Destination prediction method, device and terminal equipment

Abstract

The present application provides a destination prediction method, apparatus, and terminal device. The method includes: the terminal device can obtain historical navigation information, user information, calendar information, and other data from applications such as navigation software and calendar software. The terminal device can input the historical navigation information, user information, and calendar information into a destination recommendation model to calculate a prediction result. The prediction result can include at least one possible destination. The terminal device can display the prediction result on its display interface. The method of the present application improves the recommendation efficiency of the terminal device and enhances the user experience.

Description

Technical Field

[0001] The present application relates to the field of navigation, and in particular to a destination prediction method, apparatus, and terminal device. Background Art

[0002] With the continuous development of navigation technology, users' travel is becoming more and more convenient. Usually, a navigation system can be set in a vehicle's terminal equipment, such as a mobile phone, a tablet, and a computer.

[0003] In the prior art, a terminal device can obtain multiple frequently used destinations set in user information and can predict the current destination based on historical navigation information of these frequently used destinations, thereby improving user efficiency.

[0004] However, the destinations predicted by this method are limited to the range of commonly used destinations, and there is a problem of low prediction accuracy. Summary of the Invention

[0005] The present application provides a destination prediction method, apparatus, and terminal device to solve the problem of low prediction accuracy in the prior art.

[0006] In a first aspect, the present application provides a destination prediction method, comprising:

[0007] Get historical navigation information, user information and calendar information;

[0008] determining a prediction result based on the historical navigation information, the user information, and the calendar information, the prediction result including at least one possible destination;

[0009] The prediction result is displayed for the user to select a navigation destination from at least one of the possible destinations.

[0010] Optionally, determining a prediction result based on the historical navigation information, the user information, and the calendar information specifically includes:

[0011] Acquire a first destination that has appeared within a preset time period from the historical navigation information, the favorite points of the user information, the search history of the user information, and the calendar information;

[0012] determining a recommendation index for the first destination based on the data source, recording time, and matching degree of the first destination with the user preferences in the user information;

[0013] According to the recommendation indicators, a first preset number of first destinations with the largest recommendation indicators are determined to form the prediction result.

[0014] Optionally, determining the recommendation index of the first destination based on the data source, recording time, and matching degree of the first destination with the user preferences in the user information specifically includes:

[0015] determining a first indicator based on a data source of the first destination;

[0016] determining a second indicator based on the recording time of the first destination;

[0017] determining a third indicator based on a degree of matching between the first destination and the user's preferences in the user information;

[0018] Determine a recommendation index for the first destination based on the first index, the second index, and the third index.

[0019] Optionally, determining a prediction result based on the historical navigation information, the user information, and the calendar information further includes:

[0020] Determining whether the current date is a working day based on the calendar information;

[0021] If the current date is the working day, and the current time and the current location meet the preset conditions in the user information, a prediction result is determined according to the user information.

[0022] Optionally, if the current date is the working day, and the current time and current location meet the preset conditions in the user information, determining the prediction result according to the user information specifically includes:

[0023] If the current time is within the working hours set in the user information, and the distance between the current location and the home address set in the user information is less than a preset threshold, the possible destination included in the prediction result is the company address;

[0024] If the current time is within the off-duty period set in the user information, and the distance between the current location and the company address set in the user information is less than a preset threshold, the possible destination included in the prediction result is the home address.

[0025] Optionally, determining a prediction result based on the historical navigation information, the user information, and the calendar information further includes:

[0026] Based on the historical navigation information, statistics are collected to determine whether there is a travel pattern for the user;

[0027] If there is a travel pattern in the user's travel, the prediction result is determined according to the travel pattern.

[0028] Optionally, determining a prediction result based on the historical navigation information, the user information, and the calendar information further includes:

[0029] Determine whether the current date is a special holiday based on the calendar information;

[0030] If the current date is the special holiday, a second preset number of recommended destinations are selected from the recommended destinations for the special holiday in the preset guide to form the prediction result.

[0031] In a second aspect, the present application provides a destination prediction device, comprising:

[0032] Acquisition module, used to obtain historical navigation information, user information and calendar information;

[0033] A processing module is used to determine a prediction result based on the historical navigation information, the user information and the calendar information, wherein the prediction result includes at least one possible destination; and display the prediction result so that the user can select a navigation destination from at least one of the possible destinations.

[0034] Optionally, the processing module is specifically configured to:

[0035] Acquire a first destination that has appeared within a preset time period from the historical navigation information, the favorite points of the user information, the search history of the user information, and the calendar information;

[0036] determining a recommendation index for the first destination based on the data source, recording time, and matching degree of the first destination with the user preferences in the user information;

[0037] According to the recommendation indicators, a first preset number of first destinations with the largest recommendation indicators are determined to form the prediction result.

[0038] Optionally, the processing module is specifically configured to:

[0039] determining a first indicator based on a data source of the first destination;

[0040] determining a second indicator based on the recording time of the first destination;

[0041] determining a third indicator based on a degree of matching between the first destination and the user's preferences in the user information;

[0042] Determine a recommendation index for the first destination based on the first index, the second index, and the third index.

[0043] Optionally, the processing module is further configured to:

[0044] Determining whether the current date is a working day based on the calendar information;

[0045] If the current date is the working day, and the current time and the current location meet the preset conditions in the user information, a prediction result is determined according to the user information.

[0046] Optionally, the processing module is specifically configured to:

[0047] If the current time is within the working hours set in the user information, and the distance between the current location and the home address set in the user information is less than a preset threshold, the possible destination included in the prediction result is the company address;

[0048] If the current time is within the off-duty period set in the user information, and the distance between the current location and the company address set in the user information is less than a preset threshold, the possible destination included in the prediction result is the home address.

[0049] Optionally, the processing module is further configured to:

[0050] Based on the historical navigation information, statistics are collected to determine whether there is a travel pattern for the user;

[0051] If there is a travel pattern in the user's travel, the prediction result is determined according to the travel pattern.

[0052] Optionally, the processing module is further configured to:

[0053] Determine whether the current date is a special holiday based on the calendar information;

[0054] If the current date is the special holiday, a second preset number of recommended destinations are selected from the recommended destinations for the special holiday in the preset guide to form the prediction result.

[0055] In a third aspect, the present application provides a terminal device, comprising: a memory and a processor;

[0056] The memory is used to store computer programs; the processor is used to execute the destination prediction method in the first aspect and any possible design of the first aspect according to the computer programs stored in the memory.

[0057] In a fourth aspect, the present application provides a computer-readable storage medium, which stores a computer program. When at least one processor of a terminal device executes the computer program, the terminal device executes the destination prediction method in the first aspect and any possible design of the first aspect.

[0058] In a fifth aspect, the present application provides a computer program product, which includes a computer program. When at least one processor of a terminal device executes the computer program, the terminal device executes the destination prediction method in the first aspect and any possible design of the first aspect.

[0059] The destination prediction method, apparatus, and terminal device provided in the present application obtain historical navigation information, user information, calendar information, and other data from applications such as navigation software and calendar software; input the historical navigation information, user information, and calendar information into a destination recommendation model to calculate a prediction result, which may include at least one possible destination; and display the prediction result in its display interface, thereby improving the recommendation efficiency of the terminal device and enhancing the user experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0060] In order to more clearly illustrate the technical solutions in the present application or the prior art, a brief introduction will be given below to the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0061] Figure 1 A schematic diagram of a scenario of a destination prediction system provided in one embodiment of the present application;

[0062] Figure 2 A flowchart of a destination prediction method provided in one embodiment of the present application;

[0063] Figure 3 A flowchart of a destination prediction process provided by one embodiment of the present application;

[0064] Figure 4 A schematic diagram of a user data statistics process provided in one embodiment of the present application;

[0065] Figure 5 A schematic diagram of a destination recommendation provided in an embodiment of the present application;

[0066] Figure 6 A flowchart of a destination prediction process provided by one embodiment of the present application;

[0067] Figure 7 A schematic diagram of the structure of a destination prediction device provided in one embodiment of the present application;

[0068] Figure 8 A schematic diagram of the hardware structure of a terminal device provided in one embodiment of the present application. DETAILED DESCRIPTION

[0069] To make the objectives, technical solutions, and advantages of this application more clear, the technical solutions in this application will be clearly and completely described below in conjunction with the accompanying drawings. Obviously, the embodiments described are only part of the embodiments of this application, not all of them. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0070] In the specification and claims of this application, as well as in the accompanying drawings, the terms "first," "second," "third," "fourth," and the like are used to distinguish similar objects and are not necessarily used to describe a particular order or precedence. It should be understood that such terms are interchangeable where appropriate. For example, first information could be referred to as second information, and similarly, second information could be referred to as first information without departing from the scope of this disclosure.

[0071] The word "if" as used herein may be interpreted as "when" or "when" or "in response to determining," depending on the context.

[0072] Furthermore, as used herein, the singular forms "a," "an" and "the" are intended to include the plural forms as well, unless the context indicates otherwise.

[0073] It should be further understood that the terms “comprises” and “includes” indicate the existence of features, steps, operations, elements, components, items, types, and / or groups, but do not preclude the existence, occurrence, or addition of one or more other features, steps, operations, elements, components, items, types, and / or groups.

[0074] The terms "or" and "and / or" as used herein are to be interpreted as inclusive, or mean any one or any combination. Thus, "A, B, or C" or "A, B, and / or C" means "any one of the following: A; B; C; A and B; A and C; B and C; A, B, and C." An exception to this definition occurs only when a combination of elements, functions, steps, or operations are inherently mutually exclusive in some manner.

[0075] With the continuous advancement of navigation technology, travel is becoming increasingly convenient. Navigation systems are typically installed in terminal devices such as vehicle computers, mobile phones, tablets, and computers. Traditionally, users manually enter their destination in the navigation system for commuting, among other tasks. If the input is incorrect, the user may need to search again. For less popular destinations, the user may need to scroll through pages several times before finding the actual destination. The navigation system can then provide navigation based on the user's final selected destination. This manual destination selection process is often time-consuming. Performing this operation while driving can significantly impact the user's travel experience and even lead to traffic accidents. To enhance the user experience and increase the intelligence of navigation systems, conventional technologies allow terminal devices to obtain user information and historical navigation data from the navigation system. This user information may include multiple frequently used destinations. Based on these frequently used destinations and historical navigation data, the terminal device can predict the user's most likely destination at the current moment. The terminal device can then recommend this destination in the navigation system. When the recommended destination is correct, the user can more easily select it, achieving faster navigation, thereby improving the user's navigation efficiency. However, the destinations predicted by this method are limited to the range of frequently used destinations. Destination prediction can only be achieved relatively accurately when users regularly visit these frequently used destinations, resulting in a low prediction accuracy. In addition, in today's fast-paced world, users are particularly prone to forgetting special holidays, resulting in a lack of planning for special days. Special holidays can include family members' birthdays, wedding anniversaries, statutory holidays, etc. The sense of ritual of these special holidays is often very important to users in the new era. Therefore, recommending special destinations to users on these special holidays can effectively improve the user experience.

[0076] In response to the above situation, the present application proposes a destination prediction method. The present application can achieve accurate recommendations for user travel by mining data such as the user's special holidays, historical navigation information, calendar information, and user information. The present application can also be combined with commuting scenarios to improve user recommendations in different application scenarios, improve user experience, and improve destination prediction efficiency. At the same time, the improvement in the destination prediction efficiency reduces the attention consumed by users when using the navigation system in scenarios such as vehicle driving, improves the user's concentration on driving, and further reduces the incidence of traffic accidents. In the destination prediction process, the present application can also continuously update users' travel preferences and personal preferences on special holidays by mining users' special holidays and combining them with the recommended information of preset strategies, so as to achieve self-learning and optimization of user data, make destination predictions more personalized, let users experience the convenience brought by artificial intelligence, and solve the pain points brought to users by fast-paced life.

[0077] The following specific embodiments are used to describe the technical solution of the present application in detail. The following specific embodiments can be combined with each other, and the same or similar concepts or processes may not be described in detail in some embodiments.

[0078] Figure 1 A schematic diagram of a destination prediction system provided by an embodiment of the present application is shown. Figure 1 As shown, the destination prediction system may include two parts: a navigation app and a cloud. The navigation app is a navigation system installed in a terminal device. The navigation system may be installed in a vehicle computer, a mobile phone, a tablet or other device. The cloud is used to obtain historical navigation information, user information, calendar information and other data, and then use a destination recommendation algorithm to achieve destination prediction. The cloud may be installed in a remote server. The cloud may be connected to a terminal device for communication. The use of a computer program in the cloud can solve the problem of limited computing power of the terminal device in the prior art, greatly improving the time spent on destination prediction. Optionally, the destination recommendation algorithm implemented in the cloud may also be installed in the terminal device. The terminal device may directly obtain historical navigation information, user information, calendar information and other data from the navigation system therein, and then use the computer program of the destination recommendation algorithm stored in the terminal device to achieve the effect of the destination prediction. The use of a computer program in the terminal device can reduce the time loss caused by network data transmission and effectively improve the efficiency of the terminal device in obtaining data and feedback results.

[0079] like Figure 1 As shown in step S01, the navigation app can also obtain the corresponding system information from the terminal device. The system information may include user information obtained from the user module and calendar information obtained from the calendar module. The calendar information may include calendar setting points. The user information may include information such as user hobbies and special days of the user. The navigation app can also obtain historical destinations, historical routes, home and company, search history, favorites, special days and other information from its user module. Among them, special days may include birthdays, anniversaries, holidays, etc. The navigation app can integrate the information obtained from the calendar module, user module and user module of the navigation app, and upload the above data to the cloud. This step can be as follows Figure 1 As shown in S02.

[0080] The cloud device can obtain the historical destination, historical route, home and company, search history, favorites, special days and other information, and use the destination recommendation algorithm to calculate the destination prediction result. This step can be as follows Figure 1 As shown in S03 in the figure. The navigation app can also include a commuting switch. When the user turns on the commuting switch, as shown in Figure 1As shown in step S04, the prediction module of the navigation app can use the commuting recommendation algorithm to recommend home or company. Figure 1 As shown in step S05, the prediction module of the navigation app can recommend destination prediction results to the user.

[0081] In this application, the destination prediction method of the following embodiments is executed by a terminal device as the execution subject. Specifically, the execution subject can be a hardware device of the terminal device, or a software application that implements the following embodiments in the terminal device, or a computer-readable storage medium that has installed thereon the software application that implements the following embodiments, or the code that implements the software application that implements the following embodiments.

[0082] Figure 2 A flow chart of a destination prediction method provided by an embodiment of the present application is shown. Figure 1 Based on the embodiment shown, Figure 2 As shown, with the terminal device as the execution subject, the method of this embodiment may include the following steps:

[0083] S101: Acquire historical navigation information, user information, and calendar information.

[0084] In this embodiment, the terminal device can obtain historical navigation information, user information, calendar information, and other data from applications such as navigation software and calendar software. The historical navigation information may include data such as historical destinations, historical routes, home and company information. User information may include data such as the user's hobbies, favorites, and search history. Calendar information may include data such as calendar-set destinations and the user's special days.

[0085] In one example, the above information acquisition process can be implemented through navigation software of a terminal device, which can be a mobile phone, tablet, car computer, etc.

[0086] In one example, after obtaining the above information, the terminal device can invoke a computer program for a destination recommendation algorithm through an interface or other means. The computer program can be stored in the cloud. The interface can upload the above information to the cloud via a network and obtain the prediction results. Alternatively, the computer program can be stored in the terminal device. The interface can invoke the computer program locally and calculate the prediction results.

[0087] S102: Determine a prediction result based on historical navigation information, user information, and calendar information, where the prediction result includes at least one possible destination.

[0088] In this embodiment, the terminal device may input historical navigation information, user information, and calendar information into a destination recommendation model to calculate a prediction result, which may include at least one possible destination.

[0089] In one example, after determining multiple first destinations, the destination recommendation model may calculate the recommendation index of each first destination to determine the prediction result, which may be as follows:

[0090] Step 1: The terminal device obtains the first destination that appeared within a preset time period from historical navigation information, favorite points of user information, search history of user information, and calendar information.

[0091] In this step, the terminal device can obtain historical navigation information within a preset time period. The historical navigation information may include locations such as historical destinations, historical routes, and historical departure points. The locations such as historical destinations, historical routes, and historical departure points are the first destinations. The favorite points of the user information are the locations that the user clicks to favorite in the navigation software. The favorite points are the first destinations. The user information may also include the user's search history in the navigation software within the preset time period. The location corresponding to the search history is the first destination. The calendar information may also record a partial address. Usually, the record is used to remind the user to go to the corresponding address at the corresponding time. The address recorded in the calendar information is the first destination.

[0092] Optionally, in some terminal devices, to improve subsequent computational efficiency, the terminal device may perform a preliminary screening of the first destinations. To improve system computational efficiency, the terminal device may appropriately reduce the number of first destinations, thereby improving the computational efficiency of the recommendation metrics for each first destination. For example, after determining the user's current location, the terminal device may remove first destinations whose distance from the user's current location exceeds a distance threshold. The distance threshold may be an empirical value, or alternatively, the distance threshold may be determined based on the user's daily range of activities. Locations that exceed the distance threshold from the user's current location are generally considered to be less likely to be visited by the user. For another example, the terminal device may appropriately limit the number of first destinations for each data source. After the terminal device obtains information such as historical destinations, historical transit points, and historical departure points from historical navigation information over a preset period of time, it may calculate the frequency of occurrence of each location. The terminal device may select a third preset number of locations with the highest frequency of occurrence as the first destinations. After the terminal device obtains multiple locations from search records over a preset period of time, it may calculate the frequency of occurrence of each location. The terminal device may select a fourth preset number of locations with the highest frequency of occurrence as the first destinations.

[0093] Optionally, after determining multiple first destinations based on different data sources, the terminal device may consolidate these destinations. For example, the first destinations may include the east gate and west gate of Park A. These two first destinations may then be consolidated into one first destination, which may be Park A. Consolidating the first destinations can effectively improve data accuracy.

[0094] Step 2: The terminal device determines a recommendation index for the first destination based on the data source, recording time, and the degree of matching between the first destination and the user's preferences in the user information.

[0095] In this step, the effectiveness of the first destinations from different data sources must be different. For example, the historical destinations, historical routes, historical departure points, etc. in the historical navigation information are the locations that the user actually went to. The first destination in the search record may be the location that the user wants to know, but the user does not necessarily go there. It can be seen that the effectiveness of the first destination in the historical navigation information is necessarily higher than that in the search record. Therefore, the terminal device determines the effectiveness of different first destinations based on the different data sources of the first destination. Secondly, the terminal device can also obtain the user's hobbies in the user information. The terminal device can determine the possibility of the user going to the first destination based on the user's hobbies. For example, if the user likes swimming, the probability of the user going to the swimming pool will be higher than the probability of the user going to the badminton hall. The terminal device can estimate the recommendation index for each destination based on these two indicators. Specifically, the calculation process of the recommendation index may include the following:

[0096] Step 21. The terminal device determines a first indicator based on the data source of the first destination. The first indicator can be determined based on the data source. Different data sources may correspond to different parameter values. The different parameter values ​​corresponding to different data sources may be determined based on frequency of use. Alternatively, the different parameter values ​​corresponding to different data sources may be determined based on empirical values. For example, if the data source of a first destination is a historical destination, home, or company, since it is a destination that has already been visited, its parameter value can be set to 0.9 based on empirical values. Users usually add the destinations they want to visit to favorites for easier searching. Therefore, if the data source of a first destination is a favorite, it can be set to 0.7 based on empirical values. If the data source of a first destination is a search record, it is a destination that the user has viewed. Compared to favorites, these first destinations are less likely to be visited, so the parameter value of these first destinations can be set to 0.5. The parameter value of a first destination whose data source is a calendar setting point can be 0.3.

[0097] Optionally, the terminal device can also set parameter value correction values. The terminal device can count the data sources of adopted first destinations. The terminal device can appropriately adjust upwards the value of data sources with high adoption frequency. Alternatively, the terminal device can appropriately adjust downwards the value of data sources with low adoption frequency. For example, the terminal device can increase the parameter value of the data source with the highest adoption frequency by 0.1. In another example, the terminal device can decrease the parameter value of the data source with the lowest adoption frequency by 0.1. The upward and downward adjustment values ​​can be determined based on empirical values. For example, the upward adjustment value can be 0.1, 0.2, 0.3, etc. In another example, the downward adjustment value can be 0.1, 0.2, 0.3, etc. The terminal device can also determine that a data source is in a user-interested category when the adoption frequency of the data source exceeds a first frequency threshold. The terminal device can reset the parameter value of the user-interested category based on empirical values. For example, if the first destination of a calendar setting point is frequently adopted and the adoption frequency exceeds a first frequency threshold, the terminal device can determine that the data source is in a user-interested category and adjust its parameter value to 1. The first frequency threshold and the parameter value of the user-interested category can be set based on empirical values.

[0098] Optionally, the first indicator may have a value range of [0.1, 1]. That is, the first indicator is a value greater than or equal to 0.1 and less than or equal to 1. When the value of the first indicator after correction using the parameter correction value is less than 0.1, the first indicator takes a value of 0.1. When the value of the first indicator after correction using the parameter correction value is greater than 1, the first indicator takes a value of 1. Because using 0.1 as the gradient of the first indicator in calculations can better statistically analyze indicator changes, 0.1 can be used as the minimum value of the first indicator.

[0099] Step 22: The terminal device determines a second index based on the recording time of the first destination. The second index can be set based on the freshness of the recording time. That is, the closer the recording time is to the preset date, the larger the second index. For example, the second index can decrease daily within a month, with the daily decrease being 1 / 30, or approximately 0.03. For example, the preset date can be April 30th. The second index of a first destination recorded after April 30th is 1. The weight of a first destination recorded on April 29th is 29 / 30, or approximately 0.97.

[0100] Alternatively, first destinations such as home and work are typically fixed addresses that, once set, do not change. For these first destinations, using freshness to calculate their second index is not accurate. Therefore, the second index for first destinations such as home and work can be defaulted to 1.

[0101] Optionally, the value range of the second indicator can be [0.1, 1]. That is, the second indicator is a value greater than or equal to 0.1 and less than or equal to 1. When the recording time of the first destination is 30 days before the preset date and the calculated second indicator is less than 0.1, the second indicator takes a value of 0.1. For example, when the preset date is April 30 and the recording date is February 2, the second indicator takes a value of 0. When the recording time of the first destination is after the preset date and the calculated second indicator is greater than 1, the second indicator takes a value of 1. For example, when the preset date is April 30 and the recording date is May 3, the second indicator takes a value of 1. Since using 0.1 as the gradient of the second indicator in the calculation can better statistically analyze the indicator changes, 0.1 can be used as the minimum value of the second indicator.

[0102] Step 23: The terminal device determines a third indicator based on the degree of match between the first destination and the user's hobbies in the user information. This third indicator can be determined based on the degree of match with the user's hobbies. User hobbies can be personal information set by the user on the terminal device. For example, user hobbies may include running, fitness, badminton, football, basketball, bars, barbecue, etc. Based on these hobbies, the terminal device can more accurately categorize users and facilitate better destination recommendations for the user. For example, if the first destination is a certain bar, this bar meets the user's hobbies. Therefore, when the first destination is this bar, the third indicator can be the first parameter value. That is, when the first destination meets the user's hobbies, the third indicator is the first parameter value. Otherwise, when the first destination does not meet the user's hobbies, the third indicator is the second parameter value. For example, the first parameter value can be 1, and the second parameter value can be 0.1. The first and second parameter values ​​can be determined based on empirical values.

[0103] Optionally, the third indicator may have a value range of [0.1, 1]. That is, the third indicator is a value greater than or equal to 0.1 and less than or equal to 1. The third indicator may have a default value of 0.1. This default value may be determined based on empirical data. Since using 0.1 as the gradient of the third indicator in calculations can better reflect statistical changes, 0.1 may be used as the minimum value of the third indicator.

[0104] Optionally, the terminal device can also update the user's hobbies based on the user's acceptance of recommendations to adapt to the user's dynamic changes. For example, if the user's frequency of visiting a training institution exceeds a second frequency threshold, the terminal device can add the training to the user's hobbies. User hobbies can include running, fitness, badminton, football, basketball, bars, barbecue, training, etc. The second frequency threshold can be set based on experience.

[0105] Optionally, the terminal device may also set an adjustment value based on the trigger frequency of the user's hobby. The adjustment value may be set based on empirical data. The adjustment value may be 0.1, 0.2, 0.3, or the like. For example, when the trigger frequency of a user's hobby exceeds a third frequency threshold, the terminal device may use the adjustment value to adjust the user's hobby upward. The third frequency threshold may be set based on empirical data. For example, when the trigger frequency of badminton exceeds the third frequency threshold and the adjustment value is 0.2, when the first destination is a badminton hall, the terminal device may adjust its third index to 1.2. For another example, the terminal device may periodically determine the frequency of selection of each recommended location in the user's hobby. The terminal device may use the adjustment value to adjust the third index corresponding to the most frequently selected user hobby. For example, when badminton has the highest selection frequency and the adjustment value is 0.2, when the first destination is a badminton hall, the terminal device may adjust its third index to 1.2.

[0106] Step 24: The terminal device determines the recommended index for the first destination based on the first index, the second index, and the third index. Specifically, the calculation formula can be expressed as:

[0107] Recommended indicator = first indicator * second indicator * third indicator

[0108] Step 3: The terminal device determines the first destinations with the largest recommendation indexes according to the first preset number of recommendation indexes to form the prediction result. After calculating the recommendation index of each first destination, the terminal device can sort these first destinations according to these recommendation indexes. The terminal device can select the first destinations with the largest recommendation indexes according to the sorting result. The first preset number of first destinations can form the prediction result. For example, Figure 3 As shown in step S05-10, the terminal device may filter out eight first destinations with the largest recommendation indexes. As shown in step S05-11, the eight first destinations may form a prediction result and be recommended to the user by the terminal device.

[0109] In another example, the destination recommendation model may determine a prediction result based on whether the user is a regular user, and the specific steps include:

[0110] Step 4: The terminal device counts the user's travel patterns based on historical navigation information. Figure 3 As shown in step S05-5, the terminal device can classify the data types into three types: S05-6 irregular users, S05-7 partially regular users and S05-8 regular users. The three data types can be distinguished as follows: Figure 4As shown. The terminal device can obtain the second destination that appears in the historical navigation information of the user within the first preset time period. The terminal device can determine the regularity index of the user within the first preset time period based on the frequency of appearance of the second destination. For example, the first preset time period can be Monday to Friday. During the five days, the historical navigation information only includes 4 records of the user going from home to work at the company. Then the regularity index can be 4 / 5=80%. For another example, during the five days, the historical navigation information includes 5 records of going from home to work at the company and 1 record of going home from the company. Then the regularity index can be (5+1) / (5+5)=60%. That is, after the terminal device obtains multiple second destinations from the historical navigation information of the first preset time period, the terminal device can calculate the numerator of the regularity index based on the number of times each second destination appears. The terminal device can also determine the denominator of the regularity index based on the product of the number of the second destinations and the number of days in the first preset time period. The regularity index can be calculated based on the numerator and denominator. The terminal device can determine whether the user's travel patterns are regular based on the user's regularity index within the first preset time period. The terminal device may be preset with a first index threshold and a second index threshold. When the regularity index is greater than or equal to the first index threshold, the user's travel patterns are regular. When the regularity index is less than the first index threshold and greater than or equal to the second index threshold, the user's travel patterns are partially regular. When the regularity index is less than the second index threshold, the user's travel patterns are not regular. For example, the first index threshold may be 70% and the second index threshold may be 20%. For example, when a user's travel patterns are regular, the user may regularly go to work in the mornings and return home in the evenings from Monday to Friday. When a user's travel patterns are partially regular, the user may return home on Monday, Wednesday, and Friday evenings. On Tuesday and Thursday, the user may travel to different destinations. When a user's travel patterns are not regular, the user may have no repetitive behavior or only minimal repetitive behavior during the period from Monday to Friday.

[0111] Step 5: If the user's travel pattern exists, the terminal device determines the prediction result based on the travel pattern. Figure 3As shown in step S05-8, when the user's travel has a travel pattern, the terminal device can determine the prediction result based on the travel pattern. The prediction result includes a destination corresponding to the travel pattern. The terminal device can determine the historical destination of the user in the time period corresponding to the current moment in the historical navigation data based on the current moment. The historical destination is the destination corresponding to the travel pattern. For example, when the current moment is in the off-duty time period, the terminal device can count the historical destinations of the user in the off-duty time period. When one historical destination is included, the historical destination is the destination corresponding to the travel pattern. When multiple historical destinations are included, the historical destination with the highest frequency among the multiple historical destinations is the destination corresponding to the travel pattern.

[0112] Optionally, if the user's travel does not have a regular pattern, the terminal device can determine the prediction result by calculating the recommendation index in the previous example. The prediction result may include at least one possible destination. This step can be as follows: Figure 3 As shown in S05-10 and S05-11.

[0113] Optionally, if the user's travel has some travel regularity, the terminal device can further determine whether the current date is a date with travel regularity. The determination of the date can be as follows: Figure 3 As shown in S05-9 in

[15] . If the current date is a date with a travel pattern, the terminal device can determine a prediction result based on the travel pattern. Otherwise, if the current date is not a date with a travel pattern, the terminal device can determine a prediction result using the method of calculating the recommendation index in the previous example. The prediction result can include at least one possible destination.

[0114] Optionally, the terminal device can count whether there is a travel pattern on each date of the user based on historical navigation information. After obtaining the historical navigation information, the terminal device can parse the data to determine whether there is a pattern in the data. The pattern may include the presence of fixed destinations on multiple dates at preset time intervals. For example, the user may regularly go to place A on Mondays, place B on Tuesdays, place C on the first Saturday of each month, place D on the 15th of each month, and place E on the Xth day of each month. The judgment conditions for the travel pattern may include:

[0115] Step 51: The terminal device obtains multiple third destinations that appear on multiple dates within a preset time interval. For example, the terminal device may determine that all historical destinations that appear in the most recent 100 Mondays in the historical navigation information are third destinations.

[0116] Step 52: The terminal device may count the percentage of times each third destination appears during these Mondays. For example, one of the third destinations may be an office building. The terminal device may count the percentage of times that the office building appears during these 100 Mondays. If this percentage is greater than 70%, it indicates that the user visited the office building on more than 70 of these 100 Mondays. For another example, if the user visited a swimming pool 35 times during these 100 Mondays, the swimming pool's appearance percentage is 35%.

[0117] Step 53: The terminal device may obtain the highest ratio for each day. When the ratio is greater than a ratio threshold, the terminal device may determine that the multiple days in the time interval are regular. For example, when the ratio threshold is 70%, if the ratio on Monday is greater than 70%, then there is a regular pattern on that Monday. Otherwise, there is no regular pattern on that Monday.

[0118] In another example, the destination recommendation model can generate prediction results based on a preset guide when the current date is a special holiday. The specific steps include:

[0119] Step 6: The terminal device determines whether the current date is a special holiday based on the calendar information. The terminal device can collect information about special holidays related to the user through the vehicle computer or the user module in the terminal device. For example, special holidays may include family members' birthdays, wedding anniversaries, and other commemorative dates. Special holidays may also include Valentine's Day, Chinese Valentine's Day, Father's Day, Mother's Day, Women's Day, Children's Day, and other holidays.

[0120] Step 7: If the current date is a special holiday, the terminal device selects a second preset number of recommended destinations from the recommended destinations for special holidays in the preset guide to form a prediction result. The terminal device may store recommended destinations for special holidays. The recommended destinations may be as follows: Figure 5 For example, when the special holiday is Father's Day, the destination can be the parents' residence. When the special holiday is a wedding anniversary, the destination can be a flower shop, a cosmetics store, a hotel, etc. The terminal device can select a second preset number of recommended destinations from the preset guide according to the special holiday determined in step 6. This step can be as follows Figure 3 As shown, when S05-2 determines that the current date is a special holiday (special day), the terminal device can continue to execute steps S05-3 and S05-4. Optionally, the terminal device can also update the preset strategy according to the user's selection or the user's actual destination.

[0121] In another example, the destination recommendation model may determine whether to enable commuting mode by determining whether the current date is a weekday, thereby determining a prediction result based on the commuting mode on weekdays. The specific steps may include:

[0122] Step 8: The terminal device determines whether the current date is a working day based on the calendar information. Optionally, before executing this step, the terminal device may also Figure 3 As shown in S05-1, it is first determined whether the commuting switch in the terminal device is turned on. When the commuting switch is turned on, the terminal device can execute step S5-13. That is, when the commuting switch is turned on, the terminal device can continue to execute the above step 8 to determine whether the current date is a weekday.

[0123] Step 9: If the current date is a weekday and the current time and current location meet the preset conditions in the user information, the terminal device determines the prediction result based on the user information. After determining that the current date is a weekday, the terminal device can further determine the current time and current location to determine whether the user needs to go to the company or go home. Specifically, the judgment process may include:

[0124] Step 91: If the current time is during the working hours set by the user information, and the distance between the current location and the home address set by the user information is less than a preset threshold, the possible destination included in the prediction result is the company address. For example, the working hours may include 7 o'clock to 10 o'clock. The working hours can be set by the user. When it is during the working hours and the user is near home, it means that the user needs to go to the company to work. If it is currently during the working hours, but the user is not near home, it means that the user may be on a business trip and does not need to go to the company. For example, if Figure 6 As shown in steps S04-2 and S04-6, when the current time is between 6:00 and 10:30 and the current position (vehicle position) is within 1 km from home, the destination determined by the terminal device is the company.

[0125] Step 92: If the current time is during the off-duty period set by the user information, and the distance between the current location and the company address set by the user information is less than a preset threshold, the possible destination included in the prediction result is the home address. For example, the off-duty period may include 17:00 to 20:00. The off-duty period can be set by the user. When it is during the off-duty period and the user is near the company, it means that the user needs to go home after get off work. If it is currently during the off-duty period, but the user is not near the company, it means that the user may be out on business, and his or her off-duty period may change. For example, Figure 6 As shown in steps S04-3 and S04-5, when the current time is between 17:00 and 00:00 and the current position (vehicle position) is within 1 km from the company, the destination determined by the terminal device is home.

[0126] Step 93: When the terminal device determines that the above two steps are not met, the terminal device may maliciously not execute the recommendation. Figure 6 As shown in step S04-4

[0127] S103: Display the prediction result so that the user can select a navigation destination from at least one possible destination.

[0128] In this embodiment, the terminal device may display the prediction results on its display interface. When the prediction results include only one destination, the terminal device may directly plan a navigation route in the navigation software based on the prediction results. After completing the planning of the navigation route, the terminal device may ask the user whether to start navigation. When the prediction results include multiple destinations, the terminal device may display the multiple destinations on the display interface of the navigation software and ask the user to select one of the destinations. Once the user selects one of the destinations, the terminal device will begin planning the navigation route based on the destination.

[0129] The destination prediction method provided in this application allows a terminal device to obtain historical navigation information, user information, calendar information, and other data from applications such as navigation software and calendar software. The terminal device can input the historical navigation information, user information, and calendar information into a destination recommendation model to calculate a prediction result. The prediction result may include at least one possible destination. The terminal device can display the prediction result on its display interface. In this application, through this destination prediction method, destinations can be pushed to users more quickly and accurately, improving the recommendation efficiency of the terminal device and enhancing the user experience.

[0130] Figure 7 A schematic diagram of the structure of a destination prediction device provided by an embodiment of the present application is shown. Figure 7 As shown, the destination prediction device 10 of this embodiment is used to implement the operations corresponding to the terminal device in any of the above method embodiments. The destination prediction device 10 of this embodiment includes:

[0131] The acquisition module 11 is used to acquire historical navigation information, user information and calendar information.

[0132] The processing module 12 is configured to determine a prediction result based on historical navigation information, user information, and calendar information, wherein the prediction result includes at least one possible destination, and display the prediction result for the user to select a navigation destination from the at least one possible destination.

[0133] In one example, the processing module 12 is specifically configured to:

[0134] The first destination that appeared within a preset time period is obtained from historical navigation information, favorite points of user information, search history of user information, and calendar information.

[0135] The recommendation index of the first destination is determined based on the data source, recording time and matching degree of the first destination with the user preferences in the user information.

[0136] According to the recommendation indicators, a first destination having a maximum first preset number of recommendation indicators is determined to form a prediction result.

[0137] In one example, the processing module 12 is specifically configured to:

[0138] A first indicator is determined based on a data source of the first destination.

[0139] A second indicator is determined based on the recording time of the first destination.

[0140] The third indicator is determined according to the degree of matching between the first destination and the user preferences in the user information.

[0141] Determine the recommended index for the first destination based on the first index, the second index and the third index.

[0142] In one example, the processing module 12 is further configured to:

[0143] Determines whether the current date is a weekday based on calendar information.

[0144] If the current date is a weekday and the current time and current location meet the preset conditions in the user information, the prediction result is determined based on the user information.

[0145] In one example, the processing module 12 is specifically configured to:

[0146] If the current time is during the working hours set in the user information, and the distance between the current location and the home address set in the user information is less than a preset threshold, the possible destination included in the prediction result is the company address.

[0147] If the current time is during the off-get off work period set in the user information, and the distance between the current location and the company address set in the user information is less than a preset threshold, the possible destination included in the prediction result is the home address.

[0148] In one example, the processing module 12 is further configured to:

[0149] Based on historical navigation information, statistics are collected to see whether there is a travel pattern in the user's travel.

[0150] If there is a travel pattern for the user, the prediction result is determined based on the travel pattern.

[0151] In one example, the processing module 12 is further configured to:

[0152] Based on the calendar information, determine whether the current date is a special holiday.

[0153] If the current date is a special holiday, a second preset number of recommended destinations are selected from the recommended destinations for special holidays in the preset travel guide to form the prediction result.

[0154] The destination prediction device 10 provided in the embodiment of the present application can execute the above method embodiment. Its specific implementation principles and technical effects can be found in the above method embodiment, and this embodiment will not be repeated here.

[0155] Figure 8 FIG1 shows a hardware structure diagram of a terminal device provided in an embodiment of the present application. Figure 8 As shown, the terminal device 20 is used to implement the operations corresponding to the terminal device in any of the above method embodiments. The terminal device 20 of this embodiment may include: a memory 21 and a processor 22.

[0156] Memory 21 is used to store computer programs. Memory 21 may include high-speed random access memory (RAM) or non-volatile memory (NVM), such as at least one disk memory. It may also be a USB flash drive, a mobile hard drive, a read-only memory, a magnetic disk, or an optical disk.

[0157] The processor 22 is used to execute the computer program stored in the memory to implement the destination prediction method in the above embodiment. For details, please refer to the relevant description in the above method embodiment. The processor 22 can be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), etc. The general-purpose processor can be a microprocessor or the processor can be any conventional processor, etc. The steps of the method disclosed in the present invention can be directly implemented as a hardware processor, or can be implemented by a combination of hardware and software modules in the processor.

[0158] Optionally, the memory 21 may be independent or integrated with the processor 22 .

[0159] When the memory 21 is a device independent of the processor 22, the terminal device 20 may further include a bus 23. The bus 23 is used to connect the memory 21 and the processor 22. The bus 23 may be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus. Buses can be divided into address buses, data buses, control buses, etc. For ease of illustration, the buses in the drawings of this application are not limited to only one bus or one type of bus.

[0160] The terminal device provided in this embodiment can be used to execute the above-mentioned destination prediction method. Its implementation method and technical effects are similar and will not be described in detail in this embodiment.

[0161] The present application also provides a computer-readable storage medium, in which a computer program is stored. When the computer program is executed by a processor, it is used to implement the methods provided in the various embodiments described above.

[0162] Among them, the computer-readable storage medium can be a computer storage medium or a communication medium. The communication medium includes any medium that facilitates the transmission of a computer program from one place to another. The computer storage medium can be any available medium that can be accessed by a general-purpose or special-purpose computer. For example, a computer-readable storage medium is coupled to a processor so that the processor can read information from the computer-readable storage medium and write information to the computer-readable storage medium. Of course, the computer-readable storage medium can also be an integral part of the processor. The processor and the computer-readable storage medium can be located in an application-specific integrated circuit (ASIC). In addition, the ASIC can be located in a user device. Of course, the processor and the computer-readable storage medium can also exist in a communication device as discrete components.

[0163] Specifically, the computer-readable storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random-access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic storage, flash memory, magnetic disk or optical disk. The storage medium can be any available medium that can be accessed by a general-purpose or special-purpose computer.

[0164] The present application also provides a computer program product, comprising a computer program stored in a computer-readable storage medium. At least one processor of a device can read the computer program from the computer-readable storage medium, and at least one processor executes the computer program so that the device implements the methods provided in the various embodiments described above.

[0165] An embodiment of the present application also provides a chip, which includes a memory and a processor, the memory is used to store computer programs, and the processor is used to call and run the computer programs from the memory, so that a device equipped with the chip executes the methods in various possible implementation modes as described above.

[0166] In the several embodiments provided in this application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of modules is only a logical function division. In actual implementation, there may be other division methods, such as multiple modules can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or modules, which can be electrical, mechanical or other forms.

[0167] The modules may be physically separate, for example, installed in different locations on a single device, or installed on different devices, or distributed across multiple network units, or distributed across multiple processors. The modules may also be integrated, for example, installed in the same device, or integrated into a set of codes. The modules may exist in the form of hardware, or in the form of software, or may be implemented in the form of software plus hardware. The present application may select some or all of the modules according to actual needs to achieve the purpose of the present embodiment.

[0168] When each module is implemented as an integrated module in the form of a software function module, it can be stored in a computer-readable storage medium. The above-mentioned software function module is stored in a storage medium and includes a number of instructions for causing a computer device (which can be a personal computer, server, or network device, etc.) or a processor to perform some steps of the methods of each embodiment of the present application.

[0169] It should be understood that, although the various steps in the flowcharts of the above embodiments are shown in sequence as indicated by the arrows, these steps are not necessarily performed in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order restriction on the execution of these steps, and they may be performed in other orders. Moreover, at least a portion of the steps in the figure may include multiple sub-steps or multiple stages, and these sub-steps or stages are not necessarily performed at the same time, but may be performed at different times, and their execution order is not necessarily sequential, but may be performed in turn or alternately with other steps or at least a portion of sub-steps or stages of other steps.

[0170] Finally, it should be noted that the above embodiments are intended only to illustrate the technical solutions of this application and are not intended to limit them. Although this application has been described in detail with reference to the aforementioned embodiments, those skilled in the art will appreciate that they may modify the technical solutions described in the aforementioned embodiments or replace some or all of the technical features therein with equivalents. However, such modifications or replacements do not deviate from the essence of the corresponding technical solutions within the scope of the various embodiments of this application.

Claims

1. A destination prediction method, characterized in that: The method comprises: Acquiring historical navigation information, user information, and calendar information; the user information includes at least one of favorites, search history, and user preferences; and the calendar information includes at least one of calendar-set destinations and special holiday information; determining a first destination that has appeared within a preset time period based on the historical navigation information, the user information, and the calendar information, and determining a recommendation index for the first destination; Determining, based on the recommendation indicators, a first preset number of first destinations having the largest recommendation indicators to form a prediction result; the prediction result includes at least one possible destination; displaying the prediction result so that the user can select a navigation destination from at least one of the possible destinations; The determining of the recommendation index for the first destination includes: determining a first indicator based on a data source of the first destination; the data source comprising at least one of historical navigation data, favorite points, search records, and calendar settings; determining a second indicator based on the recording time of the first destination; determining a third indicator based on a degree of matching between the first destination and the user's preferences in the user information; Determine a recommendation index for the first destination based on the first index, the second index, and the third index.

2. The method according to claim 1, characterized in that The determining, based on the historical navigation information, the user information, and the calendar information, of a first destination that has appeared within a preset time period and determining a recommendation index for the first destination specifically includes: Acquire a first destination that has appeared within a preset time period from the historical navigation information, the favorite points of the user information, the search history of the user information, and the calendar information; The recommendation index of the first destination is determined according to the data source, recording time and matching degree of the first destination with the user preferences in the user information.

3. The method according to claim 1, characterized in that Before determining, based on the recommendation indicators, a first preset number of first destinations having the largest recommendation indicators to form a prediction result, the method further includes: Determining whether the current date is a working day based on the calendar information; If the current date is the working day, and the current time and the current location meet the preset conditions in the user information, a prediction result is determined according to the user information.

4. The method according to claim 3, characterized in that If the current date is the working day, and the current time and the current location meet the preset conditions in the user information, determining a prediction result based on the user information specifically includes: If the current time is within the working hours set in the user information, and the distance between the current location and the home address set in the user information is less than a preset threshold, the possible destination included in the prediction result is the company address; If the current time is within the off-duty period set in the user information, and the distance between the current location and the company address set in the user information is less than a preset threshold, the possible destination included in the prediction result is the home address.

5. The method according to claim 1, wherein Before determining, based on the recommendation indicators, a first preset number of first destinations having the largest recommendation indicators to form a prediction result, the method further includes: Based on the historical navigation information, statistics are collected to determine whether there is a travel pattern for the user; If the user's travel has a travel pattern, determining the prediction result according to the travel pattern; If there is no travel pattern for the user, the first destination that has appeared within a preset time period is determined based on the historical navigation information, the user information and the calendar information, and the recommendation index of the first destination is determined; based on the recommendation index, the first destination with the largest first preset number of recommendation indexes is determined to form a prediction result.

6. The method according to claim 1, characterized in that Before determining, based on the recommendation indicators, a first preset number of first destinations having the largest recommendation indicators to form a prediction result, the method further includes: Determine whether the current date is a special holiday based on the calendar information; If the current date is the special holiday, a second preset number of the recommended destinations are selected from the recommended destinations for the special holiday in a preset strategy to form the prediction result, wherein the preset strategy is a user's regular destination recommendation strategy for special holidays and a recommendation strategy based on an algorithm that prefers novelty over oldness; If the current date is not the special holiday, counting whether there is a travel pattern for the user's travel based on the historical navigation information; If the user's travel has a travel pattern, determining the prediction result according to the travel pattern; If there is no travel pattern for the user, the first destination that has appeared within a preset time period is determined based on the historical navigation information, the user information and the calendar information, and the recommendation index of the first destination is determined; based on the recommendation index, the first destination with the largest first preset number of recommendation indexes is determined to form a prediction result.

7. A destination prediction device, characterized in that: The device comprises: an acquisition module, configured to acquire historical navigation information, user information, and calendar information; the user information including at least one of favorite points, search history, and user preferences; and the calendar information including at least one of calendar-set destinations and special holiday information; a processing module configured to determine, based on the historical navigation information, the user information, and the calendar information, first destinations that have appeared within a preset time period, and determine a recommendation index for the first destination; determine, based on the recommendation index, a first preset number of first destinations with the largest recommendation indexes to form a prediction result, the prediction result including at least one possible destination; and display the prediction result for the user to select a navigation destination from the at least one possible destination; The processing module is specifically used to determine a first indicator based on the data source of the first destination; determine a second indicator based on the recording time of the first destination; determine a third indicator based on the degree of matching between the first destination and the user's preferences in the user information; determine a recommendation indicator for the first destination based on the first indicator, the second indicator and the third indicator; the data source includes at least one of historical navigation data, favorite points, search records and calendar setting points.

8. A terminal device, characterized in that: The device includes: a memory and a processor; The memory is used to store a computer program; the processor is used to implement the destination prediction method according to any one of claims 1 to 6 according to the computer program stored in the memory.

9. A computer-readable storage medium, characterized in that The computer-readable storage medium stores a computer program, which, when executed by a processor, is used to implement the destination prediction method according to any one of claims 1 to 6.

10. A computer program product, characterized in that The computer program product comprises a computer program, and when the computer program is executed by a processor, the destination prediction method according to any one of claims 1 to 6 is implemented.

Images