Information recommendation method and device, electronic equipment and storage medium

Abstract

The invention discloses an information recommendation method and device, electronic equipment and a storage medium, and belongs to the technical field of electronic equipment. The method comprises the following steps: acquiring a travel destination; displaying travel recommendation information according to the AI memory information corresponding to the travel destination; the AI memory information is personalized information, recorded through an AI function, of the user for the travel destination.

Description

Technical Field

[0001] The present application belongs to the technical field of electronic equipment, and specifically relates to an information recommendation method, device, electronic equipment and storage medium. Background Art

[0002] At present, with the development of electronic devices, electronic devices are becoming more and more intelligent. For example, electronic devices can recommend itineraries for users. However, the itinerary recommendations are often generated based on travel guides on the Internet, which are stereotyped, resulting in inflexible itinerary recommendations of electronic devices. Summary of the invention

[0003] The purpose of the embodiments of the present application is to provide an information recommendation method, device, electronic device and storage medium, which can improve the flexibility of itinerary recommendations of electronic devices.

[0004] In a first aspect, an embodiment of the present application provides an information recommendation method, which includes: obtaining task information; obtaining a travel destination; displaying travel recommendation information based on artificial intelligence (AI) memory information corresponding to the travel destination; the AI ​​memory information is the user's personalized information about the travel destination recorded by the AI ​​function.

[0005] In a second aspect, an embodiment of the present application provides an information recommendation device, which includes: an acquisition module and a display module. The acquisition module is used to acquire a travel destination. The display module is used to display travel recommendation information according to AI memory information corresponding to the travel destination acquired by the acquisition module; the AI ​​memory information is the user's personalized information about the travel destination recorded by the AI ​​function.

[0006] 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.

[0007] 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.

[0008] 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.

[0009] In a sixth aspect, an embodiment of the present application provides a computer program product, which is stored in a storage medium and executed by at least one processor to implement the method described in the first aspect.

[0010] In an embodiment of the present application, travel recommendation information is displayed based on the AI ​​memory information corresponding to the travel destination. Since the AI ​​memory information is the user's personalized information about the travel destination recorded by the AI ​​function, such as the places the user wanted to go to but did not have time to go to at the travel destination last time, the travel recommendation information is richer and more in line with the user's needs, thereby improving the flexibility of the electronic device's itinerary recommendations. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] Figure 1 This is one of the flow charts of an information recommendation method provided in an embodiment of the present application;

[0012] Figure 2 This is the second flowchart of an information recommendation method provided in an embodiment of the present application;

[0013] Figure 3A It is a schematic diagram of an interface displaying a travel recommendation information identifier provided in an embodiment of the present application;

[0014] Figure 3B is a schematic diagram of an interface for displaying travel recommendation information provided by an embodiment of the present application;

[0015] Figure 4A is a schematic diagram of an interface for selecting travel recommendation information provided in an embodiment of the present application;

[0016] Figure 4B is a schematic diagram of an interface for displaying scenic spot information provided by an embodiment of the present application;

[0017] Figure 5 is a schematic diagram of an interface for displaying predetermined information provided by an embodiment of the present application;

[0018] Figure 6 This is one of the flow charts of another information recommendation method provided in an embodiment of the present application;

[0019] Figure 7 This is one of the structural schematic diagrams of an information recommendation device provided in an embodiment of the present application;

[0020] Figure 8 This is a second structural diagram of an information recommendation device provided in an embodiment of the present application;

[0021] Fig. 9 This is one of the hardware structure diagrams of an electronic device provided in an embodiment of the present application;

[0022] Fig.10 This is the second schematic diagram of the hardware structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0023] 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.

[0024] 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 terms used in this way are interchangeable where appropriate, so that the embodiments of the present application can be implemented in an order other than those illustrated or described herein, 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.

[0025] The terms "at least one (item)", "at least one of" and the like in the specification and claims of the present 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)".

[0026] The information recommendation method, device, electronic device and storage medium provided by the embodiments of the present application are described in detail below with reference to the accompanying drawings through specific embodiments and their application scenarios.

[0027] The information recommendation method, device, electronic device and storage medium provided in the embodiments of the present application can be applied to travel planning scenarios based on travel destinations input by users, such as travel planning scenarios for tourism and city sightseeing.

[0028] For the above-mentioned travel planning scenario, the user can enter "I want to travel to City A" in the travel planning interface of the electronic device. Then, the electronic device can obtain the items that the user did not do when he went to City A last time from the historical AI memory information corresponding to the travel to City A, for example, restaurants that the user did not check in at in City A last time, and attractions that the user did not visit in City A last time; and then make itinerary recommendations to the user based on restaurants that the user did not check in at in City A last time and attractions that the user did not visit in City A last time.

[0029] For the above-mentioned city sightseeing travel planning scenario, the user can enter "I am now in city B for city sightseeing" in the travel planning interface of the electronic device, and then the electronic device can obtain the items that the user did not undertake during the last city sightseeing in city B from the historical AI memory information corresponding to the city sightseeing in city B, such as the attractions that the user did not ride last time in city B, and the snacks that the user did not eat last time in city B; and then make itinerary recommendations to the user based on the attractions that the user did not ride last time in city B and the snacks that the user did not eat last time in city B.

[0030] It should be noted that the above scenarios are merely illustrative examples of some scenarios in which the embodiments of the present application may be applied. In actual implementation, the embodiments of the present application can also be applied to any possible scenarios such as more reservation and subscription types, and the embodiments of the present application are not limited here.

[0031] Based on the above scenario, in an embodiment of the present application, travel recommendation information is displayed according to the AI ​​memory information corresponding to the travel destination. Since the AI ​​memory information is the user's personalized information about the travel destination recorded by the AI ​​function, such as the places the user wanted to go to but did not have time to go to at the travel destination last time, the travel recommendation information is richer and more in line with the user's needs, thereby improving the flexibility of the electronic device's itinerary recommendations.

[0032] The information recommendation method provided in the embodiment of the present application may be executed by an information recommendation device, which may be an electronic device or a functional module in an electronic device. The technical solution provided in the embodiment of the present application is described below using an electronic device as an example.

[0033] The present application embodiment provides an information recommendation method. Figure 1 FIG. 1 is a flowchart of an information recommendation method provided by an embodiment of the present application. Figure 1 As shown, the itinerary planning method provided in the embodiment of the present application may include the following steps 201 and 202.

[0034] Step 201: The electronic device obtains a travel destination.

[0035] Optionally, in an embodiment of the present application, the user can input the above travel destination in the travel planning interface so that the electronic device can obtain the travel destination.

[0036] Exemplarily, the travel planning interface may include an input box, in which a user may input a travel destination, so that the electronic device may acquire the travel destination.

[0037] Optionally, in an embodiment of the present application, the above-mentioned input box may be a text input box or a voice input box.

[0038] Optionally, in an embodiment of the present application, when the above-mentioned input box is a voice input box, when the electronic device collects a voice signal output by the user, the electronic device can obtain the text corresponding to the voice signal through a first algorithm, thereby obtaining the above-mentioned travel destination.

[0039] Optionally, in an embodiment of the present application, the first algorithm may be any one of the following: an AI algorithm, a neural network algorithm or an automatic speech recognition (ASR) algorithm.

[0040] Exemplarily, after collecting the user's voice signal, the electronic device can input the voice signal into an ASR algorithm. The ASR algorithm splits the voice signal input by the user according to audio frames, and converts the split audio frames into multi-dimensional vector information according to the characteristics of the human ear. The multi-dimensional vector information is then combined to form phonemes, and finally the phonemes are combined into words and strung together into sentences to obtain the above-mentioned travel destination.

[0041] Optionally, in the embodiment of the present application, the above step 201 can be specifically implemented by any one of the following steps 201a to 201d.

[0042] Step 201a: The electronic device obtains the travel destination through the conversation message.

[0043] In the embodiment of the present application, the above-mentioned session message may be a message in the session interface.

[0044] Optionally, in an embodiment of the present application, the above-mentioned conversation interface may be a conversation interface in a chat application or a conversation interface in a text message application.

[0045] Optionally, in an embodiment of the present application, the above-mentioned session interface may be a group chat session interface; or, the above-mentioned session interface may be a private chat session interface.

[0046] Optionally, in an embodiment of the present application, the above-mentioned conversation interface may include multiple conversation messages.

[0047] In an embodiment of the present application, the electronic device can perform semantic recognition on the conversation message to obtain the above-mentioned travel destination.

[0048] Exemplarily, the electronic device may input the conversation message into the first model to perform semantic recognition on the conversation message through the first model to obtain the above-mentioned travel destination.

[0049] Optionally, in an embodiment of the present application, the above-mentioned first model can be any one of the following: a generative pre-training (GPT) model, a bidirectional encoder representation from transformers (BRET) model or an artificial intelligence (AI) model.

[0050] Exemplarily, the electronic device can input the above-mentioned conversation message into the above-mentioned GPT model, and the GPT model can segment the conversation message to obtain a word set; then convert the word set into a word vector set, and obtain the word position vector set of all word vectors in the word vector set; and obtain the adjacent word sequence of all words in the word set, encode the adjacent word sequence, and generate an adjacent word vector set; merge the word vector set, the word position vector set and the adjacent word vector set to obtain the target word vector set; use the text feature semantic extraction module in the GPT model to encode and decode the target word vector set to obtain a text feature vector sequence, and finally generate the text semantics corresponding to the conversation message, that is, the above-mentioned travel destination.

[0051] Step 201b: The electronic device obtains the travel destination via email.

[0052] In an embodiment of the present application, the electronic device can perform keyword extraction processing on the text contained in the email to obtain the above-mentioned travel destination.

[0053] Exemplarily, the electronic device may perform keyword extraction processing on the text contained in the email by using preset keyword types to obtain the above travel destination from the text contained in the email.

[0054] Step 201c: The electronic device obtains the travel destination through the schedule information.

[0055] Optionally, in an embodiment of the present application, the electronic device can obtain the travel destination through schedule information in a calendar application.

[0056] For example, the user can add schedule information in the calendar application, that is, travel to city D on day C of month B of year A.

[0057] Step 201d: The electronic device obtains the travel destination through the input information of the AI ​​interactive interface.

[0058] Optionally, in an embodiment of the present application, the above-mentioned AI interaction interface may be an interaction interface corresponding to an AI assistant in an electronic device.

[0059] Optionally, in an embodiment of the present application, the above-mentioned input information may be voice input information or text input information.

[0060] Exemplarily, the user can long press the voice assistant and then output voice so that the electronic device can obtain the user's voice signal, obtain the travel destination based on the user's voice signal, and display the text corresponding to the voice signal in the AI ​​interaction interface.

[0061] Optionally, in the embodiment of the present application, the above input information may be context information.

[0062] Exemplarily, the user enters "I want to travel" in the AI ​​interaction interface; the voice assistant enters "where do you want to go for fun" in the AI ​​interaction interface; the user enters "I want to go to City A for fun" in the private chat interface. In this way, the electronic device can combine the information "I want to travel", "where do you want to go for fun" and "I want to go to City A for fun" to obtain the above travel destinations.

[0063] In the embodiment of the present application, the electronic device can obtain the user's travel destination from multiple dimensions, thereby improving the flexibility of the electronic device in obtaining the travel destination.

[0064] Step 202: The electronic device displays travel recommendation information based on the AI ​​memory information corresponding to the travel destination.

[0065] Among them, AI memory information is the user's personalized information about travel destinations recorded through the AI ​​function.

[0066] Optionally, in an embodiment of the present application, the AI ​​memory information corresponding to the above travel destination is determined based on at least one of the following: conversation messages, user information in the first application that matches the travel destination, schedule information, note information, and memo information. The first application may be a travel-related application, such as a travel service application, a local life service application, a transportation ticket booking application, a hotel reservation application, etc. The user information may be the user's usage information for the first application. For example, if the first application is a restaurant evaluation application, the user information may be the user's order information, the user's queue number information, the user's collection information, the user's browsing information, etc.

[0067] For example, the electronic device can form the user's personalized information about place A based on the conversation message sent by the user, "If you go to place A later, you must try restaurant A." For another example, the user went to place B, but due to time constraints, failed to go to restaurant B. The electronic device can form the user's personalized information about place B based on the conversation message sent by the user, "What a pity, I don't have time to check in at restaurant B." It can also determine whether "restaurant B" needs to be added to the user's personalized information about place B based on the user's queue number information in the first application and the user's geographical location in place B.

[0068] User information is optional, in the embodiment of the present application, combined with Figure 1 ,like Figure 2 As shown, the above step 202 can be specifically implemented through the following step 202a.

[0069] Step 202a: The electronic device displays travel recommendation information based on the AI ​​memory information corresponding to the travel destination, the travel-related information corresponding to the travel destination, and the historical travel information.

[0070] It can be understood that the above historical travel information can be obtained by the electronic device through the historical travel records of various travel-related applications.

[0071] Optionally, in the embodiment of the present application, the above travel related information may include: travel time, travel budget, travel points of interest, etc. The specific information may be determined according to actual usage, and the embodiment of the present application does not limit it.

[0072] Optionally, in the embodiment of the present application, the above historical travel information may include: historical travel accommodation information, historical travel transportation information, historical travel dining information, etc. The specific information may be determined according to actual usage, and the embodiment of the present application does not limit it.

[0073] It can be understood that the electronic device can know the user's travel habits, such as transportation habits, accommodation habits, dining habits, etc. by obtaining the above-mentioned historical travel arrangement information.

[0074] Optionally, in an embodiment of the present application, the above-mentioned travel recommendation information includes at least one of the following: travel transportation information, travel accommodation information, travel entertainment information, travel dining information, and travel social information.

[0075] It can be understood that the above travel social information can be used by the electronic device to plan meetings between the user and other users; for example, which restaurant to eat at, what gifts to buy for the social object, etc.

[0076] In the embodiments of the present application, the electronic device can know the user's personalized needs for the travel destination through AI memory information, know the time, budget, etc. of the user's travel through travel-related information corresponding to the travel destination, and know the user's travel habits through historical travel information. Based on the above information, the electronic device can recommend travel plans to the user, thereby realizing personalized plan customization for the user.

[0077] For example, Figure 3A As shown, taking the electronic device as a mobile phone as an example, after the mobile phone obtains the travel destination, the mobile phone can display a travel recommendation information icon 11 in the travel recommendation interface 10. Figure 3A The 11-day A city 3-day 2-night travel guide is shown; the user can click on the travel recommendation information icon to enter, such as Figure 3B As shown, the mobile phone can display travel recommendation information in the travel recommendation interface 10, and the travel recommendation information includes a travel route 12, the itinerary for the first day, such as D1: arrive in city A - free activities - go to homestay A; the itinerary for the second day, such as D2: homestay A - scenic spot A - activity A - project A - return to homestay A; the itinerary for the third day, such as D3: homestay A - scenic spot B - activity B - arrive in city B and route 12.

[0078] Optionally, in an embodiment of the present application, the user may input recommended information in the travel recommendation information so that the electronic device may display detailed information of the recommended information.

[0079] For example, in combination Figure 3B ,like Figure 4A As shown, the user can click and input the logo of scenic spot A, such as Figure 4B The electronic device can display the introduction of the scenic spot corresponding to the A scenic spot. For example, the A scenic spot is located on the A mountain in the A city of the A province. It is a 5A tourist attraction and is known as "the first building in the world" and "the most beautiful scenery in the world". The A scenic spot is a landmark building in the A city. It is also known as the three major scenic spots in the A city together with the B Pavilion and the C platform. A group of auxiliary buildings such as the bronze yellow crane sculpture, the Shengxiang pagoda, the memorial archway, the corridor, the pavilion, etc. outside the A scenic spot building set off the main building more magnificently. There are also buildings such as the D Pavilion, the E Tower, the stele corridor, and the mountain gate around the main building. The entire building has a unique ethnic style.

[0080] In the information recommendation method provided in the embodiment of the present application, travel recommendation information is displayed based on the AI ​​memory information corresponding to the travel destination. Since the AI ​​memory information is the user's personalized information about the travel destination recorded by the AI ​​function, such as the places the user wanted to go to but did not have time to go to at the travel destination last time, the travel recommendation information is richer and more in line with the user's needs, thereby improving the flexibility of the electronic device's itinerary recommendations.

[0081] Optionally, in the embodiment of the present application, the above step 202 can be specifically implemented by the following step 202b, and the information recommendation method provided in the embodiment of the present application also includes the following steps 301 and 302.

[0082] Step 202b: The electronic device displays travel recommendation information on the travel recommendation interface based on the AI ​​memory information corresponding to the travel destination.

[0083] Optionally, in the embodiment of the present application, the travel recommendation interface may be the AI ​​interactive interface; or, the travel recommendation interface may be an interface in a travel planning application; or, the travel recommendation interface may be a desktop. The specific interface may be determined according to actual usage requirements, and the embodiment of the present application does not limit it.

[0084] Step 301: The electronic device receives a first input to a first control in a travel recommendation interface.

[0085] In the embodiment of the present application, the above-mentioned first input is used to select the first control from the travel recommendation interface.

[0086] Optionally, in the embodiment of the present application, the first input may be a click input, a long press input, a preset track input, etc. of the first control by the user. The specific input may be determined according to actual use requirements, and the embodiment of the present application does not limit the input.

[0087] The first control may be an AI control, through which at least one of the following may be performed through the AI ​​function: booking transportation, booking a hotel, booking tickets, booking a restaurant, and sending a conversation message to a communication partner. It may also be an AI transportation booking control, an AI hotel booking control, an AI ticket booking control, an AI restaurant booking control, an AI conversation control, etc., and the AI ​​conversation control may send a conversation message to a communication partner through the AI ​​function.

[0088] Step 302: In response to the first input, the electronic device executes at least one of the following through the AI ​​function: booking transportation, booking a hotel, booking tickets, booking a restaurant, and sending a conversation message to a communication partner.

[0089] In an embodiment of the present application, the electronic device can book transportation through the transportation methods in the above travel recommendation information; book a hotel through the hotels in the above travel recommendation information; book tickets for attractions through the attractions in the above travel recommendation information; book a restaurant through the restaurants in the above travel recommendation information; and send a conversation message to the communication object through the communication object in the above travel recommendation information.

[0090] For example, Figure 5As shown, the mobile phone can display the high-speed rail ticket information 13 from City B to City A, the room information 14 and hotel information 15 of Hotel A, and the first control 16 in the travel recommendation interface 10. The user can click and input the first control 16 so that the mobile phone can use the AI ​​function to automatically book the high-speed rail ticket from City B to City A, the room and hotel of Hotel A.

[0091] In the embodiment of the present application, the electronic device can directly make a reservation based on the user's input and the information in the travel recommendation information, saving the user's time.

[0092] Optionally, in the embodiment of the present application, the information recommendation method provided in the embodiment of the present application further includes the following steps 401 and 402.

[0093] Step 401: The electronic device receives a second input to a second control in a travel recommendation interface.

[0094] In the embodiment of the present application, the second input is used to select a second control from the travel recommendation interface.

[0095] Optionally, in the embodiment of the present application, the second input may be a click input, a long press input, a preset track input, etc. of the second control by the user. The specific input may be determined according to actual use requirements, and the embodiment of the present application does not limit the input.

[0096] In the embodiment of the present application, the second control is used to edit travel recommendation information.

[0097] Step 402: The electronic device updates travel recommendation information corresponding to the second control in response to the second input.

[0098] In an embodiment of the present application, the electronic device may receive a second input from a user on any recommended information in the travel recommendation information, so that the electronic device may edit the any recommended information.

[0099] For example, in combination Figure 4A The user can long press the itinerary identifier for the next day to make the electronic device delete the itinerary for the next day, and the electronic device can obtain new travel recommendation information based on the deleted itinerary.

[0100] As another example, the user can slide to input the travel recommendation information so that the electronic device can display an input box, and the user can enter new travel arrangement information in the input box so that the electronic device can add the new travel arrangement information to the travel recommendation information to obtain new travel recommendation information.

[0101] In an embodiment of the present application, the electronic device can respond to user needs in real time, thereby ensuring that the latest and most relevant travel recommendations are provided based on user needs.

[0102] This embodiment of the application provides another information recommendation method. Figure 6 FIG. 2 is a flow chart of another information recommendation method provided by an embodiment of the present application. Figure 6 As shown, the itinerary planning method provided in the embodiment of the present application may include the following steps 501 to 503.

[0103] Step 501: The electronic device obtains task information.

[0104] In the embodiment of the present application, the above-mentioned task information may be task information of a type of task.

[0105] Optionally, in an embodiment of the present application, the above-mentioned type of task may be any one of the following: travel, purchase or appointment, etc.

[0106] Optionally, in an embodiment of the present application, the above-mentioned task information may include specific task information.

[0107] Exemplarily, the above-mentioned specific task information may include at least one of the following: travel time, travel location, points of interest, travel budget, user-collected travel information, purchased items, etc. The specific information may be determined according to actual use requirements, and the present application embodiment does not limit this.

[0108] Optionally, in an embodiment of the present application, the above-mentioned task information may include fuzzy task information.

[0109] Exemplarily, the above-mentioned ambiguous task information may be any of the following: “I want to travel”, “I want to buy a hat” or “I want to book a hotel”.

[0110] Optionally, in an embodiment of the present application, the electronic device may acquire task information when the first operation is detected.

[0111] In the embodiment of the present application, the above-mentioned first operation is used to trigger information recommendation.

[0112] Optionally, in the embodiment of the present application, the first operation may be a click operation, a long press operation, a sliding operation, etc. on the information recommendation control in the first interface. The specific operation may be determined according to actual use requirements, and the embodiment of the present application does not limit the operation.

[0113] Optionally, in an embodiment of the present application, the first interface may be a desktop or itinerary planning interface of an information recommendation application.

[0114] Optionally, in the embodiment of the present application, the above step 501 can be specifically implemented by the following step 501a.

[0115] Step 501a: The electronic device receives task information input by the user.

[0116] Optionally, in an embodiment of the present application, the user can input the information recommendation control in the above-mentioned first interface so that the electronic device can display a text input box; then, the user can enter the task information in the text input box.

[0117] Optionally, in an embodiment of the present application, a user can input the information recommendation control in the above-mentioned first interface so that the electronic device can display a voice input box; then, the user can long press the voice input box and output voice, so that the electronic device can collect the user's voice signal and convert the voice into text to obtain the above-mentioned task information.

[0118] Exemplarily, after collecting the user's voice signal, the electronic device can input the voice signal into an ASR algorithm. The ASR algorithm splits the user's input voice signal according to audio frames, and converts the split audio frames into multi-dimensional vector information according to human ear characteristics, and then combines the multi-dimensional vector information into phonemes. Finally, the phonemes are combined into words and strung together into sentences to obtain the above-mentioned task information.

[0119] In the embodiment of the present application, the electronic device can collect the user's voice signal through a microphone in the electronic device.

[0120] Optionally, in the embodiment of the present application, the microphone may be any one of the following: a condenser microphone, a piezoelectric microphone, a pressure difference microphone, etc. The specific type may be determined according to actual use requirements, and the embodiment of the present application does not limit this.

[0121] Optionally, in an embodiment of the present application, the user can directly input into the text input box or the voice input box displayed in the first interface, so that the electronic device can obtain the above-mentioned task information.

[0122] Optionally, in an embodiment of the present application, the user can directly wake up the voice assistant and input a sound signal so that the electronic device can obtain the above-mentioned task information according to the above-mentioned ASR algorithm.

[0123] In the embodiment of the present application, the electronic device can obtain the user's needs through the task information input by the user, and then the electronic device can recommend information based on the user's needs, thereby improving the accuracy of the electronic device's information recommendation.

[0124] Optionally, in the embodiment of the present application, the above step 501 can be specifically implemented by the following step 501b.

[0125] Step 501b: The electronic device performs semantic recognition on the first message in the conversation interface to obtain task information.

[0126] In an embodiment of the present application, the first message may include the task information.

[0127] Optionally, in an embodiment of the present application, the above-mentioned conversation interface may be a conversation interface in a chat application or a conversation interface in a text message application.

[0128] Optionally, in an embodiment of the present application, the above-mentioned session interface may be a group chat session interface; or, the above-mentioned session interface may be a private chat session interface.

[0129] Optionally, in an embodiment of the present application, the above-mentioned conversation interface may include multiple conversation messages.

[0130] Exemplarily, the first message may be one or more of the multiple session messages.

[0131] Preferably, the first message may be all the session messages among the multiple session messages.

[0132] Optionally, in the embodiment of the present application, the first message may further include a historical session message corresponding to the session interface.

[0133] Optionally, in an embodiment of the present application, the above-mentioned session interface can be multiple session interfaces in an instant messaging application; or, the above-mentioned session interface can be multiple session interfaces in multiple instant messaging applications, and one session interface in the multiple session interfaces corresponds to one application.

[0134] In one example, when the above-mentioned conversation interface is a plurality of conversation interfaces in an instant messaging application, the electronic device may display a plurality of interface identifiers corresponding to the plurality of conversation interfaces, with one interface identifier corresponding to one conversation interface; then, the user may click and input a first interface identifier among the plurality of interface identifiers, so that the electronic device may determine a message in the conversation interface corresponding to the first interface identifier as the above-mentioned first message.

[0135] In another example, when the above-mentioned conversation interface is multiple conversation interfaces in multiple instant messaging applications, the electronic device can display multiple interface identifiers corresponding to the multiple conversation interfaces, one interface identifier corresponding to one conversation interface; then, the user can click and input a second interface identifier among the multiple interface identifiers, so that the electronic device can determine the message in the conversation interface corresponding to the second interface identifier as the above-mentioned first message.

[0136] Optionally, in the embodiment of the present application, the above interface identification can be any of the following: an interface thumbnail, a text identification, a pattern identification or a symbol identification, etc. The specific information can be determined according to actual use requirements and is not limited in the present application.

[0137] In an embodiment of the present application, the electronic device may input the first message into the first model to perform semantic recognition on the first message through the first model, thereby obtaining the above-mentioned task information.

[0138] It should be noted that the introduction of the Transformer architecture has enabled breakthroughs in GPT model technology, the implementation of large-scale pre-training, and the continued expansion of model size. These technological innovations have enabled the GPT series of models to make significant progress in the field of natural language processing and have promoted the development of intelligent dialogue and personalized recommendations in various application scenarios.

[0139] One of the key advances in large models is the introduction of pre-training and transfer learning. GPT models have acquired rich language knowledge and contextual understanding capabilities by training on massive amounts of text data. These models can be fine-tuned on specific tasks and quickly adapt to different application scenarios. Transfer learning technology enables large models to demonstrate powerful language generation and understanding capabilities in multiple fields, thereby improving the effectiveness of personalized recommendation systems.

[0140] Optionally, in an embodiment of the present application, the electronic device may perform semantic recognition based on the context information in the first interface to obtain the above-mentioned task information.

[0141] It can be understood that the above-mentioned context information may include the above-mentioned first message.

[0142] In one example, take the first interface as a private chat interface and user 1 as the user of the electronic device; user 1 enters "I want to travel" in the private chat interface; user 2 enters "where do you want to go" in the private chat interface; user 1 says "I'll go somewhere warm first, preferably the beach" in the private chat interface. If the electronic device detects the first operation, the electronic device can perform semantic recognition on the message sent by user 1 and the message sent by user 2, and obtain the task information "user 1 wants to travel to a warm seaside".

[0143] In one example, take the above-mentioned first interface as a shopping interface, and user 1 as the user of the electronic device; user 1 inputs "I want to buy a hat" in the shopping interface; the shopping customer service inputs "What color and what kind of hat do you want to buy" in the shopping interface; user 1 inputs "I want to buy a black, casual hat" in the shopping interface. If the electronic device detects the first operation, the electronic device can perform semantic recognition on the message sent by the above-mentioned user 1 and the message sent by the shopping customer service, and obtain the task information "The user wants to buy a black casual hat".

[0144] In the embodiment of the present application, the electronic device can accurately understand the user's personalized needs and task scenarios by parsing the context information.

[0145] In an embodiment of the present application, the electronic device can perform semantic recognition on the first message through the first model, so that the electronic device can obtain more accurate user needs. Furthermore, the user demand information obtained by the electronic device through task information and historical information can be more accurate, thereby improving the accuracy of information recommendation by the electronic device.

[0146] Step 502: The electronic device determines task requirement information based on the task information and historical information.

[0147] In the embodiment of the present application, the above-mentioned historical information is historical information related to the task type corresponding to the task information.

[0148] In the embodiment of the present application, the above task requirement information can be used to characterize the user's intentions and personal preferences.

[0149] Exemplarily, the above historical information is historical information related to the task type corresponding to the task information, which can be understood as: when the above task type is a travel task type, the electronic device can obtain historical information matching the travel; when the above task type is a procurement task type, the electronic device can obtain historical information matching the procurement.

[0150] Optionally, in an embodiment of the present application, the above-mentioned historical information includes at least one of the following: task execution information, task location information, task search and browsing information, and user status information related to the task in the social application.

[0151] Optionally, in the embodiment of the present application, the above-mentioned task execution information may be task scheduling information.

[0152] Exemplarily, the above-mentioned task arrangement information may include at least one of the following: travel time point, travel time arrangement, travel transportation, travel route, scheduled meetings and scheduled business activities, etc.

[0153] It can be understood that the electronic device can obtain the above-mentioned task arrangement information to understand which travel destinations and activities the user is interested in.

[0154] Optionally, in an embodiment of the present application, the above-mentioned task search browsing information may be task information that has been browsed historically, task information that has been liked historically by the user, and task information that has been shared historically by the user.

[0155] It can be understood that the electronic device can determine the user's interests and hobbies and activity types through the above-mentioned task search and browsing information.

[0156] Optionally, in an embodiment of the present application, the user status information related to the task in the above-mentioned social application may be user emotion information related to the task in the social application, for example, emotional inclination towards a certain scenic spot.

[0157] It can be understood that the electronic device can determine the user's emotional inclination towards historical tasks through the above user status information.

[0158] Optionally, in the embodiment of the present application, the information recommendation method provided in the embodiment of the present application further includes the following step 601.

[0159] Step 601: The electronic device obtains historical information from at least one application.

[0160] In the embodiment of the present application, the at least one application mentioned above may be at least one application in an electronic device.

[0161] Optionally, in an embodiment of the present application, the electronic device can obtain the above-mentioned task scheduling information through a calendar application; obtain the above-mentioned task search and browsing information through a browser application or an information recommendation application; obtain the above-mentioned task location information through a global positioning system (GPS) or a geographic location service; and obtain user status information related to the tasks in the above-mentioned social applications through a social application.

[0162] Exemplarily, the electronic device may obtain at least one of the pictures or texts uploaded by the user in a social application, and by analyzing the content of the pictures or texts, it may be determined which scenic spots the user has a special emotional inclination towards.

[0163] It should be noted that the execution timing of the above step 601 may be after step 501 or before step 501. The specific timing may be determined according to actual usage, and the embodiment of the present application does not limit this.

[0164] In the embodiment of the present application, the electronic device obtains multiple historical information matching the task information from at least one application program, so that the electronic device can comprehensively obtain the user's personal preference for the task based on the historical information.

[0165] Optionally, in the embodiment of the present application, the above step 502 can be specifically implemented by the following steps 502a and 502b.

[0166] Step 502a: The electronic device performs content analysis on the task information and the history information to obtain a task keyword set.

[0167] Optionally, in an embodiment of the present application, the above-mentioned task keyword set may include at least two keywords.

[0168] In an embodiment of the present application, the electronic device can input the above-mentioned task information and historical information into the above-mentioned first model, and perform content analysis on the task information and historical information through the first model to obtain the first semantic text and the second semantic text corresponding to the task information, and then perform keyword extraction on the first semantic text and the second semantic text to obtain the above-mentioned task keyword set.

[0169] Optionally, in an embodiment of the present application, when the above-mentioned historical information includes text, the electronic device can perform semantic analysis on the text to obtain a first sub-semantic text; or, when the above-mentioned historical information includes an image, the electronic device can perform semantic extraction on the image to obtain a second sub-semantic text corresponding to the image.

[0170] In the embodiment of the present application, the first semantic text may be used to represent the user's intention; and the second semantic text may be used to represent the preference corresponding to the user's intention.

[0171] It should be noted that the specific process of obtaining the first semantic text and the first sub-semantic text can be found in the above embodiment, and will not be described again here to avoid repetition.

[0172] Exemplarily, in the case where the above-mentioned historical information includes an image, the electronic device can input the image into the first model, and the first model can perform convolution processing on the image to obtain high-dimensional feature information corresponding to the image, and then perform text conversion processing on the high-dimensional feature information to obtain the above-mentioned second sub-semantic text.

[0173] In an embodiment of the present application, after obtaining the first semantic text and the second semantic text, the electronic device can input the first semantic text and the second semantic text into the first algorithm in the first model, perform keyword extraction on the first semantic text and the second semantic text through the first algorithm, and obtain the task keyword set.

[0174] Optionally, in an embodiment of the present application, the above-mentioned first algorithm can be any one of the following: a term frequency-inverse document frequency (TF-IDF) algorithm, a text ranking TextRank algorithm, or a rapid automatic keyword extraction (RAKE) algorithm.

[0175] In one example, the above TF-IDF algorithm calculates the importance of each word in the first semantic text by the frequency of occurrence of each word in the first semantic text. Specifically, for the first semantic text, the TF-IDF algorithm can calculate the TF value of each word, where a TF value is the frequency of occurrence of a word in the first semantic text divided by the total number of words in the first semantic text, and calculate the IDF value of each word, where an IDF value is the logarithm of the reciprocal of the total number of words in the first semantic text; then the TF value of each word and the IDF value of each word are multiplied to obtain the TF-IDF value of each word, and finally, the TF-IDF value of each word can be sorted from high to low, and the words corresponding to the first 5 TF-IDF values ​​are determined as keywords.

[0176] It should be noted that the specific process of obtaining the keywords corresponding to the second semantic text through the above TF-IDF algorithm can be found in the above embodiment, and will not be repeated here to avoid repetition.

[0177] In another example, the above TextRank algorithm regards each word in the first semantic text as multiple nodes in a graph, constructs a graph through the co-occurrence relationship between each word, and then calculates the importance of each word according to the weight between each word to obtain keywords. Specifically, the TextRank algorithm iteratively calculates the weight of each word, uses the weight of each word as the score of the node in the graph, and then sorts each word from high to low according to its score, and determines the words corresponding to the top 5 scores as keywords.

[0178] It should be noted that the specific process of obtaining the keywords corresponding to the second semantic text through the above-mentioned TextRank algorithm can be found in the above-mentioned embodiment, and will not be described again here to avoid repetition.

[0179] In another example, the above RAKE algorithm obtains keywords by treating each word in the first semantic text as a candidate keyword, and then calculating each candidate keyword based on the co-occurrence relationship between each word and the position of each word in the first semantic text. Specifically, the RAKE algorithm splits the first semantic text into multiple words, and then constructs a weighted undirected graph based on the co-occurrence relationship between each word, and defines the score of each word as the sum of the co-occurrence frequency between two adjacent words and the position of each word in the first semantic text; finally, according to the score of each word, it is sorted from high to low, and the words corresponding to the top 5 scores are determined as keywords.

[0180] It should be noted that the specific process of obtaining the keywords corresponding to the second semantic text through the above RAKE algorithm can be found in the above embodiment, and will not be described again here to avoid repetition.

[0181] The above step 502a is described in detail below.

[0182] Example 1: The user can enter "I want to travel" in the text input box in the itinerary planning interface, so that the electronic device can input the text "I want to travel" into the GPT model, and the GPT model can perform semantic analysis on the text "I want to travel" to obtain the user's intention, that is, to travel; then, the electronic device can obtain the historical itinerary travel time and historical travel arrangements from the calendar application, obtain the user's frequently visited places, points of interest, and frequently visited places and the number of tourists from the historical travel records in the itinerary planning application, obtain the user's browsed travel websites, the user's searched travel information, and the user's clicked travel advertisements from the browsing history in the browser application, and obtain the user's browsing history in the travel application from the travel application. The electronic device can then input the above multiple historical itinerary information into the GPT model, and the GPT model can perform semantic recognition on the above multiple historical itinerary information to obtain the user's travel preferences, for example, liking warm places, liking self-driving, moderate distance, liking sunbathing on the beach, liking homestays, 4 people, children, and the elderly; finally, the GPT model can perform keyword extraction on the first semantic text and the second semantic text to obtain at least two keywords, for example, October 1, A year, City A, beach vacation, budget 10,000, warmth, self-driving, short distance, sunbathing on the beach, homestay, 4 people, children, the elderly, and 3 days.

[0183] Example 2: The user can input "I want to buy a hat" in the text input box in the shopping interface, so that the electronic device can input the above text input "I want to buy a hat" into the above GPT model, and the GPT model performs semantic analysis on the above text "I want to buy a hat" to obtain the user's intention, namely shopping, hat; then, the electronic device can obtain historical shopping prices, historical shopping stores and types of historical shopping items from the shopping application, for example, leisure, business, etc.; then the electronic device can input the above historical information into the GPT model, and the GPT model can perform semantic analysis on the above historical information to obtain the user's shopping preferences, for example, budget 100, leisure, store A.

[0184] Optionally, in an embodiment of the present application, before the electronic device obtains historical information, it may display prompt information, where the prompt information is used to prompt the user that the electronic device is to obtain historical information.

[0185] Exemplarily, the electronic device can display the above prompt information on the desktop, and the prompt information can be "Historical information is being obtained, do you allow it? The historical information is used to provide you with personalized information recommendations." The prompt information can include an authorization consent control and a cancellation authorization control. The user can click the authorization consent control to allow the electronic device to obtain historical information.

[0186] Step 502b: The electronic device integrates the content of the task keywords in the task keyword set to obtain task requirement information.

[0187] In the embodiment of the present application, the electronic device can splice each task keyword in the task keyword set to obtain the above-mentioned task requirement information.

[0188] In one example, combined with the above example 1, the above task keyword set can be October 1st of A year, City A, beach vacation, budget of 10,000, warmth, self-driving, short distance, sunbathing on the beach, homestay, 4 people, children, elderly and 3 days; the electronic device can splice the above 13 keywords to obtain October 1st of A year, City A, beach vacation, budget of 10,000, warmth, self-driving, short distance, sunbathing on the beach, homestay, 4 people, children and elderly; that is, the above travel demand information.

[0189] In another example, combined with the above Example 2, the above task keyword set can be shopping, hat, budget 100, leisure, A store; the electronic device can splice the above 5 keywords to obtain shopping, hat, budget 100, leisure and A store; that is, the above travel demand information.

[0190] Optionally, in an embodiment of the present application, after obtaining the above-mentioned travel demand information, the electronic device may store the above-mentioned travel demand information in the electronic device. In this way, the next time the electronic device receives task information of the same task type input by the user, the electronic device can directly recommend information based on the stored travel demand information, thereby improving the efficiency of the electronic device in recommending information.

[0191] In the embodiment of the present application, the electronic device can perform content analysis on the task information and historical information through the first model, so as to deeply understand the user's intention and the personalized needs corresponding to the intention, and then generate accurate information recommendations based on the user's personalized needs.

[0192] Step 503: The electronic device generates task recommendation information based on the task requirement information.

[0193] Optionally, in an embodiment of the present application, the above-mentioned task recommendation information is used to characterize a first task, and the first task includes any one of the following: a travel task, a procurement task, and an appointment task.

[0194] In an embodiment of the present application, the electronic device can input the above-mentioned task requirement information into the above-mentioned first model, and the first model generates personalized task recommendation information through a deep learning algorithm.

[0195] In the embodiment of the present application, taking the first task as a travel task as an example, the electronic device can support travel of different types.

[0196] For example, for business travelers, the electronic device can plan meeting arrangements, business activity recommendations, and optimal transportation plans based on the above task requirement information to improve work efficiency.

[0197] For family travel, electronic devices can plan family-friendly activities based on the above task requirement information, such as child-friendly attractions and family packages.

[0198] For extreme adventure travel, electronic devices can provide recommendations for extreme sports and adventure activities for adventurous users based on the above task requirement information, and generate personalized itineraries based on the user's interests and physical fitness data.

[0199] It should be noted that the above examples only list some scenarios in which the embodiments of the present application may be applied. In actual implementation, the embodiments of the present application can also be applied to any more possible scenarios such as skiing, going to school, mountain climbing, etc., and the embodiments of the present application are not limited here.

[0200] Optionally, in an embodiment of the present application, the electronic device may generate task recommendation information based on the multimodal data in combination with the above-mentioned task requirement information.

[0201] Exemplarily, the multimodal data may include at least one of the following: social media dynamics, such as travel posts, user health data, such as exercise data, conversation records of a voice assistant, and user emotions.

[0202] It can be understood that by combining the user's emotions with the above-mentioned task requirement information, recommendations that are more in line with the user's emotional state can be generated, such as recommending healing activities when the user is depressed.

[0203] In the information recommendation method provided in the embodiment of the present application, the electronic device can obtain task information; and based on the task information and historical information, determine the task requirement information, the historical information is the historical information related to the task type corresponding to the task information; and then generate the task recommendation information based on the task requirement information. In this scheme, since the electronic device can know the user's intention through the task information, and the user's preference information related to the task type can be known through the historical information, the task requirement information obtained by the electronic device in combination with the task information and the historical information can comprehensively characterize the user's needs and the preference information corresponding to the needs, so that the task recommendation information generated by the electronic device through the task requirement information can comprehensively characterize the user's personalized needs; that is, through the task requirement information, an information recommendation scheme that better matches the user's needs can be obtained, thereby improving the flexibility and accuracy of the electronic device in recommending information.

[0204] Optionally, in the embodiment of the present application, the above step 503 can be specifically implemented by the following steps 503a and 503b.

[0205] Step 503a: Based on the task requirement information, the electronic device determines task reference data matching the task requirement information from a database.

[0206] In the embodiment of the present application, the above-mentioned task reference data includes data of different dimensions related to the task type.

[0207] Optionally, in an embodiment of the present application, the above-mentioned database may be one or more databases. Each of the multiple databases may store a type of data. For example, one database may store weather type data, and another database may store scenic spot location type data.

[0208] Optionally, in an embodiment of the present application, the information in the above database can be obtained by integrating multiple data sources.

[0209] Optionally, in an embodiment of the present application, when the above-mentioned task information includes a task destination, the electronic device can integrate N information related to the task destination from multiple data sources based on the task destination, and store the N information in the data, where N is a positive integer.

[0210] Optionally, in the embodiment of the present application, the above-mentioned multiple data sources may include: a scenic spot database, a navigation application, a weather application, a travel application, etc. The specific data sources may be determined according to actual use requirements, and the embodiment of the present application does not limit them.

[0211] Optionally, in an embodiment of the present application, after determining N pieces of information, the electronic device may establish a comprehensive data model through the N pieces of information, and may subsequently use the comprehensive data model to integrate relevant information determined at other travel destinations to provide an accurate basis for recommendation.

[0212] In this way, the electronic device can integrate information from multiple data sources to provide an accurate recommendation basis, thereby improving the accuracy and practicality of information recommendations.

[0213] Optionally, in an embodiment of the present application, the above-mentioned task reference data may include at least one of the following: the travel destination, multiple attractions corresponding to the travel destination, location information corresponding to the multiple attractions, ticket information corresponding to the multiple attractions, evaluation information of the multiple attractions, traffic information of the multiple attractions, accommodation location information corresponding to the multiple attractions, prices of accommodation corresponding to the multiple attractions, and weather information corresponding to the travel destination.

[0214] In the embodiment of the present application, the electronic device can determine multiple information in the database whose matching degree with the travel demand information is greater than or equal to a preset threshold as the above-mentioned task reference data.

[0215] Exemplarily, the electronic device inputs the above travel demand information into the GPT model. The GPT model can calculate the matching value between each of the multiple information and each of the above travel demand information through multiple information stored in the database, thereby confirming the information whose matching value between the multiple information and each of the travel demand information is greater than or equal to 80% as the task reference data.

[0216] For example, taking the above travel demand information of "October 1st, A year, city A, beach vacation, budget 10,000, warmth, self-driving, short distance, sunbathing on the beach, homestay, 4 people, children, and the elderly" as an example, the electronic device can input October 1st, A year, beach vacation, budget 10,000, warmth, self-driving, short distance, sunbathing on the beach, homestay, 4 people, children, and the elderly into the GPT model, and the first model can calculate the matching value based on the city A, beach vacation, warmth, and budget 10,000 in the above travel preference information and each of the multiple attractions stored in the database, thereby determining the travel destinations with matching values ​​greater than or equal to 80% from the multiple attractions as K first attractions; Then, a matching value is calculated based on sunbathing on the beach and each of the K first attractions, so that the travel destinations with a matching value greater than or equal to 80% are determined as J second attractions from the K first attractions; finally, a matching value is calculated between the 4 persons, the homestay, the child, the elderly and each of the J second attractions and the homestay corresponding to each second attraction, and the attractions and homestays with a matching value greater than or equal to 80% are determined as the first attraction and the first homestay from the J second attractions and the homestays corresponding to the J second attractions; in this way, the above-mentioned task reference data is obtained, that is, the task reference data includes the travel destination, the attractions in the travel destination and the homestay near the attraction; wherein K and J are both positive integers.

[0217] Step 503b: The electronic device generates task recommendation information based on the task reference data.

[0218] Optionally, in an embodiment of the present application, the above-mentioned task recommendation information may include at least one of the following: task time arrangement, task time point, task traffic arrangement and task route planning, etc.; the specific information can be determined according to actual usage requirements and is not limited by the embodiment of the present application.

[0219] In one example, when the first task is a travel task, the task recommendation information includes at least one of the following: travel mode, travel route, daily schedule, routes between different attractions, homestay locations, visit time and restaurants for each attraction, etc. The specific information can be determined according to actual usage needs and is not limited in the embodiments of this application.

[0220] For example, when the first task is a purchase task, the task recommendation information includes at least one of the following: a purchase store, item style, item price, and item quality, etc. The specific information can be determined according to actual use requirements, and the present application embodiment does not limit this.

[0221] Optionally, in the embodiment of the present application, the above-mentioned task recommendation information may be one or more.

[0222] Optionally, in an embodiment of the present application, when there are multiple task recommendation information as mentioned above, the electronic device can display task identifiers of multiple task recommendation information, and the user can input a first task identifier among the multiple task identifiers, so that the electronic device can determine the task recommendation information corresponding to the first task identifier as the task recommendation information used by the user.

[0223] In the embodiment of the present application, the first task identifier may be any one of a plurality of task identifiers.

[0224] Optionally, in the embodiment of the present application, the task identifier may be any of the following: a text identifier, a thumbnail, a pattern identifier, or a special symbol identifier, which may be determined according to actual use requirements and is not limited in the embodiment of the present application.

[0225] Optionally, in an embodiment of the present application, the electronic device may display the task recommendation information in a task recommendation interface; or, the electronic device may display the task recommendation information on the desktop via a pop-up window.

[0226] Optionally, in an embodiment of the present application, a user can input task recommendation information so that the electronic device can display detailed information in the task recommendation information, such as travel routes, daily itinerary, routes between different attractions, homestay locations and visiting hours for each attraction.

[0227] Optionally, in an embodiment of the present application, the electronic device may display a translation control in the task recommendation interface, and the user may input into the translation control and select a corresponding language, so that the electronic device may fully translate the task recommendation information in the task recommendation interface according to the language selected by the user.

[0228] Optionally, in the embodiment of the present application, the user may input a second task identifier in the task recommendation information so that the electronic device may display information corresponding to the second task identifier.

[0229] Optionally, in an embodiment of the present application, the electronic device can generate a preliminary task arrangement through the above-mentioned task information. For example, the task arrangement includes attractions, activities, accommodation, etc.; and then adjust the above-mentioned preliminary itinerary according to the user's preference information, that is, the above-mentioned user demand information. For example, if the user has a limited budget, the system will give priority to recommending cost-effective attractions and activities, thereby obtaining task recommendation information that can meet the user's personalized needs.

[0230] Optionally, in an embodiment of the present application, the user can evaluate and provide feedback on the recommended task information during the use of the task recommendation information, so that the electronic device can record the user feedback data, and the user feedback data is used to update the model parameters in the first model, so that the first model can be further trained and optimized to improve the recommendation accuracy and user satisfaction of the first model.

[0231] Optionally, in an embodiment of the present application, the electronic device can integrate the itinerary planning information with a smart home system, such as a smart speaker or a home assistant, to provide a seamless user experience. For example, a user can inquire about upcoming itineraries through a smart speaker at home, or confirm the security settings at home before leaving home.

[0232] Optionally, in the embodiment of the present application, the electronic device can cooperate with a travel agency or an online travel platform to provide more abundant resources and services. For example, the electronic device can automatically generate a cooperative itinerary with a travel agency and make a reservation on the platform.

[0233] Optionally, in the embodiment of the present application, the electronic device can build an intelligent virtual travel assistant, which can interact with the user through natural language to provide instant itinerary suggestions, solutions to emergencies, etc. For example, when the user is planning a trip through the above itinerary, the user can ask the voice assistant "Where can I go for dinner now?" and get recommendations that meet the current location and budget.

[0234] Optionally, in an embodiment of the present application, the electronic device can support itinerary planning needs in multiple countries and regions around the world and provide localized recommended content.

[0235] Optionally, in an embodiment of the present application, when a user uses the above-mentioned itinerary planning information to travel, the electronic device can use augmented reality (AR) technology to display real-time navigation and attraction information on the electronic device or AR device to enhance the travel experience.

[0236] Optionally, in an embodiment of the present application, the electronic device can generate personalized travel content based on the itinerary planning information by introducing Generative Adversarial Nets (GANs). For example, a virtual attraction tour video or travel story is generated based on the itinerary planning information.

[0237] In the embodiment of the present application, since the task requirement information can comprehensively characterize the user's needs and obtain the preference information corresponding to the needs, the task recommendation information generated by the electronic device through the task requirement information can comprehensively characterize the user's personalized needs; that is, through the task requirement information, an information recommendation scheme that better matches the user's needs can be obtained, thereby improving the flexibility and accuracy of the electronic device in making information recommendations.

[0238] Optionally, in the embodiment of the present application, the information recommendation method provided in the embodiment of the present application further includes the following step 701.

[0239] Step 701: When first information changes, the electronic device adjusts task recommendation information based on the changed first information.

[0240] In an embodiment of the present application, the above-mentioned first information includes at least one of the following: task information, task completion progress information and task environment information.

[0241] In the embodiments of the present application, the electronic device can introduce a real-time learning mechanism, so that the electronic device can adjust the recommendation algorithm according to the user's real-time feedback, such as the instant evaluation of the recommended content, to quickly adapt to the user's changing needs, and use the large model's ability to understand the context to analyze the user's current situation, such as emergencies during travel, to make more detailed recommendation adjustments. For example, if the user temporarily decides to add a stop, the electronic device can calculate in real time the impact of the adjustment on the overall itinerary.

[0242] Optionally, in an embodiment of the present application, the change in the above-mentioned environmental information may be a change in the weather of the travel destination in the task recommendation information; or the change in the above-mentioned environmental information may be a congestion in the travel route in the task recommendation information.

[0243] In one example, when the first information is task environment information, if the weather of the travel destination in the task recommendation information changes from sunny to rainy, the electronic device can update the indoor activities in the task recommendation to indoor activities.

[0244] Example 3: In the case where the first information mentioned above is task environment information, and when the user is traveling according to the task recommendation information, if the electronic device detects that the weather at the travel destination changes from sunny, the electronic device can update the indoor activities in the task recommendation information to indoor activities.

[0245] Example 4: In the case where the first information mentioned above is task environment information, and before the user travels according to the task recommendation information, if the electronic device detects that the weather at the travel destination changes from sunny, the electronic device can update the indoor activities in the task recommendation information to indoor activities.

[0246] In another example, when the first information is route environment information, when the travel route in the itinerary planning information changes from unobstructed to congested, the electronic device may update the travel route in the itinerary planning information to another route, which is a unobstructed route.

[0247] Example 5: In the case where the first information is route environment information, and when the user is traveling according to the itinerary planning information, if the electronic device detects that the road has changed from being unobstructed to being congested, the electronic device can update the travel route in the itinerary planning information to another route.

[0248] Example 6: In the case where the first information is route environment information, and before the user travels according to the itinerary planning information, if the electronic device detects a change from unobstructed traffic to congested traffic, the electronic device can update the travel route in the itinerary planning information to another route.

[0249] Optionally, in an embodiment of the present application, the change in the above-mentioned task information may be a change in the task type or task purpose by the user. When the task information is changed, the electronic device may regenerate the task recommendation information through the first model.

[0250] It should be noted that the specific process of regenerating the itinerary planning information can be found in the above embodiment, and will not be described again here to avoid repetition.

[0251] In one example, when the first information is a travel destination and before the user travels according to the travel task recommendation information, if the electronic device detects that the user has updated the travel destination, the electronic device can re-execute the task recommendation operation according to the updated travel destination to obtain new task recommendation information.

[0252] In another example, when the first information is the travel destination and the user is traveling according to the itinerary planning information, if the electronic device detects that the user has updated the travel destination, the electronic device can re-execute the task recommendation operation according to the updated travel destination to obtain new task recommendation information.

[0253] In the embodiment of the present application, the above-mentioned task completion progress information is used to represent the progress of the user completing the execution of the task according to the task recommendation information.

[0254] For example, the task completion progress information may be that the user's visiting time at a certain scenic spot exceeds the planned visiting time in the itinerary when traveling according to the task recommendation information.

[0255] For example, if the electronic device detects that the user's visiting time at a certain attraction exceeds the planned visiting time during a trip according to the itinerary planning information, the electronic device may shorten the visiting time of subsequent attractions; or, the electronic device may delete the last attraction in the itinerary planning information.

[0256] For example, if the electronic device detects that the user directly skips a certain attraction during a trip according to the itinerary planning information, the electronic device can extend the visiting time of the subsequent attractions; or, the electronic device can add new attractions on its own.

[0257] It should be noted that before the electronic device adjusts the task recommendation information, the electronic device may display a prompt message, which is used to prompt the user that the current task has been adjusted and to execute the task after the adjustment.

[0258] It should be noted that the execution timing of the above step 701 may be before the above step 503 ; or, the execution timing of the above step 701 may be after the above step 503 .

[0259] In an embodiment of the present application, the electronic device can monitor and respond to changes in user needs and the external environment in real time, thereby ensuring that the latest and most relevant task recommendations are provided based on changes in user needs and the external environment.

[0260] The information recommendation method provided by the embodiment of the present application is specifically explained below by taking the beach vacation itinerary recommendation as an example. The method can be implemented by the following steps 20 to 25.

[0261] Step 20: The user enters itinerary-related information in the itinerary planning interface of the electronic device, for example, "I want to go on a beach vacation with my family during the National Day holiday, and the budget is within 10,000 yuan."

[0262] Step 21, the electronic device obtains the travel time from the calendar, learns the beaches previously visited by the user from the location data, and analyzes the points of interest for beach vacations in the browsing history.

[0263] Step 22: The electronic device inputs the itinerary-related information and the user's travel preferences into a large model. The large model combines the user profile, the operation data in the electronic device, the itinerary-related information and the user's travel preferences to identify the needs as "beach vacation", "family activities" and "budget constraints".

[0264] Optionally, in the embodiment of the present application, the user profile may include at least one of the following: user gender, user age, user family members, etc. The specific information may be determined according to actual use requirements, and the embodiment of the present application does not limit this.

[0265] Optionally, in an embodiment of the present application, the operation data in the above-mentioned electronic device may include at least one of the following: historical travel browsing information and historical travel search information.

[0266] Step 23: The electronic device obtains nearby beach information from the scenic spot database, obtains weather conditions at the destination from a weather application, and obtains evaluation data of scenic spots and activities from user evaluations.

[0267] Step 24, the electronic device generates recommendations including affordable beaches, family-friendly activities, and budget-friendly accommodations through the large model.

[0268] Step 25: If the electronic device detects that the weather forecast for the destination shows heavy rain, the electronic device may adjust the recommended itinerary through the large model, provide indoor activities or adjust the destination.

[0269] The information recommendation method provided by the embodiment of the present application is specifically explained below by taking the recommendation of a city sightseeing itinerary as an example. The method can be implemented by the following steps 30 to 35.

[0270] Step 30: The user enters itinerary-related information in the itinerary planning interface of the electronic device, for example, "I want to go sightseeing in the city for three days tomorrow, mainly interested in historical sites, with no budget limit."

[0271] Step 31: The electronic device obtains travel time from the calendar application, learns the user's interest in the city's historical attractions from the location data, and analyzes relevant records in the application usage to obtain the user's travel preference information.

[0272] Optionally, in an embodiment of the present application, the relevant records in the above-mentioned application usage may include at least one of the following: scenic spot information that the user has historically liked in the browser application and scenic spot information that the user has historically shared in the browser application.

[0273] Step 32: The electronic device inputs the itinerary-related information and travel preference information into the big model. The big model combines the user profile and the electronic device operation data to identify the needs as "city sightseeing", "historical attractions", and "unlimited budget".

[0274] Step 33: The electronic device obtains historical scenic spot information from the city scenic spot database, and obtains traffic conditions between scenic spots from the traffic application program.

[0275] Step 34: The electronic device generates an itinerary including major historical attractions and recommends highly rated guided tours and dining options.

[0276] Step 35: If the user is particularly interested in a certain attraction during the trip, the electronic device can adjust the itinerary based on user feedback and add related attractions or activities.

[0277] The above-mentioned method embodiments, or various possible implementation methods in each method embodiment, can be executed separately, or, under the premise that there is no contradiction, can also be executed in combination with each other. The specific implementation can be determined according to actual usage requirements, and the embodiments of the present application do not limit this.

[0278] It should be noted that the information recommendation method provided in the embodiment of the present application can be executed by an information recommendation device. In the embodiment of the present application, the information recommendation device executing the information recommendation method is taken as an example to illustrate the information recommendation device provided in the embodiment of the present application.

[0279] Figure 7 A possible structural diagram of the information recommendation device involved in the embodiment of the present application is shown. Figure 7 As shown, the information recommendation device 70 may include: an acquisition module 71 and a display module 72 .

[0280] The acquisition module 71 is used to acquire the travel destination. The display module 72 is used to display the travel recommendation information according to the AI ​​memory information corresponding to the travel destination acquired by the acquisition module 71.

[0281] In a possible implementation, the acquisition module 71 is specifically used to acquire the travel destination through conversation messages; acquire the travel destination through emails; acquire the travel destination through schedule information; and acquire the travel destination through input information of an AI interactive interface.

[0282] In one possible implementation, the AI ​​memory information corresponding to the travel destination is determined based on at least one of the following: conversation messages, user information matching the travel destination in the first application, schedule information, note information, and memo information.

[0283] In a possible implementation, the display module 72 is specifically used to display travel recommendation information based on the AI ​​memory information corresponding to the travel destination, the travel-related information corresponding to the travel destination, and the historical travel information.

[0284] In a possible implementation, the above travel recommendation information includes at least one of the following: travel transportation information, travel accommodation information, travel entertainment information, travel dining information, and travel social information.

[0285] In one possible implementation, combining Figure 7 ,like Figure 8As shown, the information recommendation device 70 provided in the embodiment of the present application also includes a receiving module 73 and a processing module 74. The display module 72 is specifically used to display the travel recommendation information on the travel recommendation interface according to the AI ​​memory information corresponding to the travel destination; the receiving module 73 is used to receive a first input to the first control in the travel recommendation interface. The processing module 74 is used to respond to the first input received by the receiving module 73 and perform at least one of the following through the AI ​​function: booking transportation, booking a hotel, booking tickets, booking a restaurant, and sending a conversation message to a communication object.

[0286] In a possible implementation, the receiving module is further configured to receive a second input to a second control in the travel recommendation interface. The processing module is further configured to update the travel recommendation information corresponding to the second control in response to the second input received by the receiving module.

[0287] An embodiment of the present application provides an information recommendation device that displays travel recommendation information based on AI memory information corresponding to a travel destination. Since the AI ​​memory information is the user's personalized information about the travel destination recorded by the AI ​​function, such as the places the user wanted to go to at the travel destination last time but did not have time to go, the travel recommendation information is richer and more in line with the user's needs, thereby improving the flexibility of the electronic device's itinerary recommendations.

[0288] The task recommendation 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 mobile electronic device can be a mobile phone, a tablet computer, a laptop computer, a PDA, a car 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. It 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.

[0289] The task recommendation 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.

[0290] The task recommendation device provided in the embodiment of the present application can implement each process implemented in the above method embodiment, and will not be described again here to avoid repetition.

[0291] Alternatively, if Fig. 9 As shown, an embodiment of the present application also provides an electronic device 90, including a processor 91 and a memory 92, wherein the memory 92 stores programs or instructions that can be executed on the processor 91, and when the program or instructions are executed by the processor 91, the various steps of the above-mentioned task recommendation method embodiment are implemented, and the same technical effect can be achieved. To avoid repetition, they are not described here.

[0292] 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.

[0293] Fig.10 A schematic diagram of the hardware structure of an electronic device to implement an embodiment of the present application.

[0294] 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.

[0295] 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.10 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.

[0296] Among them, the processor 110 is used to obtain the travel destination; and display travel recommendation information according to the AI ​​memory information corresponding to the travel destination.

[0297] Optionally, in an embodiment of the present application, the above-mentioned processor 110 is specifically used to obtain the travel destination through conversation messages; obtain the travel destination through emails; obtain the travel destination through schedule information; obtain the travel destination through input information of the AI ​​interactive interface.

[0298] Optionally, in an embodiment of the present application, the above-mentioned processor 110 is specifically used to display travel recommendation information based on the AI ​​memory information corresponding to the travel destination, the travel-related information corresponding to the travel destination, and the historical travel information.

[0299] Optionally, in an embodiment of the present application, the processor 110 is specifically used to display travel recommendation information on the travel recommendation interface according to the AI ​​memory information corresponding to the travel destination. The user input unit 107 is also used to receive a first input to a first control in the travel recommendation interface. The processor 110 is also used to execute at least one of the following through the AI ​​function in response to the first input: booking transportation, booking a hotel, booking tickets, booking a restaurant, and sending a conversation message to a communication partner.

[0300] Optionally, in the embodiment of the present application, the user input unit 107 is further configured to receive a second input to a second control in the travel recommendation interface. The processor 110 is further configured to update the travel recommendation information corresponding to the second control in response to the second input.

[0301] An embodiment of the present application provides an electronic device that displays travel recommendation information based on AI memory information corresponding to a travel destination. Since the AI ​​memory information is the user's personalized information about the travel destination recorded by the AI ​​function, such as the places the user wanted to go to at the travel destination last time but did not have time to go, the travel recommendation information is richer and better matches the user's needs, thereby improving the flexibility of the electronic device's itinerary recommendations.

[0302] 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 will not be described here.

[0303] 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, they will not be described again here.

[0304] 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.

[0305] 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.

[0306] 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.

[0307] 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 method embodiment are implemented and the same technical effect can be achieved. To avoid repetition, it will not be repeated here.

[0308] 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.

[0309] 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 method embodiment, and can achieve the same technical effect. To avoid repetition, it will not be repeated here.

[0310] 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.

[0311] 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 itinerary planning method embodiment described above, and can achieve the same technical effect. To avoid repetition, it will not be described here.

[0312] 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.

[0313] 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.

[0314] 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 information recommendation method, characterized in that: The method comprises: Get the travel destination; Travel recommendation information is displayed according to the AI ​​memory information corresponding to the travel destination; the AI ​​memory information is the user's personalized information about the travel destination recorded by the AI ​​function.

2. The method according to claim 1, characterized in that The obtaining of the travel destination includes one of the following: Acquiring the travel destination through a conversation message; Obtain the travel destination via email; Acquire the travel destination through schedule information; The travel destination is obtained through input information of the AI ​​interactive interface.

3. The method according to claim 1, characterized in that The AI ​​memory information corresponding to the travel destination is determined based on at least one of the following: conversation message, user information matching the travel destination in the first application, schedule information, note information, and memo information.

4. The method according to claim 1, characterized in that The displaying of travel recommendation information according to the AI ​​memory information corresponding to the travel destination includes: Travel recommendation information is displayed based on the AI ​​memory information corresponding to the travel destination, the travel-related information corresponding to the travel destination, and the historical travel information.

5. The method according to claim 1, characterized in that The travel recommendation information includes at least one of the following: travel transportation information, travel accommodation information, travel entertainment information, travel dining information, and travel social information.

6. The method according to claim 5, characterized in that The displaying of travel recommendation information according to the AI ​​memory information corresponding to the travel destination includes: Displaying the travel recommendation information on the travel recommendation interface according to the AI ​​memory information corresponding to the travel destination; The method further comprises: Receiving a first input to a first control in the travel recommendation interface; In response to the first input, at least one of the following is performed through the AI ​​function: booking transportation, booking a hotel, booking tickets, booking a restaurant, and sending a conversation message to a communication partner.

7. The method according to claim 6, characterized in that The method further comprises: receiving a second input to a second control in the travel recommendation interface; In response to the second input, the travel recommendation information corresponding to the second control is updated.

8. An information recommendation device, characterized in that: The information recommendation device comprises: an acquisition module and a display module; The acquisition module is used to acquire the travel destination; The display module is used to display travel recommendation information according to the AI ​​memory information corresponding to the travel destination acquired by the acquisition module; the AI ​​memory information is the user's personalized information about the travel destination recorded by the AI ​​function.

9. An electronic device, characterized in that: The method comprises a processor, a memory, and a program or instruction stored in the memory and executable on the processor, wherein the program or instruction, when executed by the processor, implements the steps of the information recommendation method as claimed in any one of claims 1 to 7.

10. A readable storage medium, characterized in that: The readable storage medium stores a program or an instruction, and when the program or the instruction is executed by the processor, the steps of the information recommendation method according to any one of claims 1 to 7 are implemented.

Images