Navigation interaction method and device, electronic equipment, storage medium and program product

Abstract

The invention relates to a navigation interaction method and device, electronic equipment, a storage medium and a program product. Comprising the steps that in response to a voice navigation instruction initiated by a user, a navigation instruction text recognized from the voice navigation instruction is obtained, and the navigation instruction text comprises a place description text; acquiring a historical navigation record, related to the navigation instruction text, of the user; acquiring a navigation preference text of the user; performing text generation according to the navigation instruction text, the historical navigation record and the navigation preference text to obtain a navigation recommendation statement for navigating to a recommended navigation site related to the site description text; outputting the navigation recommendation statement; and in response to a received voice confirmation instruction of the user for the navigation recommendation statement, navigating by taking the recommended navigation place as a navigation destination. The method can improve the navigation efficiency.

Description

Technical Field

[0001] This application relates to the field of intelligent driving technology, and in particular to a navigation interaction method, device, electronic device, storage medium, and computer program product. Background Technology

[0002] With the development of intelligent driving technology, in-vehicle navigation systems are becoming increasingly intelligent. An in-vehicle navigation system is a system inside a vehicle used to provide users with route planning, navigation guidance, and real-time traffic information.

[0003] In traditional technology, in-vehicle navigation systems can display candidate routes or destinations on the map displayed on the vehicle's screen based on the user's operations on the screen, and can interact with the user through the screen to determine the navigation destination or route.

[0004] However, traditional navigation interaction methods that rely on the vehicle's infotainment screen usually require multiple interactions between the user and the screen, which is complex and time-consuming, resulting in low navigation efficiency. Summary of the Invention

[0005] Therefore, it is necessary to provide a navigation interaction method, device, electronic device, storage medium, and program product that can improve navigation efficiency in response to the above-mentioned technical problems.

[0006] On one hand, this application provides a navigation interaction method, comprising: in response to a user-initiated voice navigation command, acquiring navigation command text identified from the voice navigation command, the navigation command text including location description text; acquiring the user's historical navigation records related to the navigation command text; acquiring the user's navigation preference text; generating text based on the navigation command text, the historical navigation records, and the navigation preference text to obtain a navigation recommendation statement for navigating to a recommended navigation location related to the location description text; outputting the navigation recommendation statement; and in response to receiving a user's voice confirmation command for the navigation recommendation statement, navigating with the recommended navigation location as the navigation destination.

[0007] On the other hand, this application also provides a navigation interaction device, comprising: a navigation instruction processing module, configured to, in response to a user-initiated voice navigation instruction, acquire navigation instruction text recognized from the voice navigation instruction, the navigation instruction text including location description text; a navigation record acquisition module, configured to acquire the user's historical navigation records related to the navigation instruction text; a preference text acquisition module, configured to acquire the user's navigation preference text; a recommendation statement acquisition module, configured to, based on the navigation instruction text, the historical navigation records, and the navigation preference text, generate text to obtain a navigation recommendation statement for navigating to a recommended navigation location related to the location description text; a recommendation statement output module, configured to output the navigation recommendation statement; and a navigation execution module, configured to, in response to receiving a user's voice confirmation instruction for the navigation recommendation statement, perform navigation with the recommended navigation location as the navigation destination.

[0008] In some embodiments, the recommendation statement acquisition module is further configured to generate a reference statement for indicating navigation recommendations based on the navigation instruction text, the historical navigation records, and the navigation preference text; and to generate text based on the reference statement to obtain a navigation recommendation statement for navigating to a recommended navigation location related to the location description text.

[0009] In some embodiments, the recommendation statement acquisition module is further configured to determine the historical destination indicated by the historical navigation record; query the real-time information of the historical destination; and generate a reference statement for indicating navigation recommendations based on the navigation instruction text, the historical navigation record, the navigation preference text, and the real-time information of the historical destination.

[0010] In some embodiments, the recommendation statement acquisition module is further configured to determine at least one keyword related to the historical destination; and query real-time information of the historical destination that is related to the at least one keyword respectively.

[0011] In some embodiments, the recommendation statement acquisition module is further configured to acquire real-time driving data of the vehicle when the voice navigation command is generated during vehicle operation; and generate a reference statement for indicating navigation recommendations based on the navigation command text, the historical navigation records, the navigation preference text, and the real-time driving data.

[0012] In some embodiments, the recommended statement acquisition module is further configured to generate text based on the reference statement to obtain an initial statement for navigating to a recommended navigation location related to the location description text; and to perform linguistic correction on the initial statement to obtain a navigation recommendation statement for navigating to a recommended navigation location related to the location description text.

[0013] In some embodiments, there are multiple navigation recommendation statements. The recommendation statement output module is further configured to generate multiple navigation recommendation statements using the reference statement, select one navigation recommendation statement from the multiple navigation recommendation statements, and output the selected navigation recommendation statement; in response to receiving a voice rejection instruction from the user for the navigation recommendation statement, it outputs one navigation recommendation statement that has not been selected from the multiple navigation recommendation statements.

[0014] In some embodiments, the historical navigation records are selected from the user's historical navigation record set. The device further includes a set update module, which is configured to generate historical navigation records for each output navigation recommendation statement based on the response instruction to the navigation recommendation statement and the navigation data in the navigation recommendation statement; and add the generated historical navigation records to the historical navigation record set to update the historical navigation record set.

[0015] In some embodiments, the navigation execution module is further configured to output at least one route option with the navigation destination as the endpoint, based on the navigation destination; receive a voice selection instruction from the user for a target route option among the at least one route options, and navigate using the route indicated by the target route option as the navigation route.

[0016] In some embodiments, the device further includes a route change module, which is configured to, during navigation with the recommended navigation location as the navigation destination, output a voice-based route adjustment command when it is determined that the navigation route needs to be changed; and when a voice confirmation command for the route change command is received, switch to navigation according to the adjusted navigation route indicated by the route adjustment command.

[0017] In some embodiments, the navigation record acquisition module is further configured to vectorize the navigation instruction text to generate a query vector; determine multiple historical navigation records of the user, and determine multiple historical vectors obtained by vectorizing the multiple historical navigation records respectively; and determine the historical navigation record related to the navigation instruction text from the multiple historical navigation records based on the vector similarity between the multiple historical vectors and the query vector respectively.

[0018] In some embodiments, the apparatus further includes a preference text generation module for generating navigation preference text, the preference text generation module being configured to obtain at least a portion of the historical navigation records from the user's historical navigation record set; analyze the at least a portion of the historical navigation records; and generate the navigation preference text.

[0019] On the other hand, this application also provides an electronic device, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps in the above-described navigation interaction method.

[0020] On the other hand, this application also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps in the above-described navigation interaction method.

[0021] On the other hand, this application also provides a computer program product, including a computer program that, when executed by a processor, implements the steps in the above-described navigation interaction method.

[0022] The aforementioned navigation interaction method, device, electronic device, computer-readable storage medium, and computer program product, in response to a user-initiated voice navigation command, acquire navigation command text recognized from the voice navigation command. This navigation command text includes location description text. The system also acquires the user's historical navigation records related to the navigation command text and the user's navigation preference text. Since both historical navigation records and navigation preference text reflect the user's navigation preferences, text generation based on the navigation command text, historical navigation records, and navigation preference text yields a navigation recommendation statement that navigates to a recommended navigation location related to the location description text. This approach aims to obtain navigation recommendation statements that best meet the user's needs, thereby increasing the likelihood of receiving the user's voice confirmation command for the navigation recommendation statement, accelerating the determination of the navigation destination, and improving navigation efficiency. Furthermore, since the user interacts via voice, navigation efficiency is further improved compared to operating a screen. Attached Figure Description

[0023] To more clearly illustrate the technical solutions in the embodiments of this application or related technologies, the drawings used in the description of the embodiments of this application or related technologies will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0024] Figure 1A This is a diagram illustrating the application environment of the navigation interaction method in some embodiments;

[0025] Figure 1B This is a diagram illustrating the application environment of the navigation interaction method in some embodiments;

[0026] Figure 2 This is a flowchart illustrating the navigation interaction method in some embodiments;

[0027] Figure 3 This is a diagram illustrating the application environment of the navigation interaction method in some embodiments;

[0028] Figure 4 A schematic diagram illustrating the principle of generating navigation recommendation statements in some embodiments;

[0029] Figure 5 This is a schematic diagram of the navigation interaction method in some embodiments;

[0030] Figure 6 This is a schematic diagram of the navigation interaction method in other embodiments;

[0031] Figure 7 This is a diagram illustrating application scenarios of the navigation interaction method in some embodiments;

[0032] Figure 8 Here are some structural block diagrams of the navigation interaction device in some embodiments;

[0033] Figure 9 These are internal structural diagrams of electronic devices in some embodiments;

[0034] Figure 10 This is a diagram of the internal structure of an electronic device in some other embodiments. Detailed Implementation

[0035] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0036] The navigation interaction method provided in this application embodiment can be applied to, for example, Figure 1AThe application environment shown includes a vehicle containing a navigation device 102. This environment may also include a server 104 and a data storage system. The vehicle can be any type of vehicle, such as a passenger car, bus, truck, or tractor-trailer; it can be a sedan, SUV, truck, or bus; it can be a gasoline-powered vehicle or a new energy vehicle; and it can be a driverless, autonomous, semi-autonomous, or non-autonomous vehicle. The navigation device 102 provides navigation services to the vehicle. For example, the navigation device 102 can be an in-vehicle device with an in-vehicle navigation system, such as a car infotainment system. The navigation device 102 can communicate with the server 104 via a network. The data storage system can store the data that the navigation device 102 and the server 104 need to process. The data storage system can be, for example, a database. The data storage system can be integrated on the server 104 or located on the cloud or other network servers. The server 104 can be a standalone physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server providing cloud computing services. Cloud servers are used to provide basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, CDN (Content Delivery Network), and big data and artificial intelligence platforms. Navigation device 102 and server 104 can be connected directly or indirectly via wired or wireless communication, which is not limited herein.

[0037] The navigation interaction method provided in this application can be jointly executed by the navigation device 102 and the server 104. Specifically, as shown in the example... Figure 1AAs shown, the data storage system stores a user's historical navigation record set and navigation preference text. Navigation device 102 receives voice navigation commands initiated by the user, identifies the navigation command text from the voice commands, and determines the historical navigation records related to the navigation command text from the user's historical navigation record set stored in the data storage system. Navigation device 102 can also obtain the user's navigation preference text from the data storage system. This navigation preference text can be generated based on at least a portion of the historical navigation records in the historical navigation record set. Navigation device 102 can also send the navigation command text, the historical navigation records related to the navigation command text, and the navigation preference text to server 104. Server 104 generates a navigation recommendation statement based on the navigation command text, the historical navigation records related to the navigation command text, and the navigation preference text. Server 104 can return the generated navigation recommendation statement to navigation device 102. Navigation device 102 receives the navigation recommendation statement returned by server 104 and outputs the navigation recommendation statement. After receiving a voice response command for the navigation recommendation statement, if the voice response command is determined to be a voice confirmation command, navigation device 102 will proceed with navigation according to the recommended navigation location suggested in the navigation recommendation statement. The navigation preference text can be updated. The generation and updating of the navigation preference text can be performed by the server 104. The navigation device 102 can collect historical navigation records and store them in the historical navigation record set in the data storage system to update the historical navigation record set.

[0038] Of course, the navigation method provided in this application can also be executed by the navigation device 102. For example... Figure 1BAs shown, navigation device 102 can determine historical navigation records related to navigation command text from the data storage system and obtain the user's navigation preference text. Based on the navigation command text, the historical navigation records related to the navigation command text, and the navigation preference text, it generates and outputs navigation recommendation statements. When a voice reply command is received for the navigation recommendation statement, and the voice reply command is a voice confirmation command, navigation is performed according to the recommended navigation location in the navigation recommendation statement. The navigation preference text can be updated, and the generation and updating of the navigation preference text can be performed by navigation device 102. Navigation device 102 may contain an edge computing module, which can process and analyze the user's historical navigation records and other types of data, such as real-time traffic data or current environmental data, in real time. Navigation device 102 can also generate navigation recommendation statements through the edge computing module; for example, it can generate navigation recommendation statements based on a large model running on an edge computing model. The introduction of edge computing can reduce data transmission latency, improve response speed, and enhance the stability and reliability of navigation device 102 in high-traffic areas. The navigation device 102 can respond to navigation commands in real time and output navigation recommendations, providing more efficient navigation services and achieving lower network dependence. The Large Model (LM) refers to a deep learning model trained on a large amount of data, capable of understanding and generating natural language text. It possesses strong contextual understanding and generation capabilities and can be applied to speech recognition tasks and natural language processing fields such as natural language generation. Natural Language Processing (NLP) is a field of computer science that involves computers' understanding, generation, and response to human natural language. Natural Language Generation (NLG) is a subfield of NLP that involves the process of computers generating natural language text to mimic human language expression.

[0039] In some embodiments, such as Figure 2 As shown, a navigation interaction method is provided. This method can be executed by the navigation device 102, or it can be jointly executed by the navigation device 102 and the server 104. This method is applied to... Figure 1A Taking the navigation device 102 in the vehicle as an example, the explanation includes the following steps 202 to 212. Wherein:

[0040] Step 202: In response to the user-initiated voice navigation command, obtain the navigation command text recognized from the voice navigation command. The navigation command text includes location description text.

[0041] Among these, navigation devices can support intelligent voice interaction. Intelligent voice interaction (IVI) is an interaction method that allows communication with intelligent devices through voice commands. The device uses voice recognition technology to understand the user's needs and provide corresponding feedback.

[0042] Location description text is text that describes a location; it can also be understood as text related to a location. Examples of location description text include "tourist attraction," "office," or "A Square." Voice navigation commands can be voice commands that navigate to the location described in the location description text. For example, voice navigation commands could be "navigate to office," "navigate to tourist attraction," or "navigate to the nearest A Square." It's important to understand that the location described in the location description text is not necessarily a unique location. For example, with the location description text "A Square," there could be multiple "A Squares" in different areas of a city. Of course, the location described in the location description text can also be a unique location, for example, "Great Wall of Beijing."

[0043] Specifically, navigation devices can utilize speech recognition technology to convert voice navigation commands into text, thus obtaining the navigation command text. For example, a navigation system may include a voice assistant that provides speech recognition technology, allowing the user to obtain the navigation command text.

[0044] Step 204: Obtain the user's historical navigation records related to navigation instruction text.

[0045] Historical navigation records, also known as Historical Navigation Data (HND), are records generated by a user while using a navigation device. These records may include at least one of the following: origin, destination, route used, departure time, or arrival time. Historical navigation records can be stored on the navigation device or synchronized to the cloud via the user's account. At least one historical navigation record related to navigation instructions can be retrieved from the user.

[0046] Specifically, the navigation device can identify the user who initiated the voice navigation command. After identifying the user, it retrieves the user's historical navigation records related to the navigation command text. From the user's historical navigation record set, it identifies at least one historical navigation record related to the navigation command text.

[0047] In some embodiments, the navigation device or data storage system may store a set of the user's historical navigation records, and the navigation device may search for historical navigation records related to navigation instruction text from the set of the user's historical navigation records.

[0048] In some embodiments, to identify a user, the navigation device performs voiceprint recognition on navigation commands to obtain a voiceprint recognition result; and determines the user who issued the navigation command based on the voiceprint recognition result. Specifically, the navigation device may support voiceprint recognition. The navigation device may collect the user's voiceprint features and store the collected user's voiceprint features locally or in a data storage system. The navigation device may collect and store the voiceprint features of multiple different users. The navigation device may calculate the similarity between the voiceprint recognition result and the stored voiceprint features, and identify the user whose voiceprint feature has the highest similarity as the user. By using voiceprint recognition to identify users, the efficiency of user identification is improved, thereby further improving navigation efficiency.

[0049] Step 206: Obtain the user's navigation preference text.

[0050] Navigation preference text is text used to describe a user's navigation preferences. It can reflect frequently visited destinations, common departure times, or frequently used routes.

[0051] Specifically, navigation preference text can be text generated based on some or all of the user's historical navigation records. To generate navigation preference text, the navigation device can analyze some or all of the historical navigation records to obtain at least one key navigation information for the user. This key navigation information may include, but is not limited to, information describing the user's frequently visited destinations, frequently departing times, or frequently used routes. The navigation device can then generate the user's navigation preference text based on this at least one key navigation information.

[0052] Step 208: Generate text based on navigation instruction text, historical navigation records, and navigation preference text to obtain navigation recommendation statements that navigate to recommended navigation locations related to the location description text.

[0053] The navigation recommendation statement is a statement used to make navigation recommendations. This statement can be in the form of an inquiry or suggestion; this application does not limit the format of the navigation recommendation statement. The navigation recommendation statement can describe recommended locations and also describe the real-time information available at those locations.

[0054] Recommended navigation locations refer to the locations suggested in navigation recommendations and are related to the locations described in the location description text. Recommended navigation locations can be determined based on historical navigation records associated with the navigation instruction text. For example, destinations recorded in historical navigation records can be used as recommended navigation locations. For instance, if the navigation instruction text is "Navigate to the office," and "office" is the location description text, and the historical navigation record indicates an office in the central business district, then the navigation recommendation text would be, for example, "Please confirm if you are going to an office in the central business district?" Navigation recommendation texts can also include route-related phrases. For example, the navigation recommendation text could be, "Please confirm if you are going to an office in the central business district? I have planned the shortest route for you.", where "I have planned the shortest route for you" is the route-related phrase.

[0055] The process of generating navigation recommendations based on voice navigation commands can be understood as a user intent recognition process. User Intent Recognition (UIR) is a natural language processing technology used to analyze and understand user input (voice or text) to determine the user's actual needs or expected behavior.

[0056] Specifically, navigation devices can generate navigation recommendations using a language model. For example, navigation command text, one or more historical navigation records related to the command text, and navigation preference text can be input into the language model, which then outputs navigation recommendations. When multiple historical navigation records related to the command text exist, and these records may contain different destinations, the navigation recommendation text can be used to select the destination that best matches the user's preferences from among the recorded destinations when generating the recommendation.

[0057] In some embodiments, the navigation device may also acquire additional data, including but not limited to current environmental data or current traffic data, such as weather data. The navigation device can generate navigation recommendation statements based on navigation instruction text, one or more historical navigation records related to the navigation instruction text, navigation preference text, and additional data.

[0058] Step 210: Output navigation recommendation statements.

[0059] Specifically, navigation devices can directly display navigation recommendations on the screen. Alternatively, navigation devices can output navigation recommendations in voice format, for example, by converting the navigation recommendations into speech and playing the converted audio.

[0060] Step 212: In response to receiving a voice confirmation command from the user regarding the navigation recommendation statement, navigation is initiated with the recommended navigation location as the navigation destination.

[0061] Among them, the voice confirmation command is a response command to the navigation recommendation statement. Other response commands can be rejection commands or new voice navigation commands. A voice confirmation command indicates that the user agrees to use the recommended navigation locations provided in the navigation recommendation statement. A rejection command indicates that the user refuses to use the recommended navigation locations provided in the navigation recommendation statement. Generating a new voice navigation command can be understood as modifying the existing voice navigation command.

[0062] Specifically, when a voice confirmation command is received, the navigation device can determine the navigation route to the destination and navigate according to that route.

[0063] Taking daily commuting as an example, the navigation interaction method of this application is illustrated. While driving to work, the user issues a voice navigation command, "Navigate to the office." The navigation device uses steps 202-210 above to determine the user's office location and outputs a navigation recommendation statement. The recommended navigation location in this statement is the specific office location. For example, the navigation recommendation statement could be, "Please confirm if you are going to an office in the central business district? I have planned the shortest route for you." The navigation recommendation statement can also be converted into voice and played.

[0064] In some embodiments, the navigation device can determine whether a unique location can be located based on the location description text. If not, steps 204-212 described above can be executed. If a location can be uniquely located based on the location description text, the navigation device can use the location located by the location description text as a recommended destination, generate and output a navigation recommendation statement corresponding to the recommended destination, and use the navigation recommendation statement to recommend navigation to the recommended destination. When a voice confirmation command is received for the output navigation recommendation statement, navigation can proceed with navigation to the recommended destination. This allows for quick identification of the user's desired destination, improving navigation efficiency.

[0065] In some embodiments, when the response command is a new voice navigation command, the process of generating navigation recommendation statements described above can be repeated. Therefore, new navigation recommendation statements can be generated promptly when the voice navigation command is modified, further improving navigation efficiency.

[0066] In some embodiments, the navigation device contains an application that provides navigation services, such as an application corresponding to an in-vehicle navigation system. The navigation device can determine the account currently logged into the application and the user to which that account belongs. The user who initiated the voice navigation command is designated as the first user, and the user to which the account logged into the application belongs is designated as the second user. The navigation device can compare the first user and the second user. If the first user and the second user are the same user, steps 204-212 are executed. Of course, steps 204-212 can also be executed if the first user and the second user are different users.

[0067] In some embodiments, in response to a voice navigation command initiated by a first user, the navigation device obtains the navigation command text recognized from the voice navigation command. The navigation command text includes location description text. If the first user and the second user are different users, the navigation device obtains the second user's historical navigation records related to the navigation command text, obtains the second user's navigation preference text, generates text based on the navigation command text, the second user's historical navigation records related to the navigation command text, and the second user's navigation preference text, obtains a navigation recommendation statement to navigate to a recommended navigation location related to the location description text, and outputs the navigation recommendation statement.

[0068] In some embodiments, when the first user and the second user are different users, the navigation device may output user selection instructions by voice or text. The user selection instructions are used to instruct the user to select one user from the first user and the second user. When the navigation device determines that the first user has been selected, it generates a navigation recommendation statement based on the first user's historical navigation records and navigation preference text. When the navigation device determines that the second user has been selected, it generates a navigation recommendation statement based on the second user's historical navigation records and navigation preference text.

[0069] In the above navigation interaction method, in response to a user-initiated voice navigation command, the system obtains the navigation command text recognized from the voice command. The navigation command text includes location description text. The system also obtains the user's historical navigation records related to the navigation command text and the user's navigation preference text. Since both the historical navigation records and the navigation preference text can reflect the user's navigation preferences, the system generates text based on the navigation command text, historical navigation records, and navigation preference text to obtain a navigation recommendation statement that navigates to a recommended navigation location related to the location description text. This method can obtain navigation recommendation statements that best meet the user's needs, thereby increasing the likelihood of receiving the user's voice confirmation command for the navigation recommendation statement, accelerating the determination of the navigation destination, and improving navigation efficiency. Furthermore, since the user interacts through voice, navigation efficiency is further improved compared to operating the screen.

[0070] Typically, in-vehicle navigation systems display candidate routes or destinations on a map on the vehicle's screen based on user-triggered commands. These systems rely on the screen for interaction, allowing users to determine their destination or route through on-screen operations. However, this screen-based interaction requires users to repeatedly check and manipulate the screen while driving to confirm the final destination or route. This process often involves multiple screen interactions, especially when selecting and confirming multiple navigation options. The complex and time-consuming steps reduce navigation efficiency, can easily distract users, and increase the risk of traffic accidents. Furthermore, different vehicle models and in-vehicle navigation systems can lead to significant differences in the on-screen interface, causing inconvenience and inconsistent user experiences. In this embodiment, voice interaction is used between the user and the navigation device, solving the problems associated with touchscreen interaction and improving navigation efficiency. Human-Computer Interaction (HCI) refers to the interaction process between humans and computer systems, aiming to improve user experience and efficiency through user interface design and interaction strategies.

[0071] In some embodiments, text generation based on navigation instruction text, historical navigation records, and navigation preference text to obtain a navigation recommendation statement for navigating to a recommended navigation location related to the location description text includes: generating a reference statement for indicating navigation recommendations based on the navigation instruction text, historical navigation records, and navigation preference text; and generating text based on the reference statement to obtain a navigation recommendation statement for navigating to a recommended navigation location related to the location description text.

[0072] The reference statement is used to instruct the generation of navigation recommendation statements based on reference information. The reference information includes navigation instruction text, at least one historical navigation record associated with the navigation instruction text, and navigation preference text, and may also include additional data such as environmental data mentioned above. The reference statement includes the reference information. For example, the reference statement could be: "Please generate a statement for recommending navigation to the user based on the navigation instruction text, at least one historical navigation record associated with the navigation instruction text, and navigation preference text."

[0073] Specifically, the navigation device can concatenate navigation instruction text, at least one historical navigation record related to the navigation instruction text, and navigation preference text to obtain reference information. Alternatively, the navigation device can concatenate navigation instruction text, at least one historical navigation record related to the navigation instruction text, navigation preference text, and the additional data to obtain reference information, and then generate reference statements based on the reference information.

[0074] In this embodiment, since the reference statement is used to indicate navigation recommendation, the reference statement clarifies that the purpose of text generation is to make navigation recommendations. Therefore, by generating text based on the reference statement, navigation recommendation statements that conform to navigation recommendations can be obtained.

[0075] In some embodiments, the method further includes: determining a historical destination indicated by a historical navigation record; querying real-time information of the historical destination; and generating a reference statement for indicating navigation recommendations based on navigation instruction text, historical navigation records, and navigation preference text, including: generating a reference statement for indicating navigation recommendations based on navigation instruction text, historical navigation records, navigation preference text, and real-time information of the historical destination.

[0076] The historical navigation record may include a destination identifier. The historical destination indicated by the historical navigation record refers to the destination represented by the destination identifier.

[0077] Real-time information about a destination can include information about events currently occurring at the destination, as well as information about events currently occurring in the surrounding area. Events can be, but are not limited to, activities such as promotions. Real-time information about a destination can also include information about activities currently offered at the destination; for example, if the destination is a shopping mall, the activity information could be discount information. Real-time information about a destination can also include at least one of the following: traffic conditions, weather conditions, pedestrian traffic, or facilities in the surrounding area.

[0078] Specifically, real-time information about the destination can be stored in external data sources, such as external databases, e.g. Figure 3 As shown, the navigation device can communicate with external data sources. Based on the destination identifier, the navigation device can query real-time information associated with that destination identifier from the external data source to obtain the real-time information for that destination.

[0079] In some embodiments, in step 204, the navigation device may obtain at least one historical navigation record related to the user's navigation instruction text, determine the historical destination indicated by the at least one historical navigation record, obtain at least one historical destination, query the real-time information of each of the at least one historical destination, and generate a reference statement for indicating navigation recommendations based on the navigation instruction text, the at least one historical navigation record, the navigation preference text, and the real-time information of each of the at least one historical destination.

[0080] Since different historical navigation records can indicate the same destination, the navigation device can determine the historical destination indicated by each of the at least one historical navigation record, and then deduplicate the determined historical destinations to obtain the at least one historical destination.

[0081] In some embodiments, the navigation device can concatenate the navigation instruction text, the at least one historical navigation record, the navigation preference text, and the key real-time information of each of the at least one historical destination to obtain reference information, and generate reference statements based on the reference information.

[0082] In this embodiment, real-time destination information is also incorporated when forming the reference statement. Since real-time destination information may affect the strength of a user's willingness to navigate to that destination, incorporating real-time information can make the navigation recommendation statement generated based on the reference statement more in line with the user's intent and desire, thereby improving the accuracy of navigation recommendations.

[0083] In some embodiments, querying real-time information about a historical destination includes: identifying at least one keyword related to the historical destination; and querying real-time information about the historical destination that is related to each of the at least one keyword.

[0084] Keywords related to historical destinations can be words related to real-time information about the historical destination. For example, if the historical destination is a shopping mall, the keywords could be "promotion" or "discount." If the historical destination is a tourist attraction, the keywords could be "pedestrian flow," "vehicle flow," or "weather."

[0085] Specifically, the navigation preference text may include location preference text fragments, which describe the user's preferences for locations. For example, the location preference text might describe a user's preference for navigating to a destination with promotional activities, or a user's preference for navigating to a destination with low foot traffic. Therefore, the navigation device can identify at least one keyword that is related to both the historical destination and the location preference text fragment, and query real-time information related to each of these keywords. For example, if the keywords are "promotion" and "foot traffic," the device can retrieve current promotional information and current foot traffic information for the historical destination (and, if the departure time is known, the device can retrieve promotional information and foot traffic information for that historical destination at the departure time).

[0086] In this embodiment, relevant real-time information can be quickly retrieved using keywords related to the destination, thus improving the efficiency of real-time information retrieval.

[0087] In some embodiments, a reference statement for indicating navigation recommendations is generated based on navigation instruction text, historical navigation records, and navigation preference text, including: when the navigation instruction is generated during vehicle operation, obtaining real-time driving data of the vehicle; and generating a reference statement for indicating navigation recommendations based on the navigation instruction text, historical navigation records, navigation preference text, and real-time driving data.

[0088] The real-time driving data of the vehicle can be collected by sensors in the vehicle, including but not limited to speed sensors or acceleration sensors. Real-time driving data can include vehicle speed, braking data, or lane keeping data. Braking data reflects braking performance, while lane keeping data reflects lane keeping performance.

[0089] Specifically, the navigation device can concatenate navigation instruction text, at least one historical navigation record related to the navigation instruction text, navigation preference text, and real-time driving data to generate reference information. Based on the reference information, it can generate a reference statement to instruct navigation recommendations based on the reference information. For example, the reference statement could be "Please generate a statement to recommend navigation to the user based on the reference information."

[0090] In some embodiments, the navigation device may generate a navigation recommendation statement using at least one of real-time driving data, real-time information of historical destinations, additional data (driving habits, traffic or environmental data), navigation instruction text, at least one historical navigation record associated with the navigation instruction text, and navigation preference text.

[0091] In this embodiment, since real-time driving data can reflect the characteristics of users to a certain extent, for example, if the real-time driving data shows that the vehicle speed is high and the braking is abrupt, it can reflect that the user prefers adventure. Therefore, the generated navigation recommendation statement can tend to recommend adventure-type destinations to better meet the user's needs.

[0092] In some embodiments, text generation based on reference statements to obtain navigation recommendation statements for navigation to recommended navigation locations related to location description text includes: text generation based on reference statements to obtain initial statements for navigation to recommended navigation locations related to location description text; and linguistic correction of the initial statements to obtain navigation recommendation statements for navigation to recommended navigation locations related to location description text.

[0093] Specifically, the navigation device can input a reference statement into a first language model to obtain an initial statement output by the first language model. Then, it generates a revised statement based on the initial statement; the revised statement is a statement that indicates linguistic corrections to the initial statement to make it more fluent. The navigation device can then input the revised statement into a second language model for further linguistic corrections, obtaining a navigation recommendation statement output by the second language model, thus achieving a more fluent and natural navigation recommendation statement.

[0094] For example, if the initial statement is "Based on your history, you frequently visit Plaza A on Road B. Do you want navigation to that location? There's a promotion there today," the revised statement could be: "Please revise the sentence 'Based on your history, you frequently visit Plaza A on Road B. Do you want navigation to that location? There's a promotion there today' to make the sentence flow better." The resulting revised navigation recommendation statement would be, for example: "Please confirm that you are going to Plaza A on Road B. There's a special promotion near that location today. Do you need navigation there?" Figure 4 The diagram shown illustrates the principle of converting reference statements into output navigation recommendation statements. The text-to-speech converter is a module used to convert text into speech.

[0095] The first language model and the second language model can be the same language model or different language models. The language model can be a pre-trained large language model, such as, but not limited to, GPT (Generative Pre-trained Transformer), for example, GPT-4. GPT is a deep learning-based natural language processing model.

[0096] For example, in a shopping or entertainment scenario, the navigation device recognizes the user's voice navigation command "Navigate to Plaza A." while driving. The navigation device then executes the process described above of generating a reference statement based on the navigation command text, obtaining the reference statement. The navigation device then inputs the reference statement into a first language model to obtain a navigation recommendation statement, such as: "Based on your history, you frequently visit Plaza A on Road B. Do you want to navigate there? There's a promotion at that location today," or "You previously visited Plaza A on Road B. Do you want to go there this time? We can provide the latest discount information."

[0097] In this embodiment, the initial statement is modified to obtain a more fluent and smooth navigation recommendation statement, making the navigation recommendation statement easier to understand.

[0098] In some embodiments, there are multiple navigation recommendation statements. Outputting navigation recommendation statements includes: generating multiple navigation recommendation statements using reference statements, selecting one navigation recommendation statement from the multiple navigation recommendation statements, and outputting the selected navigation recommendation statement; the method further includes: in response to receiving a voice rejection instruction from a user regarding a navigation recommendation statement, outputting a navigation recommendation statement that has not been selected from the multiple navigation recommendation statements.

[0099] Specifically, the navigation device can generate multiple navigation recommendation statements based on reference information, and can generate a corresponding recommendation score for each statement. The navigation device can prioritize outputting navigation recommendation statements with higher recommendation scores. If a voice rejection command is received for an output navigation recommendation statement, the device outputs the navigation recommendation statement with the highest recommendation score from the remaining navigation recommendation statements, and so on. If a voice confirmation command is received for an output navigation recommendation statement, navigation is performed according to the recommended navigation location described in the output navigation recommendation statement. Remaining navigation recommendation statements refer to navigation recommendation statements that have not yet been output.

[0100] In some embodiments, if no voice confirmation command is received after each navigation recommendation statement has been output, the navigation device can remind the user to issue a new voice navigation command, that is, modify the voice navigation command, that is, re-execute the process of generating navigation recommendation statements.

[0101] In this embodiment, by generating multiple navigation recommendation statements, the next navigation recommendation statement can be quickly output upon receiving a voice rejection command, thereby improving the efficiency of outputting navigation recommendation statements that meet user needs and enhancing navigation efficiency.

[0102] In some embodiments, historical navigation records are selected from the user's historical navigation record set. The method further includes: generating historical navigation records for each output navigation recommendation statement based on the response instruction to the navigation recommendation statement and the navigation data in the navigation recommendation statement; and adding the generated historical navigation records to the historical navigation record set to update the historical navigation record set.

[0103] The navigation data in the navigation recommendation statement may include destination information, such as destination identifiers, and navigation route information.

[0104] Specifically, the navigation device can generate result tags for navigation recommendation statements based on the response command. When the response command is a voice confirmation command, the result tag is the first tag; otherwise, the result tag is the second tag. The first tag indicates that the user navigated to the destination recommended by the navigation recommendation statement. The second tag indicates that the user did not navigate to the destination recommended by the navigation recommendation statement. The navigation device can combine the result tags and navigation data from the navigation recommendation statement to form historical navigation records to update the historical navigation record set. This implements a feedback mechanism (FM). The feedback mechanism is the process of collecting user feedback within the system, aiming to continuously improve and optimize system performance and user experience.

[0105] In this embodiment, historical navigation records are generated based on the response instructions to the navigation recommendation statement and the navigation data in the navigation recommendation statement. Thus, the historical navigation records contain information that can characterize whether the user has used the destination recommended by the navigation recommendation statement for navigation, reflecting the user's attitude and preferences. In this way, the accuracy of the recommendation can be further improved when making navigation recommendations based on the historical navigation records next time.

[0106] In some embodiments, navigating with a recommended navigation location as the navigation destination includes: outputting at least one route option with the navigation destination as the endpoint; receiving a user's voice selection instruction for a target route option among the at least one route option; and navigating with the route indicated by the target route option as the navigation route.

[0107] Among them, the voice selection command is used to select a route option.

[0108] Specifically, the navigation device can determine at least one route with that destination as its endpoint, either after or simultaneously with determining the navigation destination. Then, it can display route options corresponding to each of these routes on the screen. Alternatively, it can output the route options to the user via voice for the user to choose from.

[0109] In some embodiments, the navigation preference text may include a time preference text fragment, which is a text fragment describing the user's preferred departure time. The navigation device can generate a corresponding departure time for the generated route based on the time preference text fragment and can provide traffic data related to the departure time for the user's reference.

[0110] In this embodiment, route selection is achieved through voice commands, which improves the efficiency of route selection.

[0111] In some embodiments, the method further includes: during navigation with a recommended navigation location as the navigation destination, when it is determined that the navigation route needs to be changed, outputting a route adjustment instruction in the form of a voice; and when a voice confirmation instruction for the route change instruction is received, switching to navigation according to the adjusted navigation route indicated by the route adjustment instruction.

[0112] Specifically, during navigation, the navigation device can acquire real-time traffic data related to the currently used navigation route. If it determines that there are traffic anomalies such as accidents or congestion on the navigation route based on the real-time traffic data, it will determine that the navigation route needs to be changed. The device can also provide the user with relevant information about the adjusted navigation route via voice. When the user receives a voice confirmation command for the route change instruction, it means that the user agrees to switch the currently used navigation route to the adjusted navigation route, and can then switch to the adjusted navigation route to continue navigation.

[0113] In some embodiments, during navigation, when the navigation device receives a voice-based route change command from the user, it determines that the navigation route needs to be changed. The navigation device then identifies the route change command. If route information is identified from the command, the device uses the identified route information as the adjusted navigation route and outputs a route adjustment command asking whether the user wants to change the navigation route to the adjusted route. If no route information is identified from the command, the navigation device generates an adjusted route and outputs a route adjustment command asking whether the user wants to change the navigation route to the adjusted route.

[0114] In some embodiments, the navigation preference text includes a route preference text fragment, which describes the user's preference for a route. For example, the route preference text fragment may be "the user prefers to select a highway route" or "the user prefers to select a provincial road route". In order to determine the adjusted route, the navigation device can determine the adjusted route based on the route preference text fragment. For example, it can select the route that best matches the route described by the route preference text fragment from a number of available routes as the adjusted route.

[0115] In this embodiment, navigation route changes are made through voice interaction, which improves the efficiency of changing navigation routes.

[0116] In some embodiments, obtaining a user's historical navigation records related to navigation instruction text includes: vectorizing the navigation instruction text to generate a query vector; determining multiple historical navigation records of the user, and determining multiple historical vectors obtained by vectorizing the multiple historical navigation records respectively; and determining the historical navigation records related to the navigation instruction text from the multiple historical navigation records based on the vector similarity between the multiple historical vectors and the query vector respectively.

[0117] Vectorization can be achieved through pre-trained vectorization models, such as embedding models. Vectorization models can transform input text into fixed-length vectors. Vectorization models can be, but are not limited to, BERT (Bidirectional Encoder Representations from Transformers) or Word2Vec. BERT is a pre-trained language representation model used to generate vector representations of words. Word2Vec is a technique used to generate word vectors.

[0118] Specifically, a navigation device can identify some or all of the user's historical navigation records from the user's historical navigation record set, thus obtaining multiple historical navigation records. For example, the navigation device can identify historical navigation records generated within a preset time period from the historical navigation record set, thus obtaining multiple historical navigation records. The preset time period can be set as needed, such as the most recent week, the most recent month, or the most recent three months.

[0119] In some embodiments, the navigation device or data storage system may use the historical vector corresponding to each historical navigation record in the historical navigation record set. The historical vector corresponding to a historical navigation record is a vector generated by vectorizing the historical navigation record. The historical vector may be generated by the navigation device or a server. The navigation device can obtain the historical vectors corresponding to the multiple historical navigation records to obtain multiple historical vectors.

[0120] In some embodiments, for each of the plurality of historical vectors, the navigation device can calculate the similarity, i.e., vector similarity, between the historical vector and the query vector. Then, the navigation device can sort the plurality of historical vectors in descending order of vector similarity to obtain a historical vector sequence. Following a front-to-back order, at least one historical vector is extracted from the historical vector sequence, and the historical navigation record corresponding to each of the extracted at least one historical vector is used as a historical navigation record associated with the navigation instruction text.

[0121] In some embodiments, for each of the plurality of historical vectors, the navigation device can compare the vector similarity between the historical vector and the query vector with a similarity threshold. If the vector similarity is greater than or equal to the similarity threshold, the historical navigation record corresponding to the historical vector is regarded as a historical navigation record related to the navigation instruction text. The similarity threshold can be preset or determined based on the vector similarity between the plurality of historical vectors and the query vector respectively. For example, the average of the similarities of each vector can be used as the similarity threshold, or any one of the similarities of each vector can be used as the similarity threshold.

[0122] In some embodiments, the historical vector set may be stored in a vector database; for example, the data storage system may include a vector database. The vector database may be, but is not limited to, FAISS (Facebook AI Similarity Search) or Annoy (Approximate Nearest Neighbors Oh Yeah). The data storage system may also include a text database for storing text, where user preference text may be stored.

[0123] In this embodiment, the goal of determining historical navigation records related to navigation instruction text based on the similarity between vectors is achieved. Using vectors helps to perform accurate and fast retrieval and searching, improving the efficiency and accuracy of determining historical navigation records related to navigation instruction text.

[0124] In some embodiments, the step of generating navigation preference text includes: obtaining at least a portion of the historical navigation records from the user's historical navigation record set; analyzing the at least a portion of the historical navigation records to generate navigation preference text.

[0125] The process of generating navigation preference text based on historical navigation records can be understood as a preference learning process. Preference learning (PL) is a machine learning method that identifies user preferences by analyzing historical user behavior or feedback, enabling personalized adjustments.

[0126] As new historical navigation records are generated over time, navigation devices can add these new records to the historical navigation record collection to update the collection. Because the historical navigation record collection is constantly updated, navigation preference text can be periodically regenerated to improve its accuracy.

[0127] In this embodiment, since the navigation preference text is obtained by analyzing historical navigation records, the navigation preference text can reflect the user's preferences in navigation. Using the navigation preference text to generate navigation recommendation statements can increase the likelihood that the recommended navigation locations meet the user's needs, speed up the determination of navigation destinations, and thus improve navigation efficiency.

[0128] In some embodiments, such as Figure 5The diagram illustrates the principle of a navigation interaction method. A speech recognition module converts speech into text. After receiving a user's voice navigation command, the navigation device inputs the command into the speech recognition module to obtain the navigation command text. This text is then input into a vectorization model to obtain a query vector. The navigation device can then determine at least one historical navigation record related to the user's navigation command text by calculating the similarity between the query vector and historical vectors in the data storage system. Next, the navigation device retrieves navigation preference text from the data storage system. It should be noted that the data storage system may include one or more databases, such as vector databases and non-vector databases. Historical vectors are stored in the vector database. Navigation preference text can be stored in the non-vector database. The navigation device can obtain real-time information about at least one historical destination from an external data source. Based on the navigation command text, the at least one historical navigation record, the navigation preference text, and the real-time information about the at least one historical destination, the device generates a reference statement, generates a navigation recommendation statement based on the reference statement, and then outputs the navigation recommendation statement.

[0129] In this embodiment, combining historical navigation records and navigation preference text (reflecting user preferences) enables personalized recommendations, providing more accurate and relevant suggestions that align with the user's actual needs and preferences. In intelligent systems, personalization refers to dynamically adjusting the system's response and suggestions based on the user's historical behavior, preferences, and interests to enhance user experience and satisfaction. Personalized Recommendation (PR) refers to generating suggestions or options that meet the user's specific needs based on historical data and preferences, thereby improving service relevance and user satisfaction. Voice interaction reduces the complexity of screen interaction and minimizes operational steps, allowing users to quickly and directly confirm navigation, improving navigation efficiency, enhancing user experience, and strengthening driving safety.

[0130] In some embodiments, such as Figure 6The diagram illustrates another navigation interaction method. When a user initiates a voice navigation command, the in-vehicle voice assistant in the navigation device converts the command into text, obtaining the navigation command text. Based on this text, it retrieves historical navigation records, identifying at least one related historical record, and also obtains navigation preference text. Then, the navigation device generates a reference statement based on the navigation command text, the at least one related historical record, and the navigation preference text. This reference statement is processed through a large model (a first language model and a second language model) to obtain a recommended navigation statement. The recommended navigation statement is then converted into speech and played. Upon receiving a voice confirmation command, "execute navigation," meaning navigation proceeds according to the recommended navigation location. Upon receiving a modification command, the process of generating the recommended navigation statement is repeated based on the revised voice navigation command.

[0131] In some embodiments, a navigation interaction method is provided, including:

[0132] 1. In response to a user-initiated voice navigation command, obtain the navigation command text recognized from the voice navigation command. The navigation command text includes location description text.

[0133] 2. Vectorize the navigation command text to generate query vectors.

[0134] 3. Determine multiple historical navigation records from the user's historical navigation record set, and determine multiple historical vectors obtained by vectorizing the multiple historical navigation records respectively.

[0135] 4. Based on the vector similarity between multiple historical vectors and the query vector, determine at least one historical navigation record that is related to the navigation instruction text from multiple historical navigation records.

[0136] 5. Obtain the user's navigation preference text generated from at least a portion of the user's historical navigation records in the user's historical navigation record set.

[0137] 6. Generate reference statements based on navigation instruction text, historical navigation records, and navigation preference text.

[0138] 7. Input the reference statement into the first language model to obtain the initial statement.

[0139] 8. Input the initial statement into the second language model to obtain the navigation recommendation statement that navigates to the recommended navigation location related to the location description text.

[0140] 9. Convert the navigation recommendation statements into speech and play the converted speech.

[0141] 10. Receive voice responses from users regarding navigation recommendations. If the response is a voice confirmation, then navigate to the recommended location as the destination.

[0142] 11. Generate historical navigation records from the navigation data in the reply instructions and navigation recommendation statements, and add the historical navigation records to the user's historical navigation record collection.

[0143] 12. When navigating to the recommended navigation destination, if it is determined that the navigation route needs to be changed, a route adjustment command will be output in voice form.

[0144] 13. When a voice confirmation command for a route change is received, navigation will switch to the adjusted route indicated by the route adjustment command.

[0145] The technical effects of this embodiment include: a) Reduced screen reliance: Traditional navigation systems require drivers to check the vehicle's screen to confirm navigation suggestions while driving, increasing the risk of driver distraction. This application, through a comprehensive voice interaction design, allows users to confirm navigation information solely through voice, significantly reducing visual distraction during driving and improving driving safety. b) Personalized navigation suggestions: Personalized navigation recommendations are generated using the user's historical navigation records, making navigation suggestions more closely aligned with the user's actual needs and preferences. For example, based on the user's past navigation records, the system can suggest frequently visited Wanda Plazas and provide the latest promotional information. This personalized suggestion improves the relevance of navigation and user satisfaction. c) Achieved accurate recommendations: By combining navigation preference text and real-time data, the system can provide more accurate navigation suggestions, reducing user confusion when choosing destinations and routes. For example, when a user requests "navigation to Wanda Plaza," the system can accurately suggest whether to choose a frequently visited Wanda Plaza and provide useful additional information (such as promotional activities), thereby improving the accuracy of navigation recommendations. d) Enables natural and fluent voice feedback: By generating natural language feedback through a large language model, the interaction between the user and the navigation system becomes more natural and fluid. Users can confirm and adjust navigation through dialogue, improving the rigid command interaction method of traditional navigation systems. e) Enables real-time feedback optimization: The navigation plan can be dynamically adjusted based on real-time traffic data and user feedback, ensuring that navigation information is always up-to-date and most applicable, enhancing the user's driving experience.

[0146] The navigation interaction method provided in this application can be applied to any application scenario that requires navigation, including but not limited to medical navigation, daily commuting scenarios, shopping and entertainment scenarios, and tourism scenarios.

[0147] For example, such as Figure 7The diagram illustrates an application scenario for a navigation interaction method, specifically a shopping and entertainment scenario. While driving, the user issues a voice navigation command, "Navigate to the nearest Plaza A." The navigation device receives this command and generates a navigation recommendation statement using the navigation interaction method provided in this application. The recommendation statement could be, for example, "Based on your history, Plaza A, which you frequently visit, is on Road B. Do you want to navigate there? There's a discount event nearby today." The device then outputs the navigation recommendation statement.

[0148] For example, in a tourism scenario, a user driving on a trip might issue a voice command saying "Navigate to tourist attractions." This voice command is the navigation instruction. The navigation device, based on the navigation interaction method provided in this application, generates a navigation recommendation statement. This recommendation statement could be, for example, an instruction to recommend nearby attractions and restaurants, such as the voice command "Are you going to the popular C scenic area? There's a highly-rated restaurant nearby; would you like navigation there?", and outputs the navigation recommendation statement.

[0149] For example, in the application scenario of medical navigation, while driving, the user issues the voice command "Navigate to the hospital." The navigation device receives this voice command and uses the navigation interaction method provided in this application to generate a navigation recommendation statement. For example, the navigation recommendation statement could be, "Based on your history, the hospital you frequently visit is the Children's Hospital on Road D. Do you want to navigate there?" and outputs the navigation recommendation statement.

[0150] It should be understood that although the steps in the flowcharts of the embodiments described above are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the embodiments described above may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages of other steps.

[0151] Based on the same inventive concept, this application also provides a navigation interaction device for implementing the navigation interaction method described above. The solution provided by this device is similar to the implementation scheme described in the above method; therefore, the specific limitations in one or more navigation interaction device embodiments provided below can be found in the limitations of the navigation interaction method described above, and will not be repeated here.

[0152] In some embodiments, such as Figure 8 As shown, a navigation interaction device is provided, including: a navigation instruction processing module 802, a navigation record acquisition module 804, a preference text acquisition module 806, a recommendation statement acquisition module 808, a recommendation statement output module 810, and a navigation execution module 812, wherein:

[0153] The navigation instruction processing module 802 is used to respond to a user-initiated voice navigation instruction and obtain the navigation instruction text recognized from the voice navigation instruction. The navigation instruction text includes location description text.

[0154] The navigation record acquisition module 804 is used to acquire the user's historical navigation records related to navigation command text.

[0155] The preference text acquisition module 806 is used to acquire the user's navigation preference text.

[0156] The recommended statement acquisition module 808 is used to generate text based on navigation instruction text, historical navigation records and navigation preference text, and obtain navigation recommendation statements to navigate to recommended navigation locations related to the location description text.

[0157] The recommended statement output module 810 is used to output navigation recommended statements.

[0158] The navigation execution module 812 is used to respond to the user's voice confirmation command for the navigation recommendation statement and to navigate to the recommended navigation location as the navigation destination.

[0159] In some embodiments, the recommendation statement obtaining module 808 is further configured to generate a reference statement for indicating navigation recommendations based on navigation instruction text, historical navigation records, and navigation preference text; and generate text based on the reference statement to obtain a navigation recommendation statement for navigating to a recommended navigation location related to the location description text.

[0160] In some embodiments, the recommendation statement acquisition module 808 is further configured to determine the historical destination indicated by the historical navigation record; query the real-time information of the historical destination; and generate a reference statement for indicating navigation recommendations based on the navigation instruction text, historical navigation record, navigation preference text, and the real-time information of the historical destination.

[0161] In some embodiments, the recommendation statement obtaining module 808 is further configured to determine at least one keyword related to a historical destination; and query real-time information of the historical destination that is related to at least one keyword respectively.

[0162] In some embodiments, the recommendation statement acquisition module 808 is further configured to acquire real-time driving data of the vehicle when the voice navigation command is generated during vehicle operation; and generate reference statements for indicating navigation recommendations based on the navigation command text, historical navigation records, navigation preference text, and real-time driving data.

[0163] In some embodiments, the recommended statement obtaining module 808 is further configured to generate text based on reference statements to obtain an initial statement for navigating to a recommended navigation location related to the location description text; and to perform linguistic correction on the initial statement to obtain a navigation recommendation statement for navigating to a recommended navigation location related to the location description text.

[0164] In some embodiments, there are multiple navigation recommendation statements. The recommendation statement output module 810 is further configured to generate multiple navigation recommendation statements using reference statements, select one navigation recommendation statement from the multiple navigation recommendation statements, and output the selected navigation recommendation statement; in response to receiving a voice rejection instruction from the user for a navigation recommendation statement, it outputs one navigation recommendation statement that has not been selected from the multiple navigation recommendation statements.

[0165] In some embodiments, historical navigation records are selected from the user's historical navigation record set. The device further includes a set update module, which generates historical navigation records for each output navigation recommendation statement based on the response instruction to the navigation recommendation statement and the navigation data in the navigation recommendation statement; and adds the generated historical navigation records to the historical navigation record set to update the historical navigation record set.

[0166] In some embodiments, the navigation execution module 812 is further configured to output at least one route option with the navigation destination as the endpoint, based on the navigation destination; receive a voice selection instruction from a user for a target route option among the at least one route option, and navigate using the route indicated by the target route option as the navigation route.

[0167] In some embodiments, the device further includes a route change module, which is used to output a route adjustment command in the form of a voice when it is determined that the navigation route needs to be changed during navigation with a recommended navigation location as the navigation destination; and to switch to navigation according to the adjusted navigation route indicated by the route adjustment command when a voice confirmation command for the route change command is received.

[0168] In some embodiments, the navigation record acquisition module 804 is further configured to vectorize the navigation instruction text to generate a query vector; determine multiple historical navigation records of the user, and determine multiple historical vectors obtained by vectorizing the multiple historical navigation records respectively; and determine the historical navigation record related to the navigation instruction text from the multiple historical navigation records based on the vector similarity between the multiple historical vectors and the query vector respectively.

[0169] In some embodiments, the apparatus further includes a preference text generation module for generating navigation preference text, the preference text generation module being configured to obtain at least a portion of the historical navigation records from the user's historical navigation record set; analyze the at least a portion of the historical navigation records; and generate navigation preference text.

[0170] Each module in the aforementioned navigation interaction device can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in the processor of the electronic device in hardware form or independent of it, or stored in the memory of the electronic device in software form, so that the processor can call and execute the operations corresponding to each module.

[0171] In some embodiments, an electronic device is provided, the internal structure of which can be as shown in the figure. Figure 9 As shown, this electronic device includes a processor, memory, input / output (I / O) interfaces, and a communication interface. The processor, memory, and I / O interfaces are connected via a system bus, and the communication interface is also connected to the system bus via the I / O interfaces. The processor provides computational and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system, computer programs, and a database. The internal memory provides the environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The database stores data involved in the navigation interaction method. The I / O interfaces are used for exchanging information between the processor and external devices. The communication interface is used for communicating with external terminals via a network connection. When the computer program is executed by the processor, it implements a navigation interaction method.

[0172] In some embodiments, an electronic device is provided, the internal structure of which can be as shown in the figure. Figure 10As shown, this electronic device includes a processor, memory, input / output interface, communication interface, display unit, and input device. The processor, memory, and input / output interface are connected via a system bus, and the communication interface, display unit, and input device are also connected to the system bus via the input / output interface. The processor provides computing and control capabilities. The memory includes a non-volatile storage medium and internal memory. The non-volatile storage medium stores the operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage medium. The input / output interface is used for exchanging information between the processor and external devices. The communication interface is used for wired or wireless communication with external terminals; wireless communication can be achieved through Wi-Fi, mobile cellular networks, Near Field Communication (NFC), or other technologies. When the computer program is executed by the processor, it implements a navigation interaction method. The display unit is used to form a visually visible image and can be a display screen, a projection device, or a virtual reality imaging device. The display screen can be an LCD screen or an e-ink screen. The input device of the electronic device can be a touch layer covering the display screen, or buttons, trackballs, or touchpads set on the casing of the electronic device, or external keyboards, touchpads, or mice, etc.

[0173] Those skilled in the art will understand that Figure 9 and Figure 10 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the electronic device to which the present application is applied. The specific electronic device may include more or fewer components than shown in the figure, or combine certain components, or have different component arrangements.

[0174] In some embodiments, an electronic device is provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps in the navigation interaction method described above.

[0175] In some embodiments, a computer-readable storage medium is provided having a computer program stored thereon, which, when executed by a processor, implements the steps in the navigation interaction method described above.

[0176] In some embodiments, a computer program product is provided, including a computer program that, when executed by a processor, implements the steps in the navigation interaction method described above.

[0177] It should be noted that 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, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of the relevant data must comply with relevant regulations.

[0178] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, artificial intelligence (AI) processors, etc., and are not limited to these.

[0179] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this application.

[0180] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of this patent application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this application should be determined by the appended claims.

Claims

1. A navigation interaction method, characterized in that, The method includes: In response to a user-initiated voice navigation command, the system acquires navigation command text recognized from the voice navigation command, the navigation command text including location description text; Obtain the user's historical navigation records related to the navigation command text; Obtain the user's navigation preference text; Based on the navigation instruction text, the historical navigation records, and the navigation preference text, text is generated to obtain a navigation recommendation statement that navigates to a recommended navigation location related to the location description text; Output the navigation recommendation statement; In response to receiving a voice confirmation command from the user regarding the navigation recommendation statement, navigation is initiated with the recommended navigation location as the navigation destination.

2. The method according to claim 1, characterized in that, The step of generating text based on the navigation instruction text, the historical navigation records, and the navigation preference text to obtain a navigation recommendation statement that navigates to a recommended navigation location related to the location description text includes: Based on the navigation instruction text, the historical navigation records, and the navigation preference text, a reference statement is generated to indicate navigation recommendations. Based on the reference statement, text is generated to obtain a navigation recommendation statement that navigates to a recommended navigation location related to the location description text.

3. The method according to claim 2, characterized in that, The method further includes: Determine the historical destination indicated by the historical navigation record; Query the real-time information of the historical destination; The step of generating a reference statement for indicating navigation recommendations based on the navigation instruction text, the historical navigation records, and the navigation preference text includes: Based on the navigation instruction text, the historical navigation records, the navigation preference text, and the real-time information of the historical destinations, a reference statement is generated to indicate navigation recommendations.

4. The method according to claim 3, characterized in that, The query for real-time information of the historical destination includes: Identify at least one keyword related to the historical destination; Query real-time information related to the historical destination and each of the at least one keyword.

5. The method according to claim 2, characterized in that, The step of generating a reference statement for indicating navigation recommendations based on the navigation instruction text, the historical navigation records, and the navigation preference text includes: When the voice navigation command is generated during vehicle operation, the real-time driving data of the vehicle is obtained. Based on the navigation instruction text, the historical navigation records, the navigation preference text, and the real-time driving data, a reference statement is generated to indicate navigation recommendations.

6. The method according to claim 2, characterized in that, The step of generating text based on the reference statement to obtain a navigation recommendation statement that navigates to a recommended navigation location related to the location description text includes: Based on the reference statement, text is generated to obtain an initial statement for navigating to a recommended navigation location related to the location description text; The initial statement is linguistically modified to obtain a navigation recommendation statement that navigates to a recommended navigation location related to the location description text.

7. The method according to claim 2, characterized in that, The navigation recommendation statements are multiple, and the output of the navigation recommendation statements includes: Multiple navigation recommendation statements are generated using the reference statements, one navigation recommendation statement is selected from the multiple navigation recommendation statements, and the selected navigation recommendation statement is output. The method further includes: In response to receiving a voice rejection command from the user regarding the navigation recommendation statement, the system outputs one navigation recommendation statement that has not been selected from the plurality of navigation recommendation statements.

8. The method according to claim 7, characterized in that, The historical navigation records are selected from the user's historical navigation record set, and the method further includes: For each output navigation recommendation statement, a historical navigation record is generated based on the response command to the navigation recommendation statement and the navigation data in the navigation recommendation statement; The generated historical navigation records are added to the historical navigation record set to update the historical navigation record set.

9. The method according to claim 1, characterized in that, The navigation process using the recommended navigation location as the destination includes: Based on the navigation destination, output at least one route option with the navigation destination as the final destination; The system receives a voice selection command from the user for a target route option among the at least one route options, and uses the route indicated by the target route option as the navigation route.

10. The method according to claim 9, characterized in that, The method further includes: During navigation with the recommended navigation location as the destination, if it is determined that the navigation route needs to be changed, a route adjustment command in voice form will be output. When a voice confirmation command is received for the route change instruction, navigation will switch to the adjusted route indicated by the route adjustment command.

11. The method according to any one of claims 1 to 10, characterized in that, The step of obtaining the user's historical navigation records related to the navigation instruction text includes: The navigation instruction text is vectorized to generate a query vector; Determine multiple historical navigation records of the user, and determine multiple historical vectors obtained by vectorizing the multiple historical navigation records respectively; Based on the vector similarity between the plurality of historical vectors and the query vector, the historical navigation records related to the navigation instruction text are determined from the plurality of historical navigation records.

12. The method according to any one of claims 1 to 10, characterized in that, The step of generating the navigation preference text includes: Obtain at least a portion of the historical navigation records from the user's historical navigation record set; The navigation preference text is generated by analyzing at least a portion of the historical navigation records.

13. A navigation interaction device, characterized in that, The device includes: The navigation instruction processing module is used to respond to a user-initiated voice navigation instruction and obtain the navigation instruction text recognized from the voice navigation instruction, wherein the navigation instruction text includes location description text; The navigation record acquisition module is used to acquire the user's historical navigation records related to the navigation instruction text; The preference text acquisition module is used to acquire the user's navigation preference text; The recommended statement acquisition module is used to generate text based on the navigation instruction text, the historical navigation records and the navigation preference text, and obtain a navigation recommendation statement that navigates to a recommended navigation location related to the location description text. The recommended statement output module is used to output the navigation recommended statement; The navigation execution module is used to respond to the user's voice confirmation command for the navigation recommendation statement and to navigate to the recommended navigation location as the navigation destination.

14. An electronic device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 12.

15. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 12.

16. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 12.

Images