Event processing method and device

Abstract

The invention discloses an event processing method and device, and belongs to the technical field of electronics. The method comprises the steps that dialogue information in a first interface is obtained, a first event is determined from the dialogue information, and the first interface is a dialogue interface with artificial intelligence AI; under the condition that a second event exists in at least one event, fusion processing is executed on the first event and the second event to obtain a third event, the at least one event is an event in historical conversations with the AI, and the similarity between the second event and the first event is larger than or equal to a first threshold value; and storing the third event and deleting the second event.

Description

Technical Field

[0001] The present application belongs to the field of electronic technology, and specifically relates to an event processing method and device. Background Art

[0002] Artificial Intelligence (AI) dialogue systems can provide users with instant and accurate information query and question answering services based on AI's question-answering function, such as smart assistants, AI customer service, and education assistants. AI dialogue systems can provide users with more accurate and personalized services by saving user usage history, thereby enhancing the naturalness and effectiveness of interactions.

[0003] The current AI dialogue system usually saves historical records by storing the original dialogue content as historical records and extracting keywords from the dialogue content as indexes. If a user describes the same event multiple times, the AI ​​dialogue system will record the event multiple times to ensure the integrity of the event content.

[0004] However, the AI ​​dialogue system records the same event multiple times, resulting in a large number of duplications in historical records and redundancy in historical record storage. Therefore, in scenarios where users describe the same event multiple times, how to reduce the redundancy of historical record storage while ensuring the integrity of the event content is an urgent problem to be solved. Summary of the invention

[0005] The purpose of the embodiments of the present application is to provide an event processing method and device, which can reduce the redundancy of historical record storage while ensuring the integrity of event content in a scenario where a user describes the same event multiple times.

[0006] In a first aspect, an embodiment of the present application provides an event processing method, the method comprising: obtaining conversation information in a first interface, and determining a first event from the conversation information, the first interface being a conversation interface with artificial intelligence AI; in the case where there is a second event in at least one event, performing fusion processing on the first event and the second event to obtain a third event, the at least one event being an event in a historical conversation with the AI, and the second event being an event whose similarity with the first event is greater than or equal to a first threshold; storing the third event and deleting the second event.

[0007] In a second aspect, an embodiment of the present application provides an event processing device, which includes: an acquisition module, an execution module, and a processing module. The acquisition module is used to acquire dialogue information in a first interface and determine a first event from the dialogue information, and the first interface is a dialogue interface with artificial intelligence AI. The execution module is used to perform fusion processing on the first event and the second event determined by the acquisition module to obtain a third event when there is a second event in at least one event. The at least one event is an event in a historical dialogue with AI, and the second event is an event whose similarity with the first event is greater than or equal to a first threshold. The processing module is used to store the third event processed by the execution module and delete the second event.

[0008] In a third aspect, an embodiment of the present application provides an electronic device, which includes a processor and a memory, wherein the memory stores programs or instructions that can be run on the processor, and when the program or instructions are executed by the processor, the steps of the method described in the first aspect are implemented.

[0009] In a fourth aspect, an embodiment of the present application provides a readable storage medium, on which a program or instruction is stored, and when the program or instruction is executed by a processor, the steps of the method described in the first aspect are implemented.

[0010] In a fifth aspect, an embodiment of the present application provides a chip, comprising a processor and a communication interface, wherein the communication interface is coupled to the processor, and the processor is used to run a program or instruction to implement the method described in the first aspect.

[0011] In a sixth aspect, an embodiment of the present application provides a computer program product, which is stored in a storage medium and is executed by at least one processor to implement the method described in the first aspect.

[0012] In an embodiment of the present application, the conversation information in the first interface can be obtained, and the first event can be determined from the conversation information, and the first interface is a conversation interface with artificial intelligence AI; in the case where there is a second event in at least one event, the first event and the second event can be fused to obtain a third event, the at least one event is an event in the historical conversation with AI, and the second event is an event whose similarity with the first event is greater than or equal to the first threshold; the third event is stored and the second event is deleted. In this scheme, in the event of a second event in the historical conversation with AI whose similarity with the first event is greater than or equal to the first threshold, that is, in the case where there is an event identical to the first event in the historical conversation, the electronic device can perform fusion processing on the two events to obtain a third event, and then store the third event and delete the second event, so that the electronic device can fuse the repeated events into a new event, so that the new event can preserve the different contents of the two repeated events while characterizing the repeated event, maintain the integrity of the event content, and delete the existing event while storing the event, so that there is no need to store multiple repeated events, avoiding a large amount of repeated content. In this way, in the scenario where the user describes the same event multiple times, the redundancy of historical record storage can be reduced while ensuring the integrity of the event content. BRIEF DESCRIPTION OF THE DRAWINGS

[0013] Figure 1 This is one of the flow charts of the event processing method provided in the embodiment of the present application;

[0014] Figure 2 is a schematic diagram of the dialogue information provided by the embodiment of the present application as an image;

[0015] Figure 3 This is the second flowchart of the event processing method provided in the embodiment of the present application;

[0016] Figure 4 This is the third flow chart of the event processing method provided in the embodiment of the present application;

[0017] Figure 5 This is the fourth flow chart of the event processing method provided in the embodiment of the present application;

[0018] Figure 6 This is the fifth flow chart of the event processing method provided in the embodiment of the present application;

[0019] Figure 7 is a schematic diagram of an event processing device provided in an embodiment of the present application;

[0020] Figure 8 is a schematic diagram of the structure of an electronic device provided in an embodiment of the present application;

[0021] Fig. 9It is a schematic diagram of the hardware structure of the electronic device provided in the embodiment of the present application. DETAILED DESCRIPTION

[0022] The following will be combined with the drawings in the embodiments of the present application to clearly describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, rather than all the embodiments. All other embodiments obtained by ordinary technicians in this field based on the embodiments in the present application belong to the scope of protection of this application.

[0023] The terms "first", "second", etc. in the specification and claims of the present application are used to distinguish similar objects, and are not used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable under appropriate circumstances, so that the embodiments of the present application can be implemented in an order other than those illustrated or described here, and the objects distinguished by "first", "second", etc. are generally of one type, and the number of objects is not limited. For example, the first object can be one or more. In addition, "and / or" in the specification and claims represents at least one of the connected objects, and the character " / " generally indicates that the objects associated with each other are in an "or" relationship.

[0024] The terms "at least one (item)", "at least one of" and the like in this application refer to any one, any two or a combination of more than two of the objects included therein. For example, at least one (item) of a, b, and c can be represented by: "a", "b", "c", "a and b", "a and c", "b and c" and "a, b and c", where a, b, and c can be single or multiple. Similarly, "at least two (items)" refers to two or more, and its meaning is similar to that of "at least one (item)".

[0025] The event processing method and device provided in the embodiments of the present application are described in detail below through specific embodiments and their application scenarios in conjunction with the accompanying drawings.

[0026] The embodiments of the present application can be applied to a scenario where an electronic device stores the conversation information as a historical record after a user has a conversation with an AI. For example, the AI ​​can be an intelligent assistant, intelligent customer service, education assistant, health assistant, etc.

[0027] For example, taking AI as an intelligent assistant, after a user has a conversation with the intelligent assistant, the user actively closes the intelligent assistant or the intelligent assistant automatically exits, so that the electronic device can store the original conversation content as a history record and extract keywords from the conversation content as an index. If the user describes the same event multiple times, the intelligent assistant will record the event multiple times to ensure the content integrity of the event.

[0028] However, when AI records the same event multiple times, it will lead to a large number of duplications of historical records, resulting in redundancy in historical record storage. Therefore, in the scenario where users describe the same event multiple times, how to ensure the integrity of the event content while reducing the redundancy of historical record storage is an urgent problem to be solved.

[0029] The embodiment of the present application provides an event processing method and device, which can obtain the dialogue information in the first interface and determine the first event from the dialogue information, wherein the first interface is a dialogue interface with artificial intelligence AI; in the case where there is a second event in at least one event, the first event and the second event can be fused to obtain a third event, wherein the at least one event is an event in the historical dialogue with AI, and the second event is an event whose similarity with the first event is greater than or equal to the first threshold; the third event is stored and the second event is deleted. In this scheme, in the case where there is a second event in the event in the historical dialogue with AI whose similarity with the first event is greater than or equal to the first threshold, that is, in the case where there is an event identical to the first event in the historical dialogue, the electronic device can perform fusion processing on the two events to obtain a third event, and then store the third event and delete the second event, so that the electronic device can fuse the repeated events into a new event, so that the new event can preserve the different contents of the two repeated events while representing the repeated event, thereby maintaining the integrity of the event content, and while storing the event, delete the existing event, thereby eliminating the need to store multiple repeated events and avoiding a large amount of repeated content. This can reduce the redundancy of historical record storage while ensuring the integrity of event content in scenarios where users describe the same event multiple times.

[0030] The event processing method provided in the embodiment of the present application may be executed by an event processing device, which may be an electronic device, or a functional module or functional entity in the electronic device. The technical solution provided in the embodiment of the present application is described below using an electronic device as an example.

[0031] Figure 1 A flow chart of an event processing method provided by an embodiment of the present application is shown. Figure 1 As shown, the event processing method provided in the embodiment of the present application may include the following steps 201 to 203.

[0032] Step 201: The electronic device obtains dialog information in a first interface, and determines a first event from the dialog information.

[0033] In the embodiment of the present application, the above-mentioned first interface is a dialogue interface with AI.

[0034] It should be noted that the above-mentioned AI is an intelligent assistant or chatbot that can simulate human conversations. These AIs can use deep learning, natural language processing (NLP) and dialogue management technology to understand and respond to users' questions or requests and provide information, entertainment or services.

[0035] Optionally, in an embodiment of the present application, the above-mentioned AI may include but is not limited to any of the following: intelligent assistant, intelligent customer service, education assistant, health assistant, etc.

[0036] It should be noted that the event determined from the dialogue information is the specific content recorded in the dialogue information between the user and the AI, and the event is composed of event elements.

[0037] Optionally, in the embodiment of the present application, the electronic device may extract event elements of the event, which include at least one of the following: the event itself, the event time, the event location, the event person, and the event importance.

[0038] In the embodiment of the present application, the above event itself is the core of the event, describing what happened specifically. Compared with the original dialogue information, the event itself can remove redundant information in the dialogue information.

[0039] For example, the conversation information is "I ran into our high school chemistry teacher, Mr. Liu, in Central Park yesterday. He didn't look much changed and was still as energetic. We talked for a long time, and he told me that he started studying botany after retirement and recognized several rare plants in the park. The most surprising thing was that he still remembered that my favorite element was carbon, which made me feel very warm. He invited me to go to the botanical garden together next time I was free, and I agreed on the spot. What an unexpected reunion!" The electronic device can extract the event itself as "I ran into our high school chemistry teacher, Mr. Liu, in Central Park yesterday. I learned that Mr. Liu studied botany after retirement and was recognized that his favorite element was carbon. We agreed to go to the botanical garden together next time."

[0040] Optionally, in the embodiment of the present application, the above event time is the time point or time period when the event occurs. It can be a precise time, such as "10:00 am on August 29, 2024", or a vague time description, such as "yesterday", "spring", "recently", etc.

[0041] Optionally, in the embodiment of the present application, the above-mentioned event location is the geographical location where the event occurs, which can be a specific address, such as "a certain building in a certain district of a certain city", or an abstract location, such as "a game room", "an online meeting", etc.

[0042] Optionally, in the embodiment of the present application, the above-mentioned event person is a main participant of the event, which can be a specific person, such as "Zhang San" or "Xiao Wang", or an organization or group, such as "a company" or "basketball club".

[0043] Optionally, in the embodiment of the present application, the above event importance is used to describe the influence or importance of the event, which can be judged according to the nature of the event, the impact on the participants, and the impact on the wider society or industry. The event importance can be a general importance, such as "important", "general", "unimportant", etc., or the importance level can be determined according to the specific importance, such as level one to level ten.

[0044] For example, taking "the company decides to lay off a large number of employees" as an example, this event is a major decision of the company, which will directly affect the employment of the company's employees, and have a far-reaching impact on the company's organizational structure, corporate culture and future business strategies. It may also arouse public attention and social discussion. The electronic device can determine the event as "important" level, or it can specifically evaluate the importance level of the event, such as determining it as "level ten".

[0045] As another example, taking "Xiao Wang takes sick leave" as an example, this event is a personal health event. Although it may have a great impact on the individual and the family, from the perspective of the company's overall operations, the short-term leave of a single employee has a relatively limited impact on the business. It is a personal event with a small impact range. The electronic device can determine the event as a "general" level, or it can specifically evaluate the importance level of the event, such as determining it as "level five".

[0046] As another example, taking "what to eat for lunch today" as an example, this event is a daily life event, which is relatively common in daily communication and has little impact on personal life. The electronic device can determine the event as "unimportant" level, or it can specifically evaluate the importance level of the event, for example, determine it as "level one".

[0047] Optionally, in an embodiment of the present application, the above-mentioned conversation information may include at least one of text, image, voice and video.

[0048] Optionally, in an embodiment of the present application, when the conversation information is text information, the electronic device can use the text information as the first text and fill in the extraction instruction for extracting the first event. For example, the extraction instruction can be: "As an event extraction assistant, you need to extract user events from the following inputs. Events have 5 elements: the event itself, the event time, the event location, the event person, and the event importance. The output format is JSON. [First text]". Among them, "[First text]" means to fill in the above-mentioned first text here, and "JSON" means JavaScript Object Notation (JSON), which is a data format used to store and transmit data. Then, the electronic device can use a large language model to process the first text based on the extraction instruction and extract the first event.

[0049] For example, taking the first text "Yesterday afternoon, Zhang San signed a very important contract at the head office." as an example, the electronic device can fill the first text into the extraction instruction, such as "As an event extraction assistant, you need to extract user events from the following input. Events have 5 elements: event itself, event time, event location, event person, event importance, and the output format is JSON. Yesterday afternoon, Zhang San signed a very important contract at the head office." Then, the electronic device can use the large language model to extract the first event based on the extraction instruction as:

[0050] Event itself: Yesterday afternoon, Zhang San signed an important contract at the head office;

[0051] Event time: Yesterday afternoon;

[0052] Event location: Head office;

[0053] Person in the event: Zhang San;

[0054] Event importance: Important (or level eight).

[0055] Optionally, in an embodiment of the present application, when the dialogue information is image, voice or video information, the electronic device can recognize the dialogue information and extract text information, such as recognizing the content displayed in the image information or video information, recognizing text, characters, scenes and other information, and summarizing this information in the form of text as a first text, and filling in an extraction instruction for extracting a first event. For another example, voice recognition is performed on the sound in the voice information or video information, and the recognized information is used as the first text, and an extraction instruction for extracting the first event is filled in. Then, the electronic device can use a large language model to process the first text based on the extraction instruction and extract the first event.

[0056] For example, Figure 2As shown, taking the dialogue information as a winning photo of Zhang San participating in a mathematics competition as an example, the electronic device can identify the character information in the photo, such as Zhang San 22, mathematicians 23 and 24 in the photo on the background wall, the award presenter 25 on the podium, and the audience 26 in the audience. The electronic device can also recognize the text in the photo, such as the text 27 on the background wall "The Third Apple Cup Mathematics Competition", the photo watermark text 28 in the lower left corner "2023.10.20 14:30", the text 29 on Zhang San's chest badge "Zhang San", and the text 30 in the certificate in Zhang San's hand "First Place". The electronic device can also recognize the scene information in the photo, such as the podium 31, the certificate 32, and the auditorium 33. The electronic device can summarize this information in the form of text as a first text, such as "On October 20, 2023 at 14:30, Zhang San won the first place in the Third Apple Cup Mathematics Competition". Then the electronic device can use a large language model to process the first text based on the extraction instruction and extract the first event:

[0057] Event itself: At 14:30 on October 20, 2023, Zhang San won the first place in the 3rd Apple Cup Mathematics Competition (since the first text is summarized by electronic equipment and is relatively concise, the story itself is the first text);

[0058] Event time: October 20, 2023 14:30;

[0059] Event location: school auditorium (estimated based on scene layout information);

[0060] Event characters: Zhang San (contestant), award presenter, audience (participants);

[0061] Event Importance: Important.

[0062] Here, the event importance is marked as important because the event is important to Zhang San and may have a significant impact on Zhang San's study and future. In practical applications, the event importance can be determined based on more contextual information or based on specific criteria.

[0063] Optionally, in the embodiment of the present application, combined with Figure 1 ,like Figure 3 As shown, the "obtaining the dialog information in the first interface" in the above step 201 can be implemented through the following step 201a.

[0064] Step 201a: When the first condition is met, obtain the dialog information in the first interface.

[0065] In the embodiment of the present application, the first condition includes at least one of the following:

[0066] No input to the first interface is received within a first time period;

[0067] A closing input for the first interface is received.

[0068] Optionally, in an embodiment of the present application, the input to the first interface may include but is not limited to any of the following: a dialogue input to the first interface, a copy input to the first interface, a share input to the first interface, etc.

[0069] Optionally, in an embodiment of the present application, the first interface may include an input control for inputting dialogue information.

[0070] Optionally, in the embodiment of the present application, the above-mentioned dialogue input can be an input to the above-mentioned input control, such as click input, long press input, sliding input, etc., for communicating with AI. For example, a text message is input and sent in the input control so that the electronic device can display a reply message corresponding to the text message.

[0071] Optionally, in an embodiment of the present application, the copy input may be an input of the conversation information, for copying the conversation information. For example, the user may long press the conversation information to cause the electronic device to display the conversation options, and then click the copy option in the conversation options to cause the electronic device to copy the conversation.

[0072] Optionally, in the embodiment of the present application, the above-mentioned sharing input may be an input of the above-mentioned conversation information, which is used to share the conversation information. For example, the user may long-press the conversation information to make the electronic device display the conversation options, and then click the sharing option in the conversation options to make the electronic device display the application identifiers of multiple social applications, and the user may click any application identifier to make the electronic device share the conversation information using the social application.

[0073] In the embodiment of the present application, the closing input of the first interface is used to close the first interface.

[0074] Optionally, in the embodiment of the present application, the first interface may include a close control, and the close control is used to close the first interface.

[0075] Optionally, in an embodiment of the present application, the closing input for the first interface may be a click input, a long press input, etc. of a closing control by the user, or may be a closing input of the electronic device by the user, so that the electronic device closes all interfaces and shuts down.

[0076] In the embodiment of the present application, when the electronic device does not receive any input to the first interface within the first time period, or when the electronic device receives a closing input to the first interface, the electronic device may close the first interface.

[0077] In this way, the electronic device can automatically obtain the conversation information in the first interface for storage when the user has no operation for a period of time or the user closes the first interface, reducing the need for the user to manually save the conversation information, saving the user's operations and reducing the risk of losing the conversation information due to forgetting to save.

[0078] Step 202: When there is a second event in at least one event, the electronic device performs fusion processing on the first event and the second event to obtain a third event.

[0079] In an embodiment of the present application, the at least one event is an event in a historical conversation with the AI, and the second event is an event whose similarity with the first event is greater than or equal to a first threshold.

[0080] Optionally, in the embodiment of the present application, the first threshold may be a threshold preset by the system (eg, 90%), or may be arbitrarily set by the user according to actual usage requirements.

[0081] Optionally, in the embodiment of the present application, “the similarity between the first event and the second event is greater than or equal to a first threshold” may include at least one of the following:

[0082] 1) Similarity of the events themselves: The descriptions or contents of the first and second events are very close in semantics and may involve the same or related operations, such as "Xiao Wang helps Xiao Zhang repair his bicycle"

[0083] and "Xiao Wang teaches Xiao Zhang how to change a bicycle tire". Both events involve Xiao Wang and Xiao Zhang as well as bicycle repair, and the event contents are very similar in semantics.

[0084] 2) Temporal proximity: The time interval between the first event and the second event is short, or they occur in the same time period. For example, "Xiao Li reviewed the college entrance examination mathematics at 10:00 am on July 10" and "Xiao Li reviewed the college entrance examination English at 10:30 am on July 10". The two events occurred on the same day with a time interval of only half an hour, and the temporal proximity is relatively high.

[0085] 3) Coincidence in location: The first event and the second event occur at the same or nearby location, for example, "Zhang Ming was jogging in the park" and "Zhang Ming picked up a wallet while jogging in the park". Both events occurred in the park, the same location.

[0086] 4) Consistency of participating characters: The main characters involved in the first event and the second event are the same in both events. For example, "Liu Yang, Wang Gang, and Han Meimei discussed the project in a cafe" and "Liu Yang, Wang Gang, and Han Meimei went to have lunch". The participating characters in the two events are exactly the same, and the consistency of the participating characters is significant.

[0087] 5) Matching of importance: The urgency, scope of impact or other importance indicators of the first event and the second event are similar. For example, "the company decided to lay off a large number of employees" and "the company held an emergency meeting to discuss market plans". Both events involve the company's decision-making level and have a significant impact on the company's operations and development. The importance indicators match.

[0088] Optionally, in an embodiment of the present application, the above-mentioned fusion processing can be for the electronic device to fill in the first event and the second event into the fusion instruction respectively, for example, "As an event fusion assistant, you need to merge events with different descriptions into one event. An event has 5 elements: the event itself, the event time, the event location, the event person, and the event importance. The output format is JSON. Event description 1: [first event]\nEvent description 2: [second event]". Among them, "[first event]" means to fill in the first event here, and "[second event]" means to fill in the second event here. Then, the electronic device can use a large language model to process the first event and the second event based on the fusion instruction, and merge them into a third event.

[0089] In the embodiment of the present application, the third event includes complete information in the first event and the second event, that is, the first event and the second event can be summarized by the third event.

[0090] For example, the first event is "At 10 a.m. on Wednesday, Zhang San met his high school friend Li Si at the City Cafe. The two had a great conversation and decided to start a business together to engage in environmental protection technology projects." The second event is "At 11 a.m. on Wednesday, Zhang San and Li Si studied market trends together at the City Cafe to prepare for their business plans." The fused third event can be:

[0091] Event itself: Zhang San and Li Si met at the City Cafe at 10 a.m. on Wednesday and decided to start a business together. At 11 a.m., they studied market trends and prepared for an environmental technology project.

[0092] Event time: Wednesday at 10 a.m., Wednesday at 11 a.m.;

[0093] Event location: City Cafe;

[0094] Characters in the incident: Zhang San, Li Si;

[0095] Event Importance: Important.

[0096] Optionally, in the embodiment of the present application, combined with Figure 1 ,like Figure 4 As shown, the "perform fusion processing on the first event and the second event to obtain a third event" in the above step 202 can be implemented by the following steps 202a to 202c.

[0097] Step 202a: The electronic device obtains at least one first event element of the first event and at least one second event element of the second event.

[0098] Step 202b: If a first event element and a second event element are the same, the electronic device performs a deletion process on a first event element or a second event element, and determines at least one first event element and at least one second event element after the deletion process as a third event element.

[0099] Optionally, in an embodiment of the present application, if, among the at least one first event element and the at least one second event element, a first event element and a second event element are the same, the electronic device may delete the first event element, or delete the second event element, and determine the remaining second event element or the first event element as the third event element.

[0100] Optionally, in an embodiment of the present application, among the at least one first event element and the at least one second event element, when two or more first event elements and two or more second event elements are respectively the same, the electronic device may delete the two or more first event elements, or delete the two or more second event elements, or delete at least one first event element among the two or more first event elements and at least one second event element among the two or more second event elements, and determine the remaining second event elements and first event elements as third event elements.

[0101] It can be understood that the electronic device can determine whether the same event elements exist in the above-mentioned at least one first event element and the above-mentioned at least one second event element, and if the same event elements exist, delete the duplicate event elements, retain only one of the two duplicate event elements, and determine the remaining at least one first event element and at least one second event element as the third event element.

[0102] Exemplarily, the event elements of the first event include:

[0103] Event itself: At 10:00 am on August 30, 2023, Zhang San and Li Si discussed the project details in the city square;

[0104] Event time: 10:00 am, August 30, 2023;

[0105] Event location: City Square;

[0106] Characters in the incident: Zhang San, Li Si;

[0107] Event importance: Average.

[0108] The event elements of the second event include:

[0109] The event itself: At 10:00 am on August 30, 2023, Li Si and Wang Wu discussed development strategies in the city square;

[0110] Event time: 10:00 am, August 30, 2023;

[0111] Event location: City Square;

[0112] Characters involved in the incident: Li Si, Wang Wu;

[0113] Event importance: Average.

[0114] The electronic device can determine that the event characters and the event itself are not exactly the same, but the event time, event location and event importance are the same and there are repetitions. Then the electronic device can delete the repeated event time, event location and event importance, and only retain one event time, event location and event importance, and merge the event characters into: "Zhang San, Li Si, Wang Wu", and merge the event itself into: "At 10:00 am on August 30, 2023, Zhang San, Li Si and Wang Wu discussed project details and development strategies in the city square", thereby determining the third event element as:

[0115] Event itself: At 10:00 am on August 30, 2023, Zhang San, Li Si and Wang Wu discussed project details and development strategies in the city square; (integration of two different events themselves)

[0116] Event time: 10:00 am, August 30, 2023; (keep one)

[0117] Event location: City Square; (keep one)

[0118] Event characters: Zhang San, Li Si, Wang Wu; (merge the event characters of two events)

[0119] Event importance: General. (Keep one)

[0120] Optionally, after the electronic device performs deletion processing on the repeated event elements, if the number of the first event elements is zero, the electronic device may determine at least one second event element as the third event element. Similarly, if the number of the second event elements is zero, the electronic device may determine at least one first event element as the third event element.

[0121] Step 202c: The electronic device determines a third event according to the third event element.

[0122] In the embodiment of the present application, the electronic device may use the third event element as the event element of the third event, thereby determining the third event.

[0123] In this way, when there is a second event in the historical conversation with the AI ​​whose similarity with the first event is greater than or equal to the first threshold, the electronic device can fuse the first event and the second event to obtain a third event that includes all event elements of the first event and the second event, and removes repeated event elements, that is, a third event that can summarize the complete information in the first event and the second event, so that the electronic device can store the third event to save the content of the first event and the second event, without having to separately store the first event and the second event with a higher degree of similarity, thereby avoiding storing redundant parts of the event (that is, repeated event elements) in the historical records.

[0124] Optionally, in the embodiment of the present application, combined with Figure 1 ,like Figure 5 As shown, before "performing fusion processing on the first event and the second event to obtain a third event" in the above step 202, the event processing method provided in the embodiment of the present application also includes the following steps 301 to 303.

[0125] Step 301: The electronic device obtains first event information corresponding to a first event.

[0126] In an embodiment of the present application, the above-mentioned first event information includes event time information, time and location information, a first sparse vector and a first dense vector, and the first sparse vector and the first dense vector are both used to characterize the above-mentioned first event.

[0127] Optionally, in the embodiment of the present application, the electronic device may determine the event time in the event element as the event time information, and determine the event location in the event element as the event location information. Alternatively, the electronic device may also extract the event time information from the event itself, and extract the event location information from the event itself.

[0128] Optionally, in an embodiment of the present application, the electronic device may adopt a multi-lingual long text vector retrieval model (Multi-Lingual Long Text Vector Retrieval Model, BGE-M3) to generate a first sparse vector and a first dense vector according to the event itself of the first event.

[0129] It should be noted that the above-mentioned BGM-M3 is an advanced text embedding model used to generate vector representation of text.

[0130] Step 302: The electronic device determines at least one second event information from event information of at least one event.

[0131] In the embodiment of the present application, the similarity between each of the second event information and one of the first event information is greater than or equal to a second threshold.

[0132] In an embodiment of the present application, the second event information includes event time information, time and location information, a second sparse vector and a second dense vector, and both the second sparse vector and the second dense vector are used to characterize the second event.

[0133] Optionally, in the embodiment of the present application, the second threshold may be a threshold preset by the system (eg, 90%), or may be arbitrarily set by the user according to actual usage requirements.

[0134] Optionally, in the embodiment of the present application, when the first event information is event time information, the similarity may correspond to the time interval, for example, when the second threshold is 90%, the time interval may be 1 hour, when the similarity is 95%, the time interval may be 30 minutes, etc. At this time, the event time information whose similarity with the first event information is greater than or equal to the second threshold may be: the event time information that is the same as the event time information in the first event information or whose time interval is less than the time interval corresponding to the second threshold (i.e., within 1 hour).

[0135] Optionally, in the embodiment of the present application, when the first event information is event location information, the similarity may correspond to the location distance, for example, when the second threshold is 90%, the location distance may be 1000 meters, when the similarity is 95%, the location distance may be 500 meters, etc. At this time, the similarity with the first event information greater than or equal to the second threshold may be: event location information that is the same as the event location information in the first event information or has a location distance less than a threshold (i.e., within 1000 meters).

[0136] Optionally, in an embodiment of the present application, the electronic device may fill the event itself of the first event into an extraction instruction for extracting the event time information and event location information in the first event information. For example, the extraction instruction may be: "You are an expert in time and location extraction. Based on user input, extract the absolute time and location. [Event itself]". Among them, "[Event itself]" means that the event itself of the above-mentioned first event is filled in here. Then, the electronic device can use a large language model to process the event itself based on the extraction instruction, and extract the event time information and event location information in the first event information.

[0137] Optionally, in an embodiment of the present application, when the first event information is a first sparse vector or a first dense vector, the electronic device may use an artificial intelligence similarity search method to search for a second sparse vector or a second dense vector whose similarity to the first sparse vector or the first dense vector is greater than or equal to a second threshold.

[0138] Step 303: The electronic device arranges at least one piece of second event information in order of similarity with the information in the first event information, and determines the events corresponding to the first N pieces of second event information in the at least one piece of second event information as second events.

[0139] In the embodiment of the present application, the above N is a positive integer.

[0140] In an embodiment of the present application, the electronic device can respectively obtain the information in the above-mentioned first event information and the similarity of the above-mentioned at least one second event information, that is, respectively obtain: the similarity of at least one second event information similar to the event time information in the first event information, the similarity of at least one second event information similar to the event location information in the first event information, the similarity of at least one second event information similar to the first sparse vector in the first event information, and the similarity of at least one second event information similar to the first dense vector in the first event information, and arrange the at least one second event information in the order of the similarity with the information in the first event information (that is, from large to small), and determine the events corresponding to the first N second event information with the largest similarity as the second event.

[0141] Exemplarily, the similarity between event time information 10 and event time information 11 in the first event information is 91%, and the similarity between event time information 12 and event time information 12 is 96%. The similarity between event location information 13 and event location information 14 in the first event information is 92%, and the similarity between event location information 15 and event location information 15 is 94%. The similarity between the first sparse vector 16 and vector 17 is 99%, and the similarity between the first sparse vector 16 and vector 18 is 90%. The similarity between the second sparse vector 19 and vector 20 is 98%, and the similarity between the second sparse vector 19 and vector 21 is 93%. Then, according to the order of similarity, the order from large to small is: vector 17 (99%), vector 20 (98%), event time information 12 (96%), event location information 15 (94%), vector 21 (93%), event location information 14 (92%), event time information 11 (91%), vector 18 (90%). Assuming that N is 3, the electronic device may determine the events corresponding to the first three second event information with the greatest similarity as the second event, that is, determine the events corresponding to vector 17, vector 20, and event time information 12 as the second event.

[0142] In this way, the electronic device can search for event information with a high degree of similarity to the first event information from multiple angles such as event time, event location, sparse vector, dense vector, etc., thereby improving the accuracy and credibility of the search results.

[0143] Step 203: The electronic device stores the third event and deletes the second event.

[0144] Optionally, in the embodiment of the present application, combined with Figure 1 ,like Figure 6 As shown, the above step 203 can be implemented through the following steps 203a and 203b.

[0145] Step 203a: The electronic device stores the third event in the first database, and deletes the second event from the first database.

[0146] In an embodiment of the present application, the first database is used to store events in the conversation with the AI.

[0147] Step 203b: store the third sparse vector and the third dense vector corresponding to the third event in the second database, and delete the second sparse vector and the second dense vector corresponding to the second event from the second database.

[0148] In an embodiment of the present application, the third sparse vector and the third dense vector are generated based on event elements corresponding to the third event, and the second database is used to store sparse vectors and dense vectors corresponding to events in the conversation with the AI.

[0149] Optionally, in an embodiment of the present application, the electronic device may adopt the BGE-M3 model to generate a third sparse vector and a third dense vector according to the event itself in the event element corresponding to the third event.

[0150] In this way, the electronic device can delete the second event while storing the third event, thereby reducing the occupation of the system storage space by the second event and improving the utilization rate of the system storage space.

[0151] The embodiment of the present application provides an event processing method, in the case where there is a second event in the events in the historical conversation with AI whose similarity with the first event is greater than or equal to a first threshold, that is, in the case where there is already an event identical to the first event in the historical conversation, the electronic device can perform fusion processing on the two events to obtain a third event, and then store the third event and delete the second event, so that the electronic device can fuse the repeated events into a new event, so that the new event can preserve the different contents of the two repeated events while characterizing the repeated event, thereby maintaining the integrity of the event content, and while storing the event, delete the existing event, thereby eliminating the need to store multiple repeated events and avoiding a large amount of repeated content. In this way, in the scenario where the user describes the same event multiple times, the redundancy of historical record storage can be reduced while ensuring the integrity of the event content.

[0152] The following is an implementation process of a specific example to illustrate the event processing method provided in the embodiment of the present application.

[0153] Take the conversation information as the first text: "At 10:00 am on August 30, 2023, Zhang San and Li Si discussed project details in the city square" as an example. When receiving the user's close input on the first interface, the electronic device can fill the first text into the extraction instruction, such as "As an event extraction assistant, you need to extract user events from the following input. Events have 5 elements: event itself, event time, event location, event person, event importance, and the output format is JSON. At 10:00 am on August 30, 2023, Zhang San and Li Si discussed project details in the city square." Then, the electronic device can use a large language model to extract the first event based on the extraction instruction as:

[0154] Event itself: At 10:00 am on August 30, 2023, Zhang San and Li Si discussed the project details in the city square;

[0155] Event time: 10:00 am, August 30, 2023;

[0156] Event location: City Square;

[0157] Characters in the incident: Zhang San, Li Si;

[0158] Event importance: Average.

[0159] Then, the electronic device can obtain the event information of the first event, including: event time information 10 (10:00 am on August 30, 2023), event location information 13 (city square), first sparse vector 16, and first dense vector 19. The electronic device can determine that the similarity between the event time information 10 (10:00 am on August 30, 2023) and the event time information 11 (10:00 am on August 30, 2023) in the first event information is 100%, and the similarity with the event time information 12 (10:36 am on August 30, 2023) is 96%. The event location information 13 (city square) in the first event information is 100% similar to the event location information 14 (city square), and 94% similar to the event location information 15 (600 meters east of the city square shopping mall). The first sparse vector 16 has a similarity of 99% with the vector 17 and a similarity of 90% with the vector 18. The second sparse vector 19 has a similarity of 98% with vector 20 and a similarity of 93% with vector 21. Then, according to the order of similarity, the order from large to small is: event time information 11 (100%) and event location information 14 (100%), vector 17 (99%), vector 20 (98%), event time information 12 (96%), event location information 15 (94%), vector 21 (93%), vector 18 (90%). Assuming N is 3, the electronic device can determine the events corresponding to the first three second event information with the greatest similarity as the second event, that is, the event corresponding to event time information 11 (10:00 am on August 30, 2023), event location information 14 (city square), and vector 17 as the second event. Assuming that the events corresponding to the three second event information are the same event, the event is:

[0160] The event itself: At 10:00 am on August 30, 2023, Li Si and Wang Wu discussed development strategies in the city square;

[0161] Event time: 10:00 am, August 30, 2023;

[0162] Event location: City Square;

[0163] Characters involved in the incident: Li Si, Wang Wu;

[0164] Event importance: Average.

[0165] The electronic device can then determine that the event characters and the event itself are not exactly the same, but the event time, event location, and event importance are the same and there are repetitions. The electronic device can then delete the repeated event time, event location, and event importance, retaining only one event time, event location, and event importance, and merge the event characters into: "Zhang San, Li Si, Wang Wu", and merge the event itself into: "At 10:00 am on August 30, 2023, Zhang San, Li Si, and Wang Wu discussed project details and development strategies in the city square", thereby determining the third event element as:

[0166] Event itself: At 10:00 am on August 30, 2023, Zhang San, Li Si and Wang Wu discussed project details and development strategies in the city square; (integration of two different events themselves)

[0167] Event time: 10:00 am, August 30, 2023; (keep one)

[0168] Event location: City Square; (keep one)

[0169] Event characters: Zhang San, Li Si, Wang Wu; (merge the event characters of two events)

[0170] Event importance: General. (Keep one)

[0171] The electronic device may use the third event element as the event element of the third event to determine the third event. Then the electronic device may use the BGM-M3 model to generate a third sparse vector and a third dense vector according to the event itself in the event element of the third event. Finally, the electronic device may store the third event in the first database, delete the second event from the first database, store the third sparse vector and the third dense vector in the second database, and delete the second sparse vector and the second dense vector corresponding to the second event from the second database.

[0172] Each of the above-mentioned method embodiments, or various possible implementation methods in each method embodiment can be executed separately, or any two or more of them can be executed in combination with each other. The specific implementation method can be determined according to actual usage requirements, and the embodiments of the present application do not limit this.

[0173] The event processing method provided in the embodiment of the present application can be executed by an event processing device. In the embodiment of the present application, the event processing device provided in the embodiment of the present application is described by taking the event processing method executed by the event processing device as an example.

[0174] Figure 7 FIG. 2 shows a possible structural diagram of an event processing device involved in some embodiments of the present application. Figure 7 As shown, the event processing device 70 may include: an acquisition module 71, an execution module 72 and a processing module 73.

[0175] Among them, the acquisition module 71 is used to obtain dialogue information in the first interface and determine the first event from the dialogue information. The first interface is a dialogue interface with AI.

[0176] The execution module 72 is used to perform fusion processing on the first event and the second event determined by the acquisition module 71 to obtain a third event when there is a second event in at least one event, wherein the at least one event is an event in the historical dialogue with the AI, and the second event is an event whose similarity with the first event is greater than or equal to a first threshold.

[0177] The processing module 73 is used to store the third event processed by the execution module 72 and delete the second event.

[0178] In one possible implementation, the execution module 72 is specifically used to obtain at least one first event element of the first event and at least one second event element of the second event determined by the acquisition module 71; and if a first event element and a second event element are the same, then a deletion process is performed on the first event element or the second event element, and the at least one first event element and the at least one second event element after the deletion process are determined as third event elements; and a third event is determined based on the third event element.

[0179] In one possible implementation, the device also includes: a determination module; an acquisition module 71, which is also used to perform fusion processing on the first event and the second event in the execution module 72 to obtain the first event information corresponding to the first event before obtaining the third event, the first event information includes event time information, time and location information, a first sparse vector and a first dense vector, and the first sparse vector and the first dense vector are both used to characterize the first event; a determination module, which is used to determine at least one second event information from the event information of the at least one event obtained by the acquisition module 71, and the similarity between each second event information and one of the information in the first event information is greater than or equal to a second threshold; the determination module is also used to arrange the at least one second event information in order of similarity with the information in the first event information, and determine the events corresponding to the first N second event information in the at least one second event information as the second event, where N is a positive integer.

[0180] In a possible implementation, the acquisition module 71 is specifically used to: acquire the conversation information in the first interface when a first condition is met; wherein the first condition includes at least one of the following: no input to the first interface is received within a first time period; and a closing input to the first interface is received.

[0181] In one possible implementation, the processing module 73 is specifically used to: store the third event processed by the execution module 72 in a first database, and delete the second event from the first database, the first database being used to store events in a conversation with the AI; store a third sparse vector and a third dense vector corresponding to the third event in a second database, and delete the second sparse vector and the second dense vector corresponding to the second event from the second database, the third sparse vector and the third dense vector being generated based on event elements corresponding to the third event, the second database being used to store sparse vectors and dense vectors corresponding to events in a conversation with the AI.

[0182] In an embodiment of the present application, an event processing device is provided. When there is a second event in the events in the historical conversation with AI whose similarity to the first event is greater than or equal to a first threshold, that is, when there is an event identical to the first event in the historical conversation, the event processing device can perform fusion processing on the two events to obtain a third event, and then store the third event and delete the second event. Thus, the event processing device can fuse the repeated events into a new event, so that the new event can preserve the different contents of the two repeated events while representing the repeated event, thereby maintaining the integrity of the event content, and delete the existing event while storing the event, thereby eliminating the need to store multiple repeated events and avoiding a large amount of repeated content. In this way, in a scenario where a user describes the same event multiple times, the redundancy of historical record storage can be reduced while ensuring the integrity of the event content.

[0183] The event processing device in the embodiment of the present application can be an electronic device, or a component in the electronic device, such as an integrated circuit or a chip. The electronic device can be a terminal, or other devices other than a terminal. Exemplarily, the electronic device can be a mobile phone, a tablet computer, a laptop computer, a PDA, a vehicle-mounted electronic device, a mobile Internet device (Mobile Internet Device, MID), an augmented reality (augmented reality, AR) / virtual reality (virtual reality, VR) device, a robot, a wearable device, an ultra-mobile personal computer (ultra-mobile personal computer, UMPC), a netbook or a personal digital assistant (personal digital assistant, PDA), etc., and can also be a server, a network attached storage (Network Attached Storage, NAS), a personal computer (personal computer, PC), a television (television, TV), a teller machine or a self-service machine, etc., which is not specifically limited in the embodiment of the present application.

[0184] The event processing device in the embodiment of the present application may be a device having an operating system. The operating system may be an Android operating system, an iOS operating system, or other possible operating systems, which are not specifically limited in the embodiment of the present application.

[0185] The event processing device provided in the embodiment of the present application can implement each process implemented in the above method embodiment. To avoid repetition, it will not be repeated here.

[0186] Alternatively, if Figure 8 As shown, an embodiment of the present application also provides an electronic device 1000, including a processor 1001 and a memory 1002, wherein the memory 1002 stores programs or instructions that can be executed on the processor 1001, and when the program or instructions are executed by the processor 1001, the various steps of the above-mentioned event processing method embodiment are implemented, and the same technical effect can be achieved. To avoid repetition, they are not repeated here.

[0187] It should be noted that the electronic devices in the embodiments of the present application include the mobile electronic devices and non-mobile electronic devices mentioned above.

[0188] Fig. 9 A schematic diagram of the hardware structure of an electronic device to implement an embodiment of the present application.

[0189] The electronic device 100 includes but is not limited to components such as a radio frequency unit 101, a network module 102, an audio output unit 103, an input unit 104, a sensor 105, a display unit 106, a user input unit 107, an interface unit 108, a memory 109, and a processor 110.

[0190] Those skilled in the art will appreciate that the electronic device 100 may also include a power source (such as a battery) for supplying power to various components, and the power source may be logically connected to the processor 110 through a power management system, thereby implementing functions such as managing charging, discharging, and power consumption management through the power management system. Fig. 9 The electronic device structure shown in the figure does not constitute a limitation on the electronic device. The electronic device may include more or fewer components than shown in the figure, or combine certain components, or arrange the components differently, which will not be described in detail here.

[0191] The processor 110 is used to obtain dialogue information in a first interface and determine a first event from the dialogue information. The first interface is a dialogue interface with AI.

[0192] The processor 110 is used to perform fusion processing on the first event and the second event determined by the processor 110 to obtain a third event when there is a second event in at least one event, wherein the at least one event is an event in the historical dialogue with the AI, and the second event is an event whose similarity with the first event is greater than or equal to a first threshold.

[0193] The memory 109 is used to store the third event and delete the second event.

[0194] In one possible implementation, the processor 110 is specifically used to obtain at least one first event element of a first event and at least one second event element of a second event; and if a first event element and a second event element are the same, perform deletion processing on the first event element or the second event element, and determine the at least one first event element and the at least one second event element after the deletion processing as a third event element; and determine a third event based on the third event element.

[0195] In one possible implementation, the device also includes: a determination module; a processor 110, which is also used to obtain first event information corresponding to the first event before performing fusion processing on the first event and the second event to obtain the third event, the first event information including event time information, time and location information, a first sparse vector and a first dense vector, and the first sparse vector and the first dense vector are both used to characterize the first event; a determination module, which is used to determine at least one second event information from the event information of the at least one event, and the similarity between each second event information and one of the information in the first event information is greater than or equal to a second threshold; the determination module is also used to arrange the at least one second event information in order of similarity with the information in the first event information, and determine the events corresponding to the first N second event information in the at least one second event information as the second event, where N is a positive integer.

[0196] In one possible implementation, the processor 110 is specifically used to: obtain conversation information in the first interface when a first condition is met; wherein the first condition includes at least one of the following: no input to the first interface is received within a first time period; and a closing input to the first interface is received.

[0197] In one possible implementation, the memory 109 is specifically used to: store the third event in a first database and delete the second event from the first database, the first database being used to store events in a conversation with the AI; store a third sparse vector and a third dense vector corresponding to the third event in a second database, and delete the second sparse vector and the second dense vector corresponding to the second event from the second database, the third sparse vector and the third dense vector being generated based on event elements corresponding to the third event, the second database being used to store sparse vectors and dense vectors corresponding to events in a conversation with the AI.

[0198] The embodiment of the present application provides an electronic device, in the case where there is a second event in the events in the historical conversation with AI whose similarity with the first event is greater than or equal to a first threshold, that is, in the case where there is already an event identical to the first event in the historical conversation, the electronic device can perform fusion processing on the two events to obtain a third event, and then store the third event and delete the second event, so that the electronic device can fuse the repeated events into a new event, so that the new event can preserve the different contents of the two repeated events while characterizing the repeated event, thereby maintaining the integrity of the event content, and while storing the event, delete the existing event, thereby eliminating the need to store multiple repeated events and avoiding a large amount of repeated content. In this way, in the scenario where the user describes the same event multiple times, the redundancy of historical record storage can be reduced while ensuring the integrity of the event content.

[0199] The electronic device provided in the embodiment of the present application can implement each process implemented in the above method embodiment, and can achieve the same technical effect. To avoid repetition, it is not repeated here. The beneficial effects of various implementations in this embodiment can be specifically referred to the beneficial effects of the corresponding implementations in the above method embodiment. To avoid repetition, it is not repeated here.

[0200] It should be understood that in the embodiment of the present application, the input unit 104 may include a graphics processor (Graphics Processing Unit, GPU) 1041 and a microphone 1042, and the graphics processor 1041 processes the image data of a static picture or video obtained by an image capture device (such as a camera) in a video capture mode or an image capture mode. The display unit 106 may include a display panel 1061, and the display panel 1061 may be configured in the form of a liquid crystal display, an organic light emitting diode, etc. The user input unit 107 includes a touch panel 1071 and at least one of other input devices 1072. The touch panel 1071 is also called a touch screen. The touch panel 1071 may include two parts: a touch detection device and a touch controller. Other input devices 1072 may include, but are not limited to, a physical keyboard, function keys (such as volume control keys, switch keys, etc.), a trackball, a mouse, and a joystick, which will not be repeated here.

[0201] The memory 109 can be used to store software programs and various data. The memory 109 may mainly include a first storage area for storing programs or instructions and a second storage area for storing data, wherein the first storage area may store an operating system, an application program or instructions required for at least one function (such as a sound playback function, an image playback function, etc.), etc. In addition, the memory 109 may include a volatile memory or a non-volatile memory, or the memory 109 may include both volatile and non-volatile memories. Among them, the non-volatile memory may be a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), or a flash memory. The volatile memory may be a random access memory (RAM), a static random access memory (SRAM), a dynamic random access memory (DRAM), a synchronous dynamic random access memory (SDRAM), a double data rate synchronous dynamic random access memory (DDRSDRAM), an enhanced synchronous dynamic random access memory (ESDRAM), a synchronous link dynamic random access memory (SLDRAM) and a direct memory bus random access memory (DRRAM). The memory 109 in the embodiment of the present application includes but is not limited to these and any other suitable types of memory.

[0202] The processor 110 may include one or more processing units; optionally, the processor 110 integrates an application processor and a modem processor, wherein the application processor mainly processes operations related to an operating system, a user interface, and application programs, and the modem processor mainly processes wireless communication signals, such as a baseband processor. It is understandable that the modem processor may not be integrated into the processor 110.

[0203] An embodiment of the present application also provides a readable storage medium, on which a program or instruction is stored. When the program or instruction is executed by a processor, the various processes of the above-mentioned event processing method embodiment are implemented, and the same technical effect can be achieved. To avoid repetition, it will not be repeated here.

[0204] The processor is the processor in the electronic device described in the above embodiment. The readable storage medium includes a computer readable storage medium, such as a computer read-only memory ROM, a random access memory RAM, a magnetic disk or an optical disk.

[0205] An embodiment of the present application further provides a chip, which includes a processor and a communication interface, wherein the communication interface is coupled to the processor, and the processor is used to run programs or instructions to implement the various processes of the above-mentioned event processing method embodiment, and can achieve the same technical effect. To avoid repetition, it will not be repeated here.

[0206] It should be understood that the chip mentioned in the embodiments of the present application can also be called a system-level chip, a system chip, a chip system or a system-on-chip chip, etc.

[0207] An embodiment of the present application provides a computer program product, which is stored in a storage medium. The program product is executed by at least one processor to implement the various processes of the above-mentioned event processing method embodiment and can achieve the same technical effect. To avoid repetition, it will not be repeated here.

[0208] It should be noted that, in this article, the terms "comprise", "include" or any other variant thereof are intended to cover non-exclusive inclusion, so that the process, method, article or device including a series of elements includes not only those elements, but also includes other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise one..." do not exclude the presence of other identical elements in the process, method, article or device including the element. In addition, it should be pointed out that the scope of the methods and devices in the embodiments of the present application is not limited to performing functions in the order shown or discussed, and may also include performing functions in a substantially simultaneous manner or in reverse order according to the functions involved, for example, the described method may be performed in an order different from that described, and various steps may also be added, omitted, or combined. In addition, the features described with reference to certain examples may be combined in other examples.

[0209] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present application, or the part that contributes to the prior art, can be embodied in the form of a computer software product, which is stored in a storage medium (such as ROM / RAM, a disk, or an optical disk), and includes a number of instructions for a terminal (which can be a mobile phone, a computer, a server, or a network device, etc.) to execute the methods described in each embodiment of the present application.

[0210] The embodiments of the present application are described above in conjunction with the accompanying drawings, but the present application is not limited to the above-mentioned specific implementation methods. The above-mentioned specific implementation methods are merely illustrative and not restrictive. Under the guidance of the present application, ordinary technicians in this field can also make many forms without departing from the purpose of the present application and the scope of protection of the claims, all of which are within the protection of the present application.

Claims

1. An event processing method, characterized in that: include: Acquire dialogue information in a first interface, and determine a first event from the dialogue information, wherein the first interface is a dialogue interface with artificial intelligence AI; In the case where there is a second event in at least one event, performing fusion processing on the first event and the second event to obtain a third event, wherein the at least one event is an event in the historical dialogue with the AI, and the second event is an event whose similarity with the first event is greater than or equal to a first threshold; The third event is stored and the second event is deleted.

2. The method according to claim 1, characterized in that The performing fusion processing on the first event and the second event to obtain a third event includes: Acquire at least one first event element of the first event and at least one second event element of the second event; If a first event element and a second event element are the same, performing a deletion process on the first event element or the second event element, and determining the at least one first event element and the at least one second event element after the deletion process as a third event element; The third event is determined according to the third event element.

3. The method according to claim 1 or 2, characterized in that: Before performing fusion processing on the first event and the second event to obtain a third event, the method further includes: Acquire first event information corresponding to the first event, the first event information including event time information, time and location information, a first sparse vector and a first dense vector, wherein the first sparse vector and the first dense vector are both used to represent the first event; Determine at least one second event information from the event information of the at least one event, wherein the similarity between each second event information and one of the first event information is greater than or equal to a second threshold; The at least one second event information is arranged in order of similarity with the information in the first event information, and events corresponding to the first N second event information in the at least one second event information are determined as the second events, where N is a positive integer.

4. The method according to claim 1, characterized in that: The obtaining of the conversation information in the first interface includes: When the first condition is met, obtaining the dialog information in the first interface; The first condition includes at least one of the following: No input to the first interface is received within a first time period; A closing input for the first interface is received.

5. The method according to claim 1, characterized in that The storing the third event and deleting the second event includes: storing the third event in a first database and deleting the second event from the first database, the first database being used to store events in a conversation with the AI; The third sparse vector and the third dense vector corresponding to the third event are stored in a second database, and the second sparse vector and the second dense vector corresponding to the second event are deleted from the second database, the third sparse vector and the third dense vector are generated according to the event elements corresponding to the third event, and the second database is used to store sparse vectors and dense vectors corresponding to events in the conversation with the AI.

6. An event processing device, characterized in that: include: Acquisition module, execution module and processing module; The acquisition module is used to acquire dialogue information in a first interface and determine a first event from the dialogue information, wherein the first interface is a dialogue interface with artificial intelligence AI; The execution module is configured to perform fusion processing on the first event and the second event determined by the acquisition module to obtain a third event when there is a second event in at least one event, wherein the at least one event is an event in a historical conversation with the AI, and the second event is an event whose similarity with the first event is greater than or equal to a first threshold; The processing module is used to store the third event obtained by the execution module and delete the second event.

7. The device according to claim 6, characterized in that The execution module is specifically used to obtain at least one first event element of the first event and at least one second event element of the second event determined by the acquisition module; and if a first event element and a second event element are the same, perform deletion processing on the first event element or the second event element, and determine the at least one first event element and the at least one second event element after the deletion processing as the third event element; And according to the third event element, the third event is determined.

8. The device according to claim 6 or 7, characterized in that The device further comprises: a determination module; The acquisition module is further used to acquire first event information corresponding to the first event before the execution module performs fusion processing on the first event and the second event to obtain a third event, wherein the first event information includes event time information, time and location information, a first sparse vector and a first dense vector, and both the first sparse vector and the first dense vector are used to represent the first event; The determining module is used to determine at least one second event information from the event information of the at least one event acquired by the acquiring module, wherein the similarity between each second event information and one of the first event information is greater than or equal to a second threshold; The determination module is further used to arrange the at least one second event information in order of similarity with the information in the first event information, and determine the events corresponding to the first N second event information in the at least one second event information as the second event, where N is a positive integer.

9. The device according to claim 6, characterized in that The acquisition module is specifically used for: When the first condition is met, obtaining the dialog information in the first interface; The first condition includes at least one of the following: No input to the first interface is received within a first time period; A closing input for the first interface is received.

10. The device according to claim 6, characterized in that The processing module is specifically used for: storing the third event processed by the execution module in a first database, and deleting the second event from the first database, where the first database is used to store events in a dialogue with the AI; The third sparse vector and the third dense vector corresponding to the third event are stored in a second database, and the second sparse vector and the second dense vector corresponding to the second event are deleted from the second database, the third sparse vector and the third dense vector are generated according to the event elements corresponding to the third event, and the second database is used to store sparse vectors and dense vectors corresponding to events in the conversation with the AI.

Images