Information pushing method and device, equipment, storage medium and program product

Abstract

One or more embodiments of the invention provide an information pushing method and device, equipment, a storage medium and a program product. The method comprises the following steps: acquiring life information related to a geographic position according to the geographic position of a user terminal; embedding the life information into a preset prompt template, and generating a prompt word used by a trained information generation model; the cue word is used for indicating the information generation model to generate reminding information, and the reminding information comprises key information extracted from the life information and / or life suggestion information generated based on the life information; inputting the cue word into the information generation model, so that the information generation model generates reminding information according to the indication of the cue word; and pushing the reminding information in the user terminal.

Description

Technical Field

[0001] One or more embodiments of the present specification relate to the field of computer software technology, and in particular, to an information push method, device, electronic device, computer-readable storage medium, and computer program product. Background Art

[0002] In the current information overload environment, users may be disturbed by a large amount of irrelevant or insignificant information. For example, users' terminals, social media, and applications often push various notifications to them, such as promotional information, news updates, social media reminders, etc. Most of these notifications may be irrelevant to the user's current needs; or users are exposed to a large amount of information every day, such as news, emails, social media posts, etc. Most of this information may not be needed or interesting to the user. A large amount of information can easily lead to information overload for users, and even affect their daily life and work efficiency. Therefore, it is necessary to provide an accurate information push method. Summary of the invention

[0003] In view of this, one or more embodiments of the present specification provide an information push method, device, electronic device, computer-readable storage medium, and computer program product.

[0004] To achieve the above objectives, one or more embodiments of this specification provide the following technical solutions:

[0005] According to a first aspect of one or more embodiments of this specification, a method for pushing information is proposed, including:

[0006] According to the geographical location of the user terminal, obtaining life information related to the geographical location;

[0007] The life information is embedded in a preset prompt template to generate prompt words for use by the trained information generation model; the prompt words are used to instruct the information generation model to generate reminder information, and the reminder information includes key information extracted from the life information and / or life suggestion information generated based on the life information;

[0008] Inputting the prompt word into the information generation model, so that the information generation model generates the reminder information according to the instruction of the prompt word;

[0009] The reminder information is pushed in the user terminal.

[0010] According to a second aspect of the embodiments of this specification, there is provided an information push device, including:

[0011] A life information acquisition module, used to acquire life information related to the geographical location according to the geographical location of the user terminal;

[0012] a prompt word generation module, used to embed the life information into a preset prompt template to generate prompt words for use by the trained information generation model; the prompt words are used to instruct the information generation model to generate reminder information, and the reminder information includes key information extracted from the life information and / or life suggestion information generated based on the life information;

[0013] A reminder information generation module, used for inputting the prompt word into the information generation model, so that the information generation model generates the reminder information according to the instruction of the prompt word;

[0014] The reminder information push module is used to push the reminder information in the user terminal.

[0015] According to a third aspect of the embodiments of this specification, there is provided an electronic device, including:

[0016] processor;

[0017] a memory for storing processor-executable instructions;

[0018] When the processor executes the executable instructions, it is used to implement the method described in the first aspect.

[0019] According to a fourth aspect of the embodiments of this specification, there is provided a computer-readable storage medium on which a computer program is stored, and when the program is executed by a processor, the steps of any of the above methods are implemented.

[0020] According to a fifth aspect of the embodiments of this specification, a computer program product is provided, including a computer program, which implements the steps of any of the above methods when executed by a processor.

[0021] The technical solutions provided by the embodiments of this specification may have the following beneficial effects:

[0022] In the embodiments of this specification, according to the geographical location of the user terminal, the life information of the surrounding environment of the user terminal is obtained, and the information irrelevant to the user's environment can be initially filtered out, avoiding the interference of irrelevant content from the source; then the life information is embedded in the preset prompt template to generate a prompt word, and the prompt word is used to instruct the information generation model to generate reminder information, and the reminder information includes key information extracted from the life information and / or life suggestion information generated based on the life information, so that the information generation model generates reminder information according to the instructions of the prompt word, and the information generation model is deeply processed to obtain more relevant and practical reminder information and push the reminder information in the user terminal, avoiding general content. In summary, according to the scheme provided in the embodiments of this specification, not only can the amount of irrelevant information received by the user be effectively reduced, but also the accuracy of pushing information to the user to whom the user terminal belongs can be significantly improved.

[0023] It is to be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present specification. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] Figure 1 It is a schematic diagram of the architecture of an information push service system provided by an exemplary embodiment.

[0025] Figure 2 It is a flowchart of an information push method provided by an exemplary embodiment.

[0026] Figure 3 It is a flowchart of another information push method provided by an exemplary embodiment.

[0027] Figure 4A , Figure 4B and Figure 4C It is a schematic diagram of three types of cards corresponding to three display modes of weather information provided by an exemplary embodiment.

[0028] Figure 5 It is a structural schematic diagram of a device provided by an exemplary embodiment. DETAILED DESCRIPTION

[0029] Exemplary embodiments will be described in detail herein, examples of which are shown in the accompanying drawings. When the following description refers to the drawings, the same numbers in different drawings represent the same or similar elements unless otherwise indicated. The implementations described in the following exemplary embodiments do not represent all implementations consistent with one or more embodiments of this specification. Instead, they are merely examples of devices and methods consistent with some aspects of one or more embodiments of this specification as detailed in the appended claims.

[0030] It should be noted that: in other embodiments, the steps of the corresponding method are not necessarily performed in the order shown and described in this specification. In some other embodiments, the steps included in the method may be more or less than those described in this specification. In addition, a single step described in this specification may be decomposed into multiple steps for description in other embodiments; and multiple steps described in this specification may be combined into a single step for description in other embodiments.

[0031] The user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this manual are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with the relevant laws, regulations and standards of relevant countries and regions, and provide corresponding operation entrances for users to choose to authorize or refuse.

[0032] In the current information overload environment, users may be distracted by a large amount of irrelevant or insignificant information.

[0033] In one possible scenario, users' terminals, social media, and applications often push various notifications to them, such as promotional information, news updates, social media reminders, etc. Most of these notifications may be irrelevant to the user's current needs. For example, a user may be concentrating on work, but constantly receives discount promotion notifications from shopping apps, or irrelevant dynamic reminders on social media. These information not only occupy the user's attention, but may also cause their work efficiency to decrease.

[0034] In another possible scenario, users are exposed to a large amount of information every day, such as news, emails, social media posts, etc. Most of this information may be unnecessary or uninteresting to the user. However, due to the lack of an effective filtering mechanism, users need to spend a lot of time looking for useful parts in a large amount of information. This ineffective information filtering process consumes the user's time and energy.

[0035] The large amount of information leads to the problem of information overload for users, affecting their daily life and work efficiency.

[0036] Based on this, an embodiment of this specification provides an information push method, which obtains life information related to the geographical location of the user terminal based on the geographical location, ensures that the acquired life information is highly relevant to the user, and then uses the information generation model to extract key information from the life information and / or life suggestion information generated based on the life information to generate reminder information that the user really needs, which can reduce the possibility of user information overload and avoid users being disturbed by irrelevant information.

[0037] For example, Figure 1 FIG. 1 is a schematic diagram of the architecture of an information push service system provided by an exemplary embodiment. Figure 1 As shown, the system may include a server 11, a network 12, and several user terminals, including but not limited to a PC (Personal Computer) 13, a mobile phone 14, and the like.

[0038] The server 11 may be a physical server including an independent host, or the server 11 may be a virtual server carried by a host cluster. During operation, the server 11 may run a server-side program of an application to implement the relevant functions of the application. For example, when the server 11 runs a program of an information push service, it may be implemented as a corresponding information push service end.

[0039] PC13 and mobile phone 14 are only some types of user terminals that users can use. In fact, users can obviously also use user terminals such as the following types: tablet devices, laptops, PDAs (Personal Digital Assistants), wearable devices (such as smart glasses, smart watches, etc.), etc., and one or more embodiments of this specification do not limit this. During operation, the user terminal can run a program on the client side of a certain application to implement the relevant functions of the application. For example, when the user terminal runs a program for an information push service, it can be implemented as a client of the information push service. Among them, the application program of the client of the above-mentioned information push service can be started and run on the user terminal. The program on the client side can be a native application installed on the user terminal, or the program on the client side can be a small program, a quick application or other similar forms. Of course, when using web page technologies such as HTML5 or similar, the relevant functions can be implemented through the page displayed by the browser. The browser here can be an independent browser application or a browser module embedded in certain applications.

[0040] As for the network 12 for interaction between user terminals such as PC 13 and mobile phone 14 and server 11, it is possible to select a wired or wireless network to achieve communication based on the communication mode supported by the corresponding user terminal, and this specification does not limit this. For example, PC 13 can support both wired and wireless communication, so it is possible to use a wired or wireless network to achieve communication as needed, while mobile phone 14 usually only supports wireless communication, so it is possible to use a wireless network to achieve communication.

[0041] The information push method provided in the embodiments of this specification may be executed by the above-mentioned server, or by the above-mentioned user terminal, or by both the server and the user terminal, and this embodiment does not impose any limitation on this.

[0042] In some embodiments, see Figure 2 , this embodiment provides a flow chart of an information push method. Taking the information push method executed by a server as an example for exemplary description, the method includes:

[0043] In S201, life information related to the geographical location is obtained according to the geographical location of the user terminal.

[0044] In this step, the life information related to the geographical location of the user terminal contains information that is closely related to the user and often better suits the user's actual needs. For example, when the user is in the office area, it is more meaningful to push work-related reminders or lunch recommendations at nearby restaurants than to push discount notifications from shopping apps. Through this mechanism, information that is irrelevant to the user's current scenario is filtered out, avoiding interference from irrelevant content at the source.

[0045] Exemplarily, the life information includes at least one of the following: weather information, traffic information, store business information, and public facility usage information; but is not limited thereto.

[0046] For example, the server can obtain weather information of the user terminal's location from at least one meteorological platform based on the user terminal's location. The weather information includes but is not limited to: (1) temperature, the temperature of the current environment, such as the current temperature, the highest temperature of the day, the lowest temperature of the day, etc.; (2) weather type, which describes the current or future weather conditions at the user's location, such as sunny, cloudy, overcast, rainy, snowy, foggy, and dust storms; (3) warning type, including high temperature warning, rainstorm warning, typhoon warning, cold wave warning, haze warning, and strong wind warning; (4) warning level, which is usually divided into multiple levels according to the severity of the weather event, usually divided into blue warning, yellow warning, orange warning, and red warning from low to high; (5) warning content, which is a specific description of the warning information, usually including detailed information such as the cause of the warning, the affected area, the duration, and the recommended measures; the warning content can provide the public with specific prevention suggestions, such as avoiding going out, paying attention to keeping warm, and strengthening the reinforcement of buildings; (6) weather information at a future time, which refers to the forecast of weather conditions within a certain period of time in the future, usually including weather forecasts for the next few hours, the next day, or the next few days.

[0047] For another example, the server can obtain real-time traffic information of the geographical location of the user terminal from at least one traffic platform. Traffic information includes but is not limited to: (1) traffic conditions, current road congestion (such as smooth, slow, congested, etc.); (2) accident reports, traffic accident information on the road, including accident location, time of occurrence, degree of impact, etc. (3) construction information, road construction information, including construction location, construction time period, road closure or detour suggestions, etc. (4) public transportation information, real-time status of public transportation (such as buses and subways), including train numbers, schedules, whether they are delayed, etc. (5) navigation suggestions, based on current traffic conditions, provide better driving route suggestions to avoid congestion or detour construction areas.

[0048] For another example, the server can obtain business information of stores near the geographical location of the user terminal from at least one store website or online store platform. Store business information includes but is not limited to: (2) business hours, store opening and closing times, (2) peak hours, store traffic forecasts, including peak time period recommendations; (3) store promotions, current or upcoming promotions, including discount information, coupons, etc. (4) store distance, the distance between the store and the user's current location, and the estimated arrival time. (5) store ratings, user ratings and comments, to help users choose suitable stores.

[0049] For another example, the server can obtain the usage information of public facilities from at least one public service platform based on the geographical location of the user terminal. The usage information of public facilities includes but is not limited to the following: (1) opening hours, opening and closing hours of public facilities (such as parks, gymnasiums, libraries, etc.); (2) availability status, current usage of facilities (such as idle, full, reservation required, etc.); (3) reservation information, whether reservation is required in advance, how to make a reservation, and the current status of the reservation; (4) maintenance or closure information, maintenance time or temporary closure notice of the facility, including the reason and reopening time; (5) user instructions, precautions or special reminders when using public facilities (such as epidemic prevention measures, venue rules, etc.).

[0050] In S202, the life information is embedded in a preset prompt template to generate prompt words for use by the trained information generation model; the prompt words are used to instruct the information generation model to generate reminder information, and the reminder information includes key information extracted from the life information and / or life suggestion information generated based on the life information.

[0051] In this step, life information is structured into specific prompt words (prompt) through prompt templates, and the prompt words are used to instruct the information generation model to generate personalized reminder information for the user.

[0052] The preset prompt template is a text framework used to structure user life information and provide clear instructions for the information generation model during the information push process. For example, different prompt templates can be set for different types of life information to provide clear instructions for different types of life information.

[0053] For example, if the life information is weather information, and the weather information prompt template is: "According to the weather forecast, today's weather is {weather type}, and the temperature is between {minimum temperature} and {maximum temperature} degrees. Please generate corresponding reminders based on this information and suggest whether the user needs to take special measures." The life information includes: {weather type: thunderstorm, temperature between 25 and 32 degrees Celsius}. By embedding this life information into the prompt template, the prompt words that can be obtained are: "According to the weather forecast, today's weather is thunderstorm, and the temperature is between 25 and 32 degrees. Please generate corresponding reminders based on this information and suggest whether the user needs to take special measures."

[0054] For another example, life information includes traffic information. Assume that the weather information prompt template is: "The current road traffic conditions show {traffic conditions}. Please generate corresponding travel reminders based on this information and provide better travel suggestions." Life information includes congestion on the Fourth Ring Road. By embedding this life information into the prompt template, the prompt words that can be obtained are: "The current road traffic conditions show congestion on the Fourth Ring Road. Please generate corresponding travel reminders based on this information and provide better travel suggestions."

[0055] For example, the prompt word may also include the specific type of key information to be extracted, and this embodiment does not impose any restrictions on this. For example, if the life information is weather information, the specific type of key information may be the temperature range of the day, rainfall probability, rainstorm / typhoon warning, air quality index, etc. For another example, if the life information is a store business information scenario, the specific type of key information may be business hours, special business arrangements on holidays, discount activities on the day, new product recommendations, etc.

[0056] In S203, the prompt word is input into the information generation model, so that the information generation model generates reminder information according to the instruction of the prompt word.

[0057] In this step, at least one of the key information extracted from the life information and the life suggestion information generated based on the life information can be extracted through the information generation model, which not only improves the relevance and practicality of the reminder information, but also avoids general content, thereby reducing the amount of irrelevant information received by the user.

[0058] Using the weather information example above, assume that the prompt word input into the information generation model is "According to the weather forecast, today's weather is thunderstorms, and the temperature is between 25 and 32 degrees. Please generate corresponding reminders based on this information and suggest whether the user needs to take special measures." The reminder information generated by the information generation model may include: "Today there will be thunderstorms, and the temperature will be high. It is recommended that you carry rain gear with you and avoid staying outdoors for a long time."

[0059] Using the traffic information example above, assume that the prompt word input into the information generation model is "The current road traffic conditions show that the Fourth Ring Road is congested. Please generate corresponding travel reminders based on this information and provide better travel suggestions." The reminder information generated by the information generation model may include: "The Fourth Ring Road is currently congested and the travel time is expected to be extended. It is recommended that you choose public transportation or leave early to avoid peak hours."

[0060] In S204, the reminder information is pushed to the user terminal.

[0061] Through the above steps, the content pushed to the user terminal is highly relevant to the user's current geographical location, and after deep processing by the information generation model, it avoids pushing too general or redundant information. Compared with the traditional indiscriminate push mechanism, this intelligent screening-based approach greatly reduces the possibility of user information overload, avoids users being disturbed by irrelevant information, and can reduce the time and energy of users to screen information, thereby improving work and life efficiency.

[0062] In some embodiments, the information generation model is exemplarily described here:

[0063] The information generation model can be obtained by supervised training of a pre-trained model based on a number of prompt word samples marked with reminder information tags; different prompt word samples are obtained by embedding different life information into preset prompt templates.

[0064] Among them, pre-trained models are usually large language models that are pre-trained on massive amounts of text data and have the ability to generate and understand natural language. However, the generation capabilities of pre-trained models are general and need to be fine-tuned to adapt to specific tasks, such as generating reminder information related to life information.

[0065] Prompt word samples are text inputs in a specific form that guide the pre-trained model to generate specific types of outputs. In the information push scenario, prompt word samples will contain text fragments that have been embedded with life information. Each prompt word sample is manually annotated to clearly identify the expected reminder information (i.e., label) to ensure that the trained model can generate reminder content that meets the expectations.

[0066] The reminder information label is an identifier added to each prompt word sample, indicating the type of reminder information that the sample should generate. For example, a prompt word sample may contain "According to the weather forecast, today's weather is thunderstorms, and the temperature is between 25 and 32 degrees. Please generate corresponding reminders based on this information and advise users whether special measures are needed." Its corresponding label may be "Today there will be thunderstorms and high temperatures. It is recommended that you bring rain gear with you and avoid staying outdoors for a long time."

[0067] During the training process, the prompt word samples and their corresponding reminder information labels can be input into the pre-trained model for supervised fine-tuning, and its parameters can be continuously adjusted through the loss function (such as cross entropy loss) to minimize the difference between the generated reminder information and the annotated reminder information label. The trained model can generate highly relevant reminder information based on the input life information. For example, when a piece of weather information is input, the model can automatically generate a suitable weather reminder, and the content length, expression, etc. meet the requirements of the preset template. Through supervised training of the pre-trained neural network model, the information generation model can better understand and process life information and generate reminder information that meets specific requirements.

[0068] The following is a further description of the information push process:

[0069] In some embodiments, push conditions can be introduced when pushing information. Only when the push conditions are met will the life information be embedded in the prompt template for further processing and push, that is, the push steps of step S202 to step S204 will be executed. This means that the user's needs can be dynamically evaluated through push conditions, rather than pushing all information indiscriminately. For example, when the user is commuting, reminders related to traffic or weather can be pushed first based on the push conditions, and content not related to commuting can be filtered out. This mechanism blocks irrelevant information in specific scenarios and effectively reduces interference.

[0070] In one possible implementation, see Figure 3, the user terminal can obtain its geographical location and send it to the server (S301); the server can obtain life information related to the geographical location based on the geographical location of the user terminal (S302). Then, based on at least one of the historical behavior patterns and schedule information of the user to which the user terminal belongs, it can be inferred whether the user to which the user terminal belongs has a travel intention in the current time period (S303); wherein at least one of the historical behavior patterns and schedule information of the user to which the user terminal belongs can be obtained from a preset database. If the user to which the user terminal belongs has a travel intention in the current time period and it is determined that the push conditions are met, the step of embedding the life information into the preset prompt template to generate a prompt word and its subsequent steps (S305~S306) are executed; if the user to which the user terminal belongs has no travel intention in the current time period and it is determined that the push conditions are not met, the information push process is terminated (S304).

[0071] This embodiment can effectively determine whether the user has the intention to travel through at least one of the user's historical behavior patterns and schedule information, thereby more accurately pushing life information related to the user's current needs. This push mechanism based on travel needs reduces the interference of irrelevant information, so that the user only receives information related to his current situation, thereby improving the practicality and pertinence of the information.

[0072] Exemplarily, historical behavior patterns refer to the user's behavior habits and behavior patterns in the past period of time. The server can obtain the user's historical behavior patterns based on the analysis of the historical travel information of the user to which the user terminal belongs. Historical behavior patterns include but are not limited to the user's commuting time, shopping preferences, travel frequency, social activity time, etc. These historical behavior patterns can help the server infer the user's possible future behavior and decide whether to push information based on these inferences to avoid disturbing the user.

[0073] For example, if a user goes to work from home between 7 and 8 a.m. on weekdays, the server can consider this behavior as a fixed travel habit. If the weather forecast shows that there may be heavy rain on a certain weekday morning, the server can push weather information and travel suggestions in advance so that the user can make timely arrangements.

[0074] For example, for exercise habits, a user is accustomed to running on weekend mornings. The server can push relevant information such as weather information or the opening status of nearby parks before exercise.

[0075] The historical travel information of the user to which the user terminal belongs is determined based on at least one of the following methods:

[0076] In the first method, the server can obtain the historical travel information of the user to which the user terminal belongs based on the bill data of the travel-related bills in the user terminal. The bill data in the user terminal can reflect the user's travel history. For example, travel-related consumption records such as taxi rides, public transportation ticket purchases, and car rental services can all be analyzed. By analyzing the travel time, travel mode, and other information in these bill data, the user's historical travel mode can be effectively obtained.

[0077] For example, if a user has a taxi record during the peak hours every Friday night, the server can infer that the user is accustomed to traveling during this time period and may use taxi services to travel. By analyzing the bill, it is possible to determine the user's common travel methods during a specific time period, such as buses, taxis, shared bicycles, etc. For example, if the user's bill shows frequent use of high-speed rail, the server can infer that the user often takes long-distance trips on weekends.

[0078] In the second method, the server can determine the historical travel information of the user to which the user terminal belongs based on the changes in the geographical location of the user terminal in the historical time period. For example, by analyzing the changes in the geographical location of the user terminal in the historical time period, the user's travel trajectory and mode can be obtained. The user terminal's GPS data, Wi-Fi connection records, cellular network base station locations, etc. can all be used for this analysis.

[0079] For example, the change in the user's geographic location from home to work every day can indicate the user's daily commuting route. By identifying this regular change, the server can infer the user's travel habits, such as going from home to work between 7 and 8 in the morning and returning home from work between 5 and 6 in the afternoon.

[0080] For another example, if the server detects that the user travels from a fixed location to another fixed location every Friday night, and the distance between the two locations is far, it may be inferred that the user has a fixed travel habit, such as going home or visiting relatives and friends on weekends.

[0081] In the third mode, the server can determine the historical travel information of the user to which the user terminal belongs based on the historical driving data of the vehicle connected to the user terminal in communication. The historical travel information includes but is not limited to the vehicle's start time, driving route, parking location and other data.

[0082] By analyzing the driving records of vehicles connected to the user's terminal, the user's common travel time periods and routes can be inferred. For example, if the user's car leaves home and drives to the company during a specific time period every Monday to Friday morning, the server can identify it as the user's daily commuting route. Or if the server detects that the vehicle is parked for a long time at certain specific locations, it may mean that the user often goes to these locations. Combined with the driving data, the server can further infer whether these locations are the user's workplace, residence, or frequent entertainment venues.

[0083] In this embodiment, by comprehensively utilizing at least one of billing data, geographic location changes, and vehicle driving data, the server can more accurately determine the user's historical travel information. This data can help the server more accurately infer the user's travel intentions in the future, and based on this, provide more accurate and personalized information push, thereby improving the user experience and reducing the redundancy of information push.

[0084] For example, life appointment information refers to activities or events scheduled in advance by the user, such as meetings in the calendar, hospital appointments, restaurant reservations, travel arrangements, etc. By accessing this schedule information, the server can understand the user's plan in a specific time period in the future, thereby inferring his travel intention or activity needs.

[0085] For example, if a user sets a company meeting at 9 a.m. in the calendar, the server can push traffic information, weather information, or remind the user to prepare meeting materials in advance. This schedule-based reminder can help users better manage their time and avoid missing important activities.

[0086] Another example is travel planning. If a user records a business trip plan for the next few days in the calendar, the server can push relevant weather forecasts and hotel reservation reminders to help the user make adequate preparations for the trip.

[0087] Another example is restaurant reservations. If a user makes a reservation at a restaurant during a specific time period, the server can push route suggestions, parking information or weather conditions around the restaurant in advance to ensure that the user can make it to the appointment smoothly.

[0088] In this embodiment, by analyzing at least one of the historical behavior patterns and life appointment information, the server can better understand the user's daily behavior and future plans, thereby achieving more accurate information push. This not only helps to meet the personalized needs of users, but also effectively reduces the interference of irrelevant information, improves the efficiency of information push and user satisfaction.

[0089] In another possible implementation, the server may periodically obtain life information related to the geographical location according to the geographical location of the user terminal. The server may compare the currently obtained life information related to the geographical location with the life information related to the geographical location obtained last time; if the difference between the two is greater than a preset difference, it is determined that the push condition is met, and the step of embedding the currently obtained life information related to the geographical location into the preset prompt template to generate a prompt word and subsequent steps are executed.

[0090] In this embodiment, by comparing the currently acquired life information with the life information acquired last time (life information at different times in the same geographical location), the server can detect significant changes in the user's surrounding environment. For example, sudden changes in weather, sudden changes in traffic conditions, opening or closing of new stores, and other information may cause large differences. When the difference is greater than the preset threshold, the server believes that such changes may have an impact on the user's daily life, thereby triggering information push. This push strategy based on actual environmental changes can effectively avoid the push of irrelevant information and reduce interference with users. And only relevant information is pushed when the environment changes significantly. This differentiated push method is more personalized. Unlike general, periodic pushes, this push method is more in line with the actual needs of users and significantly improves the user experience.

[0091] The preset difference may be specifically set according to the actual application scenario, and this embodiment does not impose any limitation on this.

[0092] For example, life information includes weather information, and the server periodically obtains weather information at the location of the user terminal. At 10 a.m., the information obtained by the server shows that the weather is sunny, the temperature is moderate, and there is no warning. At 11 a.m., the server obtains weather information again and finds that a rainstorm warning has suddenly been issued locally, and it will continue to rain in the next few hours. The server compares the weather information at 10 a.m. and 11 a.m. and finds that the meteorological conditions have changed significantly, especially the issuance of rainstorm warnings. Based on the significant changes in weather information, the server executes steps S202 and S203 to obtain reminder information, and sends the reminder information to the user terminal so that it can be pushed to the user through the user terminal. The content of the reminder information may include rainstorm warnings, suggestions to carry rain gear, and try to avoid going out or adjusting travel plans. In this embodiment, users can obtain weather information updates related to life in a timely manner, avoid getting wet in heavy rain or travel obstructions, and improve travel safety and comfort.

[0093] For another example, life information includes traffic information. The server detects that the traffic condition of a main road in the user's city is good at 8 a.m., but at 9 a.m., the road section is seriously congested due to a traffic accident. The server compares the traffic information at 8 a.m. and 9 a.m. and finds that the traffic condition of the road section has changed significantly, from smooth to seriously congested. The server executes steps S202 and S203, obtains reminder information and pushes the reminder information in time to inform the user of the congestion of the road section and provide recommended alternative routes. Users can adjust their travel routes according to the latest traffic information to avoid traffic jams and improve travel efficiency and experience.

[0094] As another example, users usually go to the local public library on weekends. At 9 a.m. on Saturday, the information obtained by the server shows that the library is open as usual, but at 12 noon, the library is urgently closed due to equipment failure. The server compares the library usage information at 9 a.m. and 12 noon, and finds a significant change from open to emergency closure. The server executes steps S202 and S203, obtains reminder information and pushes the reminder information in time, informing the user that the library is temporarily closed due to a failure, and recommends that the user visit another day or go to another library. Users can be informed of changes in the use status of public facilities in a timely manner, avoid wasting time on the way to the library, and arrange their time and itinerary reasonably.

[0095] From the above specific examples, it can be seen that by effectively monitoring significant changes in the user's surrounding environment and actively pushing relevant reminder information when necessary, it is ensured that the information obtained by the user is relevant and useful, avoiding unnecessary interruptions, thereby improving the user experience and the accuracy of information push.

[0096] Of course, in addition to the above push conditions, other push conditions may also be considered, and this embodiment does not impose any limitation on this.

[0097] For example, based on the device status or battery level of the user terminal, the server can push relevant reminder information. For example, when the user terminal is low on battery, the server can remind the user to charge or prompt nearby charging facilities.

[0098] For example, on a specific date or holiday (such as a holiday, anniversary, birthday, etc.), the server can push life information or suggestions related to the date. For example, on the user's birthday, the service order can push birthday discount information of nearby restaurants.

[0099] In some embodiments, the user terminal pre-stores multiple display modes for displaying different reminder information, and different display modes correspond to different display conditions, which are defined based on different life contents. Figure 3The server can determine the target display mode from multiple display modes based on the display conditions satisfied by the life information (S306); render the reminder information according to the target display mode and push it to the user terminal. For example, the server can send the identification information of the target display mode (used to uniquely identify the target display mode) and the reminder information to the user terminal, and the user terminal renders and displays the reminder information according to the target display mode (S307).

[0100] In this embodiment, by pre-storing multiple display modes and selecting a suitable display mode based on specific life information, the server can dynamically adjust the display mode of information according to the user's current environment and the type of information required. This method can provide a more personalized and accurate user experience. For example, in bad weather conditions, the server can select a conspicuous and prominent display mode to ensure that users can pay attention to important weather warning information in a timely manner. And because the display conditions of the display mode are defined based on specific life content, the server can better filter out information related to the current environment or user needs for display, reduce interference from irrelevant information, and help users obtain useful information faster in an environment with information overflow, and improve the accuracy of information push.

[0101] Exemplarily, each display mode includes a card displayed in the display interface of the user terminal; a card refers to an independent information block presented on the display interface of the user terminal, usually including specific reminder information, pictures, icons or other content. Among them, the cards included in different display modes have different visual effects. For example, the cards included in different display modes have at least one of different backgrounds, different fonts, different font sizes, different text layout positions or different text colors.

[0102] The designated area in the card included in the display mode is used to display the life advice information in different reminder information; the size of this designated area will affect the amount of text content that can be displayed, that is, the number of words. When generating reminder information, the server will generate a prompt word, which contains instructions on how to generate life advice information by the information generation model. In order to ensure the readability and adaptability of the life advice information, the prompt word is also used to indicate that the number of words of the life advice information generated by the information generation model is no more than a preset threshold, which depends on the size of the designated area in the card. Among them, the preset threshold, that is, the maximum number of words of the life advice information, is proportional to the size of the designated area, which means that the larger the designated area, the more words the life advice information generated by the information generation model can contain; conversely, the smaller the designated area, the number of words of the life advice information needs to be reduced to ensure that it is fully displayed without affecting readability. By limiting the number of words of the life advice information, this embodiment can avoid the problem of information overload in a limited display area, so that users can read the reminder information more clearly and comfortably.

[0103] For example, in card design, the size of the designated area is usually fixed, and the designer determines the layout of the card and the size of each area based on the screen size and display mode of the user terminal. When the information generation model generates life advice information, the server calculates the preset word count threshold based on the size of the designated area, and adds this word count threshold to the prompt word, instructing the model to generate an appropriate amount of content. After receiving the prompt word, the information generation model will generate life advice information suitable for display in the designated area according to the prompt. Finally, the server will automatically adjust the generated life advice information according to the size of the designated area of ​​the card, so that the content is complete and easy to read. Through this design, users can get appropriate life advice related to the current situation in different display modes, which effectively improves the practicality and readability of the information.

[0104] Exemplarily, the life information at least includes weather information, and the user terminal pre-stores at least one display mode for displaying weather information: (1) The display condition corresponding to the first display mode includes: the temperature indicated by the weather information is greater than a preset threshold; (2) The display condition corresponding to the second display mode includes: the duration of the weather condition indicated by the weather information is shorter than a preset duration; (3) The display condition corresponding to the third display mode includes: other weather information that does not meet the display conditions corresponding to the first display mode and the display conditions corresponding to the second display mode. Please refer to Figure 4A , Figure 4B , Figure 4C , which schematically shows three cards corresponding to the three display modes of weather information. Figure 4A This is the card corresponding to the first display mode. Figure 4B This is the card corresponding to the second display mode. Figure 4C Cards for the third display mode. By designing a dedicated display mode for each weather condition, you can provide richer visual effects. For example, the first display mode may use more vivid colors and icons to indicate hot weather, while the third display mode may use a more minimalist design to convey basic weather information.

[0105] In this embodiment, by pre-storing different display modes, the server can automatically select the most appropriate display mode according to the specific weather conditions. Different display modes are not only visually different, but also provide different content according to the actual weather information. This makes the information in the card more targeted and practical, and avoids the generalization and redundancy of information.

[0106] For example, when the temperature is higher than the preset threshold, the server can automatically select the first display mode to highlight high temperature-related life suggestions in the card, such as sun protection, hydration, etc. In this way, users can immediately obtain practical information related to current weather conditions.

[0107] For another example, when a weather condition lasts for a short period of time (such as a brief thunderstorm), the server may select a second display mode to provide simple and easy-to-understand reminder information rather than a detailed forecast.

[0108] Of course, in addition to cards, multiple display modes can also be other display effects, such as pop-up notifications or status bar notifications. Pop-up notifications will pop up a window on the screen of the user's terminal. The pop-up window can contain clear icons, colors and sound prompts to ensure that the user immediately notices the information; at least one of the icons, colors and sound prompts corresponding to different display modes. Status bar notifications display reminder messages in the form of icons or text in the status bar; different display modes have different formats of pictures or text.

[0109] The various technical features in the above embodiments can be combined arbitrarily as long as there is no conflict or contradiction between the combinations of features. However, due to space limitations, they are not described one by one. Therefore, any combination of the various technical features in the above embodiments also falls within the scope of this specification.

[0110] In some embodiments, the embodiments of this specification also provide an electronic device, including: a processor; a memory for storing processor executable instructions; wherein the processor implements any of the above methods by running the executable instructions.

[0111] Figure 5 is a schematic structural diagram of a device provided by an exemplary embodiment. Figure 5 At the hardware level, the device includes a processor 502, an internal bus 504, a network interface 506, a memory 508, and a non-volatile memory 510, and may also include hardware required for other functions. One or more embodiments of this specification may be implemented based on software, such as the processor 502 reading the corresponding computer program from the non-volatile memory 510 into the memory 508 and then running it. Of course, in addition to the software implementation, one or more embodiments of this specification do not exclude other implementations, such as logic devices or a combination of software and hardware, etc., that is, the execution subject of the following processing flow is not limited to each logic unit, but can also be hardware or logic devices.

[0112] The information push device can be used for Figure 5 The device shown in the figure is used to implement the technical solution of this specification. Among them, the information push device may include:

[0113] A life information acquisition module, used to acquire life information related to the geographical location according to the geographical location of the user terminal;

[0114] A prompt word generation module is used to embed life information into a preset prompt template to generate prompt words for use by the trained information generation model; the prompt words are used to instruct the information generation model to generate reminder information, and the reminder information includes key information extracted from the life information and / or life suggestion information generated based on the life information;

[0115] A reminder information generation module, used for inputting the reminder word into the information generation model, so that the information generation model generates the reminder information according to the instruction of the reminder word;

[0116] The reminder information push module is used to push reminder information in the user terminal.

[0117] In one implementation, the device also includes a travel intention inference module, which is used to infer whether the user to which the user terminal belongs has a travel intention within the current time period based on at least one of the historical behavior patterns and schedule information of the user to which the user terminal belongs; wherein the historical behavior pattern is obtained based on an analysis of the historical travel information of the user to which the user terminal belongs.

[0118] The prompt word generation module is specifically used to execute the step of embedding life information into a preset prompt template to generate prompt words if the user to which the user terminal belongs has a travel intention within the current time period.

[0119] In one implementation, the historical travel information of the user to which the user terminal belongs is obtained by analyzing the bill data of the travel-related bills in the user terminal, and the bill data includes at least the bill generation time and the travel mode; the historical travel information of the user to which the user terminal belongs is determined based on the changes in the geographical location of the user terminal within a historical time period; and / or the historical travel information of the user to which the user terminal belongs is determined based on the historical driving data of a vehicle that is communicated with the user terminal.

[0120] In one implementation,

[0121] The device also includes a life information comparison module, which is used to compare the currently acquired life information related to the geographic location with the life information acquired last time.

[0122] The prompt word generation module is specifically used to execute the step of embedding the currently acquired life information related to the geographic location into a preset prompt template to generate a prompt word if the difference between the two is greater than a preset difference.

[0123] In one implementation, the user terminal pre-stores multiple display modes for displaying different reminder information, and different display modes correspond to different display conditions, and different display conditions are defined based on different life contents;

[0124] The reminder information push module is specifically used to determine a target display mode from multiple display modes based on the display conditions satisfied by the life information; render the reminder information according to the target display mode, and push it in the user terminal.

[0125] In one implementation, each display mode includes a card displayed in a display interface of a user terminal; wherein the cards included in different display modes have different visual effects.

[0126] In one implementation, a designated area in a card included in the display mode is used to display life advice information in different reminder information; wherein the prompt word is also used to indicate that the number of words in the life advice information generated by the information generation model is no more than a preset threshold, and the preset threshold is positively correlated with the size of the designated area.

[0127] In one implementation, the life information includes at least weather information, and the user terminal pre-stores at least one display mode for displaying weather information:

[0128] The display conditions corresponding to the first display mode include: the temperature indicated by the weather information is greater than a preset threshold;

[0129] The display conditions corresponding to the second display mode include: the duration of the weather condition indicated by the weather information is shorter than a preset duration;

[0130] The display conditions corresponding to the third display mode include: other weather information that does not satisfy the display conditions corresponding to the first display mode and the display conditions corresponding to the second display mode.

[0131] In one implementation, the life information includes at least one of the following: weather information, traffic information, store business information, and public facility usage information.

[0132] The weather information is obtained from at least one meteorological platform based on the geographical location of the user terminal.

[0133] Traffic information is obtained from the traffic platform based on the geographical location of the user terminal.

[0134] The store business information is obtained from the store website based on the geographical location of the user terminal.

[0135] The usage information of public facilities is obtained from the public service platform based on the geographical location of the user terminal.

[0136] In one implementation, the information generation model is obtained by supervised training of a pre-trained model based on a number of prompt word samples marked with reminder information tags; different prompt word samples are obtained by embedding different life information into the preset prompt template.

[0137] The implementation process of the functions and effects of each module in the above-mentioned device is specifically described in the implementation process of the corresponding steps in the above-mentioned method, which will not be repeated here.

[0138] Based on the same concept as the above method, this specification also provides an electronic device, including: a processor; a memory for storing processor executable instructions; wherein the processor implements the steps of the method described in any of the above embodiments by running the executable instructions.

[0139] Based on the same concept as the above method, this specification also provides a computer-readable storage medium on which computer instructions are stored. When the instructions are executed by a processor, the steps of the method described in any of the above embodiments are implemented.

[0140] Computer-readable media include permanent and non-permanent, removable and non-removable media that can be used to store information by any method or technology. Information can be computer-readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, disk storage, quantum memory, graphene-based storage media or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer-readable media does not include temporary computer-readable media (transitory media), such as modulated data signals and carrier waves.

[0141] Based on the same concept as the above method, this specification also provides a computer program product, including a computer program / instruction, which implements the steps of the method described in any of the above embodiments when executed by a processor.

[0142] The above description is merely a preferred embodiment of one or more embodiments of the present specification and is not intended to limit one or more embodiments of the present specification. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of one or more embodiments of the present specification shall be included in the scope of protection of one or more embodiments of the present specification.

Claims

1. An information push method, comprising: According to the geographical location of the user terminal, obtaining life information related to the geographical location; The life information is embedded in a preset prompt template to generate prompt words for use by the trained information generation model; the prompt words are used to instruct the information generation model to generate reminder information, and the reminder information includes key information extracted from the life information and / or life suggestion information generated based on the life information; Inputting the prompt word into the information generation model, so that the information generation model generates the reminder information according to the instruction of the prompt word; The reminder information is pushed in the user terminal.

2. The method according to claim 1, The method further comprises: Inferring whether the user to which the user terminal belongs has a travel intention in the current time period based on at least one of a historical behavior pattern and schedule information of the user to which the user terminal belongs; wherein the historical behavior pattern is obtained based on an analysis of the historical travel information of the user to which the user terminal belongs; If the user to which the user terminal belongs has the intention to travel within the current time period, the step of embedding the life information into a preset prompt template to generate a prompt word is executed.

3. According to the method of claim 2, the historical travel information of the user to which the user terminal belongs is determined based on at least one of the following methods: The historical travel information of the user to which the user terminal belongs is obtained based on analyzing bill data of travel-related bills in the user terminal, the bill data at least including bill generation time and travel mode; The historical travel information of the user to which the user terminal belongs is determined based on the change of the geographical location of the user terminal within a historical time period; and The historical travel information of the user to which the user terminal belongs is determined based on the historical driving data of the vehicle that is communicatively connected to the user terminal.

4. The method according to claim 1, The method further comprises: comparing the currently acquired life information related to the geographic location with the last acquired life information; If the difference between the two is greater than the preset difference, the step of embedding the currently acquired life information related to the geographical location into a preset prompt template to generate a prompt word is performed.

5. The method according to claim 1, wherein the user terminal pre-stores a plurality of display modes for displaying different reminder information, and different display modes correspond to different display conditions, and different display conditions are defined based on different life contents; The pushing the reminder information in the user terminal includes: Determining a target display mode from the multiple display modes based on the display conditions satisfied by the life information; The reminder information is rendered according to the target display mode and pushed in the user terminal.

6. The method according to claim 5, wherein each of the display modes comprises a card displayed in a display interface of the user terminal; in, The cards included in different display modes have different visual effects.

7. The method according to claim 6, wherein the display mode includes a designated area in the card for displaying life advice information in different reminder information; in, The prompt word is also used to indicate that the number of words in the life advice information generated by the information generation model is no more than a preset threshold, and the preset threshold is positively correlated with the size of the designated area.

8. The method according to claim 5, wherein the life information at least includes weather information, and the user terminal pre-stores at least one display mode for displaying weather information: The display conditions corresponding to the first display mode include: The temperature indicated by the weather information is greater than a preset threshold; The display condition corresponding to the second display mode includes: the duration of the weather condition indicated by the weather information is shorter than a preset duration.

9. The method according to claim 1, wherein the life information includes at least one of the following: weather information, traffic information, store business information, and public facility usage information; wherein: The weather information is obtained from at least one meteorological platform based on the geographical location of the user terminal; the traffic information is obtained from a traffic platform based on the geographical location of the user terminal; the store business information is obtained from a store website based on the geographical location of the user terminal; the use information of public facilities is obtained from a public service platform based on the geographical location of the user terminal; and / or, The information generation model is obtained by supervised training of a pre-trained model based on a number of prompt word samples marked with reminder information labels; Different prompt word samples are obtained based on embedding different life information into the preset prompt template.

10. An information push device, comprising: A life information acquisition module, used to acquire life information related to the geographical location according to the geographical location of the user terminal; a prompt word generation module, used to embed the life information into a preset prompt template to generate prompt words for use by the trained information generation model; the prompt words are used to instruct the information generation model to generate reminder information, and the reminder information includes key information extracted from the life information and / or life suggestion information generated based on the life information; A reminder information generation module, used for inputting the prompt word into the information generation model, so that the information generation model generates the reminder information according to the instruction of the prompt word; The reminder information push module is used to push the reminder information in the user terminal.

11. An electronic device, comprising: processor; A memory for storing processor-executable instructions; wherein the processor implements the steps of the method according to any one of claims 1 to 9 by executing the executable instructions.

12. A computer-readable storage medium having computer instructions stored thereon, which, when executed by a processor, implement the steps of the method according to any one of claims 1 to 9.

13. A computer program product, comprising a computer program / instruction, which, when executed by a processor, implements the steps of the method according to any one of claims 1 to 9.

Images