify whether the user has the intention to enter the news display page.

[0058] According to an embodiment of the present disclosure, in response to receiving input information from an object, the input information is matched with description texts of preset multiple functional modules, wherein the multiple functional modules include a news module based on a large model, a search module, and a creation module; and in response to the input information matching the description text of the news module, it is determined that the object's intention is to enter a news display page.

[0059] Page 302 can be a page under any functional module. The first intention recognition module 310 performs first intention recognition on the user input information, and first matches the input information with the description text of the functional module to which page 302 currently belongs. If the match fails, the input information can be matched with the description text of other functional modules.

[0060] For example, each functional module in page 301 has a corresponding description text. For example, the "hot news" functional module contains the basic description text of "hot news", and may also contain explanatory description texts such as "the latest and hottest news topics". The "AI search" functional module contains the basic description text of "AI search", and may also contain explanatory description texts such as "massive resources across the entire network". The "long article writing" functional module contains the basic description text of "long article writing", and may also contain explanatory description texts such as "one-click generation of long articles". The "picture / video generation" functional module contains the basic description text of "picture / video generation", and may also contain explanatory description texts such as "create your story".

[0061] For example, page 302 is a page under the "Long Article Writing" function module. The first intention recognition module 310 can first match the user input information with the description text of the "Long Article Writing" function module. If the match is unsuccessful, the input information is matched with the description text of other function modules until a matching function module is obtained.

[0062] For example, if the first intention recognition module 310 recognizes that the input information matches the description text of the "hot news" function module, it can be determined that the user has the intention to enter the news display page.

[0063] When the first intention recognition module 310 determines that the user has the intention to enter the news display page, the second intention recognition module 320 performs a second intention recognition on the input information to identify whether the user's sub-intention is to obtain news information about the target event or to obtain a news list.

[0064] According to an embodiment of the present disclosure, in response to the object's intention of entering a news display page, the input information is matched with at least one of the titles and serial numbers of multiple events in the historical news list; and in response to the input information successfully matching at least one of the titles and serial numbers of the target event in the historical news list, the object's sub-intent is determined to obtain the news content of the target event.

[0065] For example, the second intent recognition module 320 can obtain a historical news list, which can be a news list recently updated by the "hot news" module. The second intent recognition module 320 matches the input information with the historical news list. If the input information matches at least one of the title or sequence number of an event in the historical news list, it can be determined that the user's sub-intention is to obtain the news content of the target event.

[0066] For example, the information input by the user in the input box can be a keyword of a certain event, or the user can specify to view an event with a certain sequence number, such as "read the first news", "read the fifth news", etc. If the keyword input by the user matches the title of the target event in the historical news list, or the sequence number input by the user matches the sequence number of the target event in the historical news list, it can be determined that the user's sub-intention is to obtain the news content of the target event.

[0067] According to an embodiment of the present disclosure, in response to the input information not matching the title and serial number of any event in the historical news list, determining that the sub-intent of the object is to obtain a news list. In response to the sub-intent of the object being to obtain a news list, generating a new news list according to the input information; and pushing the new news list.

[0068] If the user's input information does not match the event title and serial number in the historical news list, it can be determined that the user's sub-intention is to obtain a news list. At this time, the news list can be updated, pushed to the mobile terminal, and displayed on the terminal so that the user can obtain the latest news list.

[0069] For example, the entire network news can be re-aggregated based on the user input information to generate a new news list that better meets the user's needs.

[0070] For example, the historical news list shows the hot news events in the past week. The user inputs information such as "what news is there today", and based on the input information, the regenerated news list can mainly contain the hot news of the day.

[0071] For another example, the user input information specifies obtaining hot news in a certain area. Based on the input information, the regenerated news list may mainly include the hot news in the area.

[0072] The embodiments of the present disclosure update the news list in real time according to the user input information, fully capture the user's interests, and the recommended news list better meets the user's personalized needs.

[0073] According to an embodiment of the present disclosure, in response to receiving a click operation from an object on a target event in a news list, news content of the target event is pushed; in response to receiving a reply message from an object on a sequence number of an event in the news list, news content of the event corresponding to the sequence number is pushed.

[0074] For example, after obtaining the latest news list 303, the user can click a link of an event in the latest news list 303 or reply to a serial number in the news list, and then the specific news content 304 of the news event clicked by the user or the specified serial number can be displayed.

[0075] In addition to supporting the traditional "send-click" method, the embodiments of the present disclosure can also support a customized input interaction method with more diverse forms and more interesting interactions.

[0076] The embodiments of the present disclosure can more accurately understand user needs by identifying the intent of user input content, and determine content generation based on user input content in combination with the generation power of a large model. Compared with rule-based recommendation algorithms that cannot fully capture user interests, the news content recommended by the embodiments of the present disclosure is more relevant and attractive, thereby improving the recommendation accuracy.

[0077] Figure 4 is a flowchart of an information interaction method according to another embodiment of the present disclosure.

[0078] like Figure 4 As shown, this embodiment includes operations S410 to S412, operations S420 to S427, and operation S430. Operation S410, operation S420, and operation S430 are three entrances to the hot news page.

[0079] In operation S410, a hot news function is selected.

[0080] For example, on the page of an application based on a large model, functional controls such as hot news, AI search, long article creation, image / video generation, etc. are displayed. By clicking the hot news control, you can enter the news display page.

[0081] In operation S411, it is determined whether a query is input.

[0082] When it is determined that the user wants to enter the news display page, it can be determined whether the user has input a query. If the user has input a query, operation S423 can be performed to perform intent recognition based on the input query to determine whether the user wants to obtain a news list (general demand) or obtain specific news. If the user has not input a query, operation S412 can be performed to display the news list.

[0083] In operation S412, a news list is displayed.

[0084] When the user selects the hot news function and does not enter a query, the user intends to obtain a news list, so the news list is displayed.

[0085] In operation S420, a free command query is input.

[0086] For example, a free command query can be entered in an input box of any page of an application based on a large model. In one example, the arbitrary page can be the homepage of an application based on a large model, such as the homepage showing function controls such as hot news, AI search, long article creation, image / video generation, etc.

[0087] In operation S421, it is determined whether the free instruction query hits the news intention.

[0088] This step may be to perform a first intent recognition on the free instruction query to determine whether the user intends to enter the news display page.

[0089] For example, the free instruction can be matched with the description text of each functional module in the application homepage. If the description text of the hot news functional module is hit, it can be determined that the news intention is hit, that is, it is determined that the user has the intention to enter the hot news display page.

[0090] In the case where the news intention is hit, operation S423 is performed, otherwise operation S422 is performed.

[0091] In operation S422, other functions or general generation of the large model is performed.

[0092] When it is determined that the news intent is not hit, it can be determined whether the free instruction query hits other functions. If it is determined that the free instruction query hits other functions, the large model can be called to execute the corresponding functions, such as long article writing, image generation, etc.

[0093] If the free command query does not hit any functional module on the application homepage based on the big model, the big model can be generated normally, for example, a reply message is generated based on the free command query.

[0094] In operation S423, it is determined whether the news intention is general demand or specific news.

[0095] This step may be to perform a second intent recognition on the free instruction query. For example, when it is determined that the news intent is hit, the second intent recognition is performed on the free instruction query to determine whether the user's sub-intent is to obtain a news list or to obtain specific news.

[0096] If the user's sub-intention is to obtain a news list, the sub-intention is a general demand, and operation S412 is performed to display the news list.

[0097] If the user's sub-intention is to obtain specific news, this sub-intention is a precise demand, and operation S424 is executed.

[0098] In operation S424, it is determined whether there is a search result.

[0099] The search results may be search results based on the free instruction query. A search result means that the information source is searched using the free instruction query, and no search result means that the information source is not searched using the free instruction query. If there is a search result, operations S425 to S426 may be performed. Otherwise, operation S427 is performed.

[0100] In operation S425, an information source is acquired.

[0101] In operation S426, news details are generated.

[0102] According to an embodiment of the present disclosure, in response to the object's sub-intention of obtaining news content of a target event, the input information is rewritten to obtain rewritten information; the rewritten information is used to search to obtain multiple information sources; and based on the multiple information sources, the news content of the target event is generated.

[0103] For example, if it is determined that the user has the intention to obtain specific news, the free instruction query can be rewritten to obtain a rewritten query. The rewriting step can include expansion and correction. For example, the free instruction query only contains a single keyword. After rewriting the free instruction query, multiple keywords associated with the keyword can be obtained, or a sentence containing the keyword can be formed. Compared with the original free instruction query, the rewritten query information is more comprehensive. Therefore, using the rewritten query for searching can obtain news events from more sources.

[0104] Based on the generation capability of the large model, the multiple information sources obtained can be reorganized and summarized into new news content, and the new news content can be pushed to the mobile terminal and displayed on the terminal.

[0105] The embodiment of the present disclosure rewrites the free instruction query, uses the rewritten query to search, aggregates hot news on the entire network in real time, and better meets the timeliness requirements of users for obtaining news.

[0106] In operation S427, the backup copy is returned.

[0107] When it is determined that the user has the intention to obtain specific news, but there is no search result when searching with a free command query, it may be that the news title or entry is normal, but the news content may involve risk control and cannot be made public. Therefore, in this case, the user's intention to obtain the target event can be identified, but the specific content of the target event cannot be obtained.

[0108] In the absence of search results, a fallback message may be returned to the user, for example, prompting the user that the incident involves sensitivity and that specific content is unavailable.

[0109] In operation S430 , in the other function page, query is input.

[0110] The other function pages may be pages of other functions other than hot news, such as pages under the long article writing function, pages under the video generation function, etc. The query inputted under the other function pages is also a kind of free command query. Therefore, when the free command query is received under the other function pages, the following operations are consistent with the operations after the free command query is inputted in operation S420.

[0111] That is to say, on any function page, by entering the free command query, if the news intent is recognized, you can jump to the hot news page.

[0112] In the embodiment of the present disclosure, a user can jump to a news display page by inputting a free command on any page, so that the user can obtain news information in a more flexible way.

[0113] According to an embodiment of the present disclosure, pushing news content of a target event includes at least one of the following operations: pushing reference links of multiple information sources of the target event; pushing timeline information of the target event; pushing at least one of text, image and video of the target event.

[0114] According to an embodiment of the present disclosure, when news content is generated based on user input information, the news content can be organized in various forms such as reference source, event context (timeline), picture, video, text, etc., and at least one of the link to the reference source, event context, picture, text, and video can be pushed to a mobile terminal for display on the mobile terminal, so that the user can view news content in various organizational forms.

[0115] Figure 5 It is a schematic diagram of a news display page according to an embodiment of the present disclosure.

[0116] like Figure 5 As shown, page 501 may be a news list display page, including a news list and an input box. Page 502 may be a display page for specific news content, and page 502 may be redirected from page 501.

[0117] Page 502 may include the reference source of the target event, which includes links to various sources. When a user clicks on a link, the user may obtain the original news page of the source, providing the user with extended search and guided reading capabilities, thereby ensuring the authenticity and accuracy of the news and the convenience of reading.

[0118] Page 502 may also include the event context of the target event, which may include time node information, and each time node may include the specific event content of the node. Page 502 may also include pictures and videos, which may be selected from multiple information sources. Page 502 may also include news text content, which may be obtained by the big model performing key information extraction, sentiment analysis and other operations on news texts from multiple information sources to obtain important information of the event, and summarizing, generalizing and mining based on the important information using the big model.

[0119] For example, the big model can be used to summarize the event summary, the mined event details, and the main highlights from multiple angles. The big model can also be used to generate event commentary information based on commentary information and event impact information. The above event summary, event details, main highlights from multiple angles, and event commentary information can be organized into news content.

[0120] Compared with the related art in which news formats are single and news content is fixed, the embodiments of the present disclosure form news content in a structured and multimodal content organization manner, and support news content aggregation in various forms such as pictures, texts, reference links, guided reading, timelines, etc., which can better meet user needs.

[0121] According to an embodiment of the present disclosure, the present disclosure also provides an information interaction device.

[0122] Figure 6 It is a block diagram of an information interaction device according to an embodiment of the present disclosure.

[0123] like Figure 6 As shown, the information interaction device 600 includes a first intention recognition module 610 , a second intention recognition module 620 and a first push module 630 .

[0124] The first intention recognition module 610 is used to perform a first intention recognition on the input information in response to receiving the input information from the object, and the first intention recognition is used to determine whether the object's intention is to enter the news display page.

[0125] The second intent recognition module 620 is used to respond to the object's intention of entering the news display page and perform second intent recognition on the input information according to the historical news list. The second intent recognition is used to determine whether the object's sub-intention is to obtain the news content of the target event.

[0126] The first push module 630 is used to push the news content of the target event or one of the new news lists according to the sub-intent of the object.

[0127] The first intention recognition module 610 includes a first matching unit and an intention determination unit.

[0128] The first matching unit is used for matching the input information with the description texts of a plurality of preset functional modules in response to receiving the input information from the object, wherein the plurality of functional modules include a news module, a search module and a creation module based on a large model.

[0129] The intention determination unit is used to determine that the intention of the object is to enter the news display page in response to the input information matching the description text of the news module.

[0130] The second intention recognition module 620 includes a second matching unit and a first sub-intention determination unit.

[0131] The second matching unit is used to match the input information with at least one of the titles and serial numbers of the plurality of events in the historical news list in response to the object's intention to enter the news display page.

[0132] The first sub-intention determination unit is used to determine that the sub-intention of the object is to obtain news content of the target event in response to a successful match between the input information and at least one of the title and the serial number of the target event in the historical news list.

[0133] The first push module 630 includes a news content generating unit and a news content pushing unit.

[0134] The news content generating unit is used to obtain the news content of the target event in response to the sub-intention of the object, aggregate multiple information sources of the target event according to input information, and generate the news content of the target event according to the multiple information sources.

[0135] The news content pushing unit is used to push the news content of the target event.

[0136] The news content generating unit includes a rewriting subunit, a searching subunit and a generating subunit.

[0137] The rewriting subunit is used to rewrite the input information in response to the sub-intention of the object to obtain the news content of the target event to obtain the rewritten information.

[0138] The search subunit is used to use the rewritten information to search and obtain multiple information sources.

[0139] The generating subunit is used to generate news content of the target event according to multiple information sources.

[0140] The news content push unit includes at least one of the following subunits

[0141] The reference link push subunit is used to push reference links of multiple information sources of the target event.

[0142] The timeline push subunit is used to push the timeline information of the target event.

[0143] The content push subunit is used to push at least one of the text, image and video of the target event.

[0144] The second intention recognition module 620 also includes a second sub-intention determination unit.

[0145] The second sub-intention determination unit is used to determine that the sub-intention of the object is to obtain a news list in response to the input information not matching the title and serial number of any event in the historical news list.

[0146] The first push module 630 further includes a news list generating unit and a news list pushing unit.

[0147] The news list generating unit is used for generating a new news list according to input information in response to the sub-intention of the object to obtain a news list.

[0148] The news list push unit is used to push new news lists.

[0149] The information interaction device 600 further includes a second push module and a third push module.

[0150] The second push module is used for pushing the news content of the clicked event in response to receiving a click operation of the object on an event in the news list.

[0151] The third push module is used for, in response to receiving a reply message from the object regarding the sequence number of an event in the news list, pushing the news content of the event corresponding to the sequence number.

[0152] According to an embodiment of the present disclosure, the present disclosure also provides an electronic device, a readable storage medium and a computer program product.

[0153] Figure 7 A schematic block diagram of an example electronic device 700 that can be used to implement an embodiment of the present disclosure is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present disclosure described and / or required herein.

[0154] like Figure 7As shown, the device 700 includes a computing unit 701, which can perform various appropriate actions and processes according to a computer program stored in a read-only memory (ROM) 702 or a computer program loaded from a storage unit 708 into a random access memory (RAM) 703. In the RAM 703, various programs and data required for the operation of the device 700 can also be stored. The computing unit 701, the ROM 702, and the RAM 703 are connected to each other via a bus 704. An input / output (I / O) interface 705 is also connected to the bus 704.

[0155] A number of components in the device 700 are connected to the I / O interface 705, including: an input unit 706, such as a keyboard, a mouse, etc.; an output unit 707, such as various types of displays, speakers, etc.; a storage unit 708, such as a disk, an optical disk, etc.; and a communication unit 709, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 709 allows the device 700 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0156] The computing unit 701 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the computing unit 701 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, digital signal processors (DSPs), and any appropriate processors, controllers, microcontrollers, etc. The computing unit 701 performs the various methods and processes described above, such as the information interaction method. For example, in some embodiments, the information interaction method may be implemented as a computer software program, which is tangibly contained in a machine-readable medium, such as a storage unit 708. In some embodiments, part or all of the computer program may be loaded and / or installed on the device 700 via the ROM 702 and / or the communication unit 709. When the computer program is loaded into the RAM 703 and executed by the computing unit 701, one or more steps of the information interaction method described above may be performed. Alternatively, in other embodiments, the computing unit 701 may be configured to perform the information interaction method in any other appropriate manner (e.g., by means of firmware).

[0157] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0158] The program code for implementing the method of the present disclosure may be written in any combination of one or more programming languages. These program codes may be provided to a processor or controller of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that the program code, when executed by the processor or controller, enables the functions / operations specified in the flow chart and / or block diagram to be implemented. The program code may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0159] 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 device, 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.

[0160] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user can provide input to the computer. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0161] The systems and techniques described herein may be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such back-end components, middleware components, or front-end components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), and the Internet.

[0162] A computer system may include clients and servers. Clients and servers are generally remote from each other and usually interact through a communication network. The relationship of client and server is generated by computer programs running on respective computers and having a client-server relationship to each other.

[0163] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps recorded in this disclosure can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solutions disclosed in this disclosure can be achieved, and this document does not limit this.

[0164] The above specific implementations do not constitute a limitation on the protection scope of the present disclosure. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present disclosure shall be included in the protection scope of the present disclosure.

Claims

1. An information interaction method, include: In response to receiving input information from an object, performing a first intention recognition on the input information, wherein the first intention recognition is used to determine whether the object's intention is to enter a news display page; In response to the object's intention being to enter the news display page, performing a second intention recognition on the input information according to the historical news list, the second intention recognition being used to determine whether the object's sub-intention is to obtain news content of a target event; as well as According to the sub-intent of the object, one of the news content of the target event or a new news list is pushed.

2. The method according to claim 1, in, In response to receiving input information from the object, performing first intent recognition on the input information includes: In response to receiving input information from the object, matching the input information with description texts of a plurality of preset functional modules, wherein the plurality of functional modules include a news module, a search module, and a creation module based on a large model; and In response to the input information matching the description text of the news module, it is determined that the object's intention is to enter a news display page.

3. The method according to claim 1, in, In response to the object's intention of entering the news display page, performing second intention recognition on the input information according to the historical news list includes: In response to the object's intention to enter the news display page, matching the input information with at least one of the titles and serial numbers of each of the plurality of events in the historical news list; and In response to the input information successfully matching at least one of the title and the serial number of the target event in the historical news list, it is determined that the sub-intent of the object is to obtain news content of the target event.

4. The method according to claim 3, in, The pushing of one of the news content of the target event or a new news list according to the sub-intent of the object comprises: In response to the sub-intent of the object being to obtain news content of the target event, aggregating multiple information sources of the target event according to the input information, and generating news content of the target event according to the multiple information sources; and Push the news content of the target event.

5. The method according to claim 4, in, The sub-intent of the object in response to which is obtained the news content of the target event, aggregating multiple information sources of the target event according to the input information, and generating the news content of the target event according to the multiple information sources includes: In response to the sub-intention of the object being to obtain news content of the target event, rewriting the input information to obtain rewritten information; Using the rewritten information to search and obtain the multiple information sources; and Based on the multiple information sources, news content of the target event is generated.

6. The method according to claim 4 or 5, in, The pushing of the news content of the target event includes at least one of the following operations: Push reference links of multiple information sources of the target event; Pushing the timeline information of the target event; At least one of the text, image and video of the target event is pushed.

7. The method according to claim 3, in, In response to the object's intention of entering the news display page, performing second intention recognition on the input information according to the historical news list further includes: In response to the input information not matching the title and serial number of any event in the historical news list, determining that the sub-intent of the object is to obtain a news list.

8. The method according to claim 7, in, The pushing of one of the news content of the target event or a new news list according to the sub-intent of the object comprises: In response to the sub-intent of the object being to obtain a news list, generating a new news list according to the input information; and The new news list is pushed.

9. The method according to claim 1 or 8, further comprising: include: In response to receiving a click operation by the object on a target event in the news list, pushing news content of the target event; In response to receiving a reply message from the object to the sequence number of the event in the news list, the news content of the event corresponding to the sequence number is pushed.

10. An information interaction device, include: A first intention recognition module, configured to, in response to receiving input information from an object, perform a first intention recognition on the input information, wherein the first intention recognition is used to determine whether the object's intention is to enter a news display page; A second intention recognition module, configured to, in response to the object's intention being to enter the news display page, perform a second intention recognition on the input information according to the historical news list, wherein the second intention recognition is used to determine whether the object's sub-intention is to obtain news content of a target event; as well as The first push module is used to push one of the news content of the target event or a new news list according to the sub-intent of the object.

11. The device according to claim 10, in, The first intention recognition module includes: a first matching unit, configured to match the input information with description texts of a plurality of preset functional modules in response to receiving input information from the object, wherein the plurality of functional modules include a news module, a search module, and a creation module based on a large model; and The intention determination unit is used to determine that the intention of the object is to enter a news display page in response to the input information matching the description text of the news module.

12. The device according to claim 10, in, The second intention recognition module includes: A second matching unit, configured to match the input information with at least one of the titles and serial numbers of the respective events in the historical news list in response to the object's intention to enter the news display page; and The first sub-intention determination unit is used to determine that the sub-intention of the object is to obtain news content of the target event in response to a successful match between the input information and at least one of the title and the serial number of the target event in the historical news list.

13. The device according to claim 12, in, The first push module includes: a news content generating unit, configured to, in response to the sub-intention of the object being to obtain news content of the target event, aggregate multiple information sources of the target event according to the input information, and generate news content of the target event according to the multiple information sources; and The news content pushing unit is used to push the news content of the target event.

14. The device according to claim 13, in, The news content generating unit comprises: A rewriting subunit, configured to rewrite the input information in response to the sub-intention of the object to obtain the news content of the target event, to obtain rewritten information; A search subunit, configured to use the rewritten information to search and obtain the multiple information sources; and The generating subunit is used to generate news content of the target event according to the multiple information sources.

15. The device according to claim 13 or 14, in, The news content push unit includes at least one of the following subunits: A reference link pushing subunit, used for pushing reference links of multiple information sources of the target event; A timeline pushing subunit, used to push the timeline information of the target event; The content push subunit is used to push at least one of the text, image and video of the target event.

16. The device according to claim 12, in, The second intention recognition module also includes: The second sub-intention determination unit is used to determine that the sub-intention of the object is to obtain a news list in response to the input information not matching the title and serial number of any event in the historical news list.

17. The device according to claim 16, in, The first push module includes: a news list generating unit, configured to generate a new news list according to the input information in response to the sub-intention of the object being to obtain a news list; and The news list pushing unit is used to push the new news list.

18. The device according to claim 10 or 17, further comprising: include: A second push module, configured to push news content of the clicked event in response to receiving a click operation of the object on an event in the news list; The third push module is used for, in response to receiving a reply message from the object to the sequence number of the event in the news list, pushing the news content of the event corresponding to the sequence number.

19. An electronic device, include: at least one processor; as well as a memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method according to any one of claims 1 to 9.

20. A non-transitory computer-readable storage medium storing computer instructions, in, The computer instructions are used to cause the computer to execute the method according to any one of claims 1 to 9.

21. A computer program product, comprising a computer program, wherein the computer program is stored on at least one of a readable storage medium and an electronic device, and when the computer program is executed by a processor, the method according to any one of claims 1 to 9 is implemented.

Images