Information determination method, device and electronic equipment for off-board location
By determining the location information outside the vehicle through voice interaction, the problem of low accuracy and cumbersome operation of visual recognition in existing technologies is solved, realizing real-time and convenient acquisition of location information outside the vehicle and improving the interactivity between the vehicle system and the user.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- SHANGHAI LIXIANG AUTOMOBILE CO LTD
- Filing Date
- 2024-12-25
- Publication Date
- 2026-06-26
AI Technical Summary
When users obtain location information outside the vehicle while driving, existing methods rely on visual recognition, which has low accuracy and limited range. Electronic devices are cumbersome to operate and have information delays, affecting the interactivity between the vehicle system and the user.
By acquiring users' voice interaction information, the system determines the inquiry information for locations outside the vehicle, uses map data to determine the target location outside the vehicle, and provides real-time feedback of relevant information, including map cards and voice prompts, thereby improving interactivity and convenience.
It enables real-time acquisition of location information outside the vehicle while driving, improving user interactivity and convenience, and reducing operational complexity and information delay.
Smart Images

Figure CN122286009A_ABST
Abstract
Description
Technical Field
[0001] This application belongs to the field of intelligent driving technology, specifically relating to a method, device, and electronic device for determining information about locations outside a vehicle. Background Technology
[0002] Currently, when users want to obtain information about locations outside the vehicle while driving, one method is to identify them using their vision and existing knowledge. However, this method has low accuracy and the range and angles that users can see are limited. Another method is for users to use maps on their electronic devices to search for information about locations outside the vehicle. This method is cumbersome and there is a delay in obtaining information, affecting the interactivity between the vehicle's infotainment system and the user. Summary of the Invention
[0003] The purpose of this application is to provide a method, apparatus, and electronic device for determining off-vehicle location information, which can at least partially solve the above-mentioned problems.
[0004] In a first aspect, embodiments of this application provide a method for determining information about locations outside a vehicle, including:
[0005] Acquire user voice interaction information, which includes: first inquiry information about the location outside the vehicle;
[0006] Determine the target off-vehicle location corresponding to the first query information;
[0007] Obtain relevant information about the target location outside the vehicle and then feed that information back to the user.
[0008] Secondly, embodiments of this application provide a device for determining information about locations outside a vehicle, including:
[0009] The first acquisition module is used to acquire the user's voice interaction information, which includes: the first inquiry information about the location outside the vehicle;
[0010] The first determining module is used to determine the target off-vehicle location corresponding to the first query information;
[0011] The feedback module is used to obtain relevant information about the target location outside the vehicle and to feed back the relevant information about the target location outside the vehicle to the user.
[0012] Thirdly, embodiments of this application also provide an electronic device, including a memory, a transceiver, and a processor:
[0013] A memory for storing computer programs; a transceiver for sending and receiving data under the control of a processor; and a processor for reading the computer programs from the memory and executing the method described in the first aspect above.
[0014] Fourthly, embodiments of this application also provide a processor-readable storage medium storing a computer program for causing the processor to perform the method described in the first aspect above.
[0015] In this embodiment, the user's voice interaction information is obtained, and the target location outside the vehicle that the user wants to inquire about is determined based on the first inquiry information of the location outside the vehicle in the voice interaction information. Then, the relevant information of the target location outside the vehicle is obtained and fed back to the user. Thus, the user can know the relevant information of the location outside the vehicle in real time through voice interaction while driving, without the need for the user to use the device to search. This not only has real-time and convenience, but also improves the interactivity between the vehicle system and the user. Attached Figure Description
[0016] Figure 1 This is a flowchart illustrating the method for determining off-vehicle location information provided in an embodiment of this application;
[0017] Figure 2 This is a schematic diagram of the orientation provided in the embodiments of this application;
[0018] Figure 3 This is a schematic diagram of the map card provided in an embodiment of this application;
[0019] Figure 4 This is a schematic diagram of the structure of the off-vehicle location information determination device provided in the embodiments of this application;
[0020] Figure 5 This is a structural block diagram of the electronic device provided in the embodiments of this application. Detailed Implementation
[0021] The technical solutions of the embodiments of this application will be clearly described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of this application. All other embodiments obtained by those skilled in the art based on the embodiments of this application are within the scope of protection of this application.
[0022] The terms "first," "second," etc., used in the specification and claims of this application are used to distinguish similar objects and not to describe a specific order or sequence. It should be understood that such terms can be used interchangeably where appropriate so that embodiments of this application can be implemented in orders other than those illustrated or described herein, and the objects distinguished by "first," "second," etc., are generally of the same class and the number of objects is not limited; for example, a first object can be one or more. Furthermore, in the specification and claims, "and / or" indicates at least one of the connected objects, and the character " / " generally indicates that the preceding and following objects are in an "or" relationship.
[0023] The method for determining off-vehicle location information provided in this application will be described below with reference to the accompanying drawings, through specific embodiments and application scenarios.
[0024] like Figure 1 As shown in the figure, this application embodiment provides a method for determining information about locations outside a vehicle, which may specifically include the following steps:
[0025] Step 101: Obtain the user's voice interaction information, which includes: the first inquiry information about the location outside the vehicle.
[0026] While the target vehicle is in motion, if a user wants to inquire about information about a location outside the vehicle, the user can interact with the target vehicle via voice acquisition equipment. The target vehicle acquires the user's voice interaction information, which includes a first inquiry about the location outside the vehicle. This first inquiry is used to ask for relevant information about the location outside the vehicle. For example, the first inquiry might be: "What is the residential area ahead of the vehicle?"
[0027] It should be noted that the steps for obtaining voice interaction information are not affected by the free dialogue switch; that is, voice interaction information can be obtained regardless of whether the free dialogue switch is turned on or off.
[0028] Step 102: Determine the target off-vehicle location corresponding to the first query information.
[0029] Based on the first query information about the location outside the vehicle in the voice interaction information, the target location outside the vehicle that the user wants to query can be determined. That is, the target location outside the vehicle that the user wants to query can be determined based on the first query information. The number of target locations outside the vehicle can be one or more.
[0030] Step 103: Obtain relevant information about the target location outside the vehicle and send the relevant information about the target location outside the vehicle back to the user.
[0031] After determining the target locations outside the vehicle, obtain relevant information for each target location and feed that information back to the user so that the user can stay informed about the target locations in a timely manner.
[0032] In the above embodiments of this application, the user's voice interaction information is obtained, and the target location outside the vehicle that the user wants to inquire about is determined based on the first inquiry information of the location outside the vehicle in the voice interaction information. Then, the relevant information of the target location outside the vehicle is obtained, and the relevant information of the target location outside the vehicle is fed back to the user. Thus, the user can know the relevant information of the location outside the vehicle in real time through voice interaction while driving, without the need for the user to use the device to search. This not only has real-time and convenience, but also improves the interactivity between the vehicle system and the user.
[0033] As an optional specific embodiment, step 102, which determines the target off-vehicle location corresponding to the first query information, specifically includes steps 1021 to 1023:
[0034] Step 1021: Determine the target direction based on the first query information, where the target direction is the direction of the target vehicle. Based on the user's first query information, the target direction of the off-vehicle location (i.e., point of interest) that the user wants to recall can be determined, thereby narrowing down the recall scope.
[0035] The specific range of the direction is explained below:
[0036] like Figure 2 As shown, draw a circle with the target car's location as the center. The area within the circle represents the 360-degree directional range around the target car. The area directly in front of the car is 0 degrees (or 360 degrees), and the area directly behind the car is 180 degrees. The directional range between 45 degrees and 315 degrees is the front, the directional range between 45 degrees and 135 degrees is the right, the directional range between 135 degrees and 225 degrees is the rear, and the directional range between 225 degrees and 315 degrees is the left.
[0037] Furthermore, the directional range formed between 0 degrees and 90 degrees is the right front, the directional range formed between 90 degrees and 180 degrees is the right rear, the directional range formed between 180 degrees and 270 degrees is the left rear, and the directional range formed between 270 degrees and 360 degrees is the left front.
[0038] That is, the preset multiple directions include: front, back, left, right, right front, right back, left front, and left back, with the target direction being at least one of these directions.
[0039] Step 1022: If the first query information includes a location type, determine the location recall area based on the location type and the target direction.
[0040] If the initial inquiry includes a location type, since each location type corresponds to a recall distance, the area of the off-vehicle location the user wants to recall (i.e., the location recall area) can be further determined by using the target vehicle as the center and the recall distance as the radius, and then by using the target direction. This allows for narrowing down the recall scope. Here, the location type is the Point of Interest (POI) type, the off-vehicle location is the POI, and the location recall area is the POI recall area.
[0041] The preset location types include, but are not limited to: parks, temples, monasteries, Taoist temples, churches, mosques, hospitals, stadiums, schools, shopping malls, residential areas, tunnels, railways, bridges, buildings, mountains, rivers, lakes, seas, and other locations.
[0042] The following examples illustrate the recall distances corresponding to different location types:
[0043] The recall distance for bridges and tunnels is 1000 meters, for buildings and locations it is 500 meters, for mountains, rivers, lakes, seas, and railways it is 5000 meters, and for other location types it is 150 meters.
[0044] Additionally, if the first query does not include a location type or the location type is not among the preset location types, such as "What is the yellow flower on the left side of the car? 'Flower' does not belong to the preset location types," then no location search will be performed, and the user will be replied to according to the preset information. For example, if the first query is "What is the yellow flower on the left side of the car? 'Flower' does not belong to the preset location types," then the reply would be "I haven't learned this skill yet, I'll try again later."
[0045] Step 1023: Search for the target off-vehicle location corresponding to the location type within the location recall area.
[0046] Based on the map, specific POIs corresponding to the POI type are retrieved within the POI recall area. If multiple POIs are retrieved, all of them are used as the target off-vehicle location corresponding to the first query information, regardless of possible precise directions or whether the user can see them, in order to improve the search scope and ensure that the retrieved target off-vehicle locations match the answer the user needs. For example: Figure 2 As shown, if the target direction is forward, and multiple POIs corresponding to the POI type are found in the POI recall area corresponding to the forward direction, namely A, B, C, and D, then all four POIs will be recalled as target off-vehicle locations.
[0047] Furthermore, the specific number of target off-vehicle locations can be set, such as setting the number of target off-vehicle locations to 3. This way, when there are a large number of POIs retrieved, only the 3 POIs that are closest or have the highest relevance can be selected as target off-vehicle locations, thereby improving retrieval speed and saving computing resources.
[0048] Additionally, if no POI corresponding to the POI type can be found within the POI recall area, the user can be replied with preset information. For example, if the first query is "What is the community in front of the vehicle?", the preset information is "I did not find the community you mentioned in front of the vehicle".
[0049] It should be noted that multiple preset POI types can be prioritized. If the first query includes multiple POI types, the search will proceed according to priority, with the highest-priority POI type being searched within the POI recall area. For example, if the first query is "What kind of residential area is the location ahead?", since both "location" and "residential area" belong to multiple preset POI types, and "location" has a lower priority than "residential area", the search will proceed based on "residential area". As another example, if the first query is "Is the location to the left and ahead XX Hospital?", since both "location" and "hospital" belong to multiple preset POI types, and "location" has a lower priority than "hospital", the search will proceed based on "hospital".
[0050] In the above embodiments of this application, the recall direction is determined by the user's first query information, and the retrieval area is determined by the location asked by the user in the first query information and the recall direction. The vehicle-external location corresponding to the first query information is detected from the retrieval area. It is not necessary to search in all directions, which not only reduces the amount of computation, but also obtains the results that the user wants more accurately, thus improving the efficiency of determining vehicle-external location information.
[0051] As an optional specific embodiment, step 1022, which determines the location recall area based on the location type and the target direction, specifically includes:
[0052] Draw a circle with the current location of the target vehicle as the center and the first distance corresponding to the location type as the radius to obtain the area of the circle;
[0053] The region in the circle that corresponds to the target direction is defined as the location recall region.
[0054] A circle is drawn with the current location of the target car as the center and the recall distance (i.e., the first distance) corresponding to the POI type in the first query information as the radius. The range of this circle is a 360-degree angle range. After determining the target direction, a portion of the circle is selected according to the target direction as the POI recall area. The target direction is used to further determine the area range of the POIs that the user wants to recall, so as to narrow down the recall range by using the POI recall area. It is not necessary to search in all directions, thus reducing the amount of computation. For example, if the first distance is 1000 meters, the range of the circle formed with the target car as the center and 1000 meters as the radius is the 360-degree recall area of the target car. If the target direction is to the right front, then the fan-shaped area with a radius of 1000 meters formed between 0 degrees and 90 degrees is the POI recall area. As an optional specific embodiment, step 101, which determines the target direction according to the first query information, specifically includes:
[0055] If the first query information includes a direction and the location type is a preset location type, then the first preset direction is determined to be the target direction.
[0056] If the first query information includes a direction and the location type is not a preset location type, then the direction in the first query information is determined to be the target direction;
[0057] If the first query information does not include a direction, the second preset direction is determined as the target direction.
[0058] The first query information may or may not include a direction. If the first query information includes a direction, it is necessary to further determine the POI type in the first query information. If the POI type in the first query information is a preset location type, then the first preset direction is determined as the target direction, and the direction in the first query information is ignored.
[0059] Because mountains, rivers, lakes, and seas cover large areas and involve wide regions, they can be set as preset location types. The first preset direction can be the four-way direction, i.e., the 360-degree direction. Since mountains, rivers, lakes, and seas cover large areas and involve wide regions, the corresponding POIs may not be in the direction indicated in the first query. Therefore, it is necessary to determine the POI through the 360-degree direction. For example, if the first query is "What kind of mountain is in front?", since "mountain" is a preset location type, the target direction is the four-way direction. For this first query, the search cannot be performed according to the "front" direction, but rather according to the four-way (360-degree) direction to obtain more accurate query results.
[0060] If the first query information includes a direction, and the POI type in the first query information is not a preset point of interest type, then the direction in the first query information will be used as the target direction.
[0061] If no direction is specified in the first query information, the second preset direction will be used as the target direction. The second preset direction can be forward or can be set as needed.
[0062] As another optional specific embodiment, step 103 obtains relevant information about the target location outside the vehicle and feeds back the relevant information about the target location outside the vehicle to the user, including but not limited to at least one of the following:
[0063] The first step: Based on the target location outside the vehicle, generate map card information related to the target location outside the vehicle, and feed the map card information back to the user. The map card information includes: the location identifier of the target vehicle, the location identifier of the target location outside the vehicle, and the area of interest.
[0064] Based on the target vehicle's external locations, map card information related to those locations (i.e., relevant information about the target vehicle's external locations) can be generated and displayed on the vehicle's display screen in the form of a map card. The map card displays: the location marker of the target vehicle, the location marker of each target vehicle's external location, and the Area of Interest (AOI) and scale range of each target vehicle's external location, so that users can intuitively perceive the location and distance relationship between their own vehicle (i.e., the target vehicle) and each target vehicle's external location.
[0065] If the number of target off-vehicle locations is 1, the map card will display the complete AOI of that target off-vehicle location. If there are multiple target off-vehicle locations, only multiple target off-vehicle locations need to be displayed on the map card. The AOI of each target off-vehicle location may or may not be displayed, or only a part of it may be displayed.
[0066] In the map card, the target car is displayed with its front facing upwards. As the target car moves, its position on the map card moves accordingly. However, other map content does not move with the target car's position to ensure that the user can see complete information about the target car's location.
[0067] It should be noted that when tunnels, railways, mountains, rivers, lakes, and seas are too large to display their corresponding AOIs, only a portion of the AOI or only the POI can be displayed in the map card.
[0068] For example, if there are three target locations outside the vehicle, namely A, B, and C, a map card is generated based on these three target locations. The information displayed on this map card is as follows: Figure 3 As shown, the map displays the location markers and interest planes 31 and 32 for points of interest (A), 33 for points of interest (B), and 35 for the target vehicle. The target vehicle's location is represented by a triangle, with the vertex pointing in the direction the vehicle is facing. The map also displays the target vehicle's route 34. This map provides a clear view of the locations of the three target points and their relative positions to the target vehicle, the area of each target point, and the target vehicle's route. Furthermore, the map displays the details of the first query: what type of residential area is the preceding area (POI), indicating the POI type.
[0069] Additionally, if the map card exits the current display or triggers a display command on the display screen, the map card's display will be interrupted.
[0070] The second step: Based on the target location outside the vehicle, generate voice prompt information related to the target location outside the vehicle, and send the voice prompt information back to the user.
[0071] Based on the target location outside the vehicle, a voice prompt message "vehicle + target direction + POI type + XX" related to the target location can be generated and broadcast, so that the user can know the inquiry result without looking at the display screen while driving.
[0072] When the number of target locations outside the vehicle is 1, and the target location is XX, the voice prompt will be "Vehicle + Target Direction + POI Type + Target Location Outside the Vehicle". This voice prompt can also be displayed on the map card. For example: Figure 3 As shown, the first query is "What is the residential area in front of the vehicle?" If only three target locations A, B, and C related to residential areas are found in front of the vehicle, the voice prompt will be "There are multiple residential areas in front of the vehicle, namely: A, B, and C".
[0073] If the target location outside the vehicle is not found, a voice reply will be given according to the preset information, such as: "I haven't learned this skill yet, I'll try again later."
[0074] It should be noted that if other voice commands are triggered, the playback of the voice prompt will end.
[0075] The third step: Based on the target location outside the vehicle, generate descriptive information related to the target location outside the vehicle, and feed the descriptive information back to the user.
[0076] Based on the target location outside the vehicle, descriptive information (i.e., introductory information) related to the target location can be generated and fed back to the user via voice broadcast, so that the user can learn about the relevant descriptive information of the target location without looking at the display screen while driving, so as to better understand the target location.
[0077] As another optional specific embodiment, the first item above, generating map card information related to the target location outside the vehicle, specifically includes:
[0078] If the number of target locations outside the vehicle is greater than 1, obtain the distance between every two target locations outside the vehicle.
[0079] During the process of generating map card information related to multiple target vehicle locations, the interest planes corresponding to two target vehicle locations that are more than a preset distance apart are at least partially covered to maintain the map card scale at the preset scale.
[0080] If there are multiple target locations outside the vehicle, the distance between any two target locations outside the vehicle can be obtained. If the distance between two target locations outside the vehicle is greater than a preset distance, the AOIs corresponding to the two target locations outside the vehicle will be partially overlaid to ensure that the map scale is the preset scale and to avoid the situation where the map scale is reduced due to the large distance between the two POIs, making it difficult for users to see clearly.
[0081] The preset distance can be set as needed, or adjusted according to a preset scale. The preset scale can be adjusted according to user habits or needs to facilitate user viewing of the display screen.
[0082] As another optional specific embodiment, the second step above generates voice prompt information related to the target location outside the vehicle, including steps 1031 to 1034:
[0083] Step 1031: If the first inquiry information does not include location information, generate a first voice prompt based on the target location outside the vehicle, wherein the voice prompt related to the target location outside the vehicle is the first voice prompt.
[0084] If the first query information includes a POI type but not location information, then the target location outside the vehicle is retrieved based on the POI type. A first voice prompt is then generated and broadcast based on the target location outside the vehicle. The location information refers to information about the POI, which can be the name of the POI.
[0085] For example: The first query is "What's that place to the left front?" This first query does not include location information. "Place" is a POI type, and "left front" is the target direction. Therefore, the search is performed according to the direction of "place" in "left front" to obtain the target location outside the vehicle. Another example: The first query is "What kind of mountain is that ahead?" This first query does not include location information. However, since "mountain" is a POI type and a preset point of interest type, the surrounding directions are used as the target direction. The search is performed according to the direction of "mountain" around the vehicle to obtain the target location outside the vehicle. Yet another example: The first query is "Is that a park ahead?" This first query does not include location information. However, "park" is a POI type, and "ahead" is the target direction. Therefore, the search is performed according to the direction of "park" in "ahead" to obtain the target location outside the vehicle.
[0086] Step 1032: If the first query information includes location information, match the location information with the target vehicle location.
[0087] If the first query information includes both POI type and location information, then the target vehicle location is retrieved in the POI recall area according to the POI type. Then the location information is matched with the target vehicle location to determine whether the target vehicle location matches the location information. If they do not match, then step 1033 is executed; if they match, then step 1034 is executed.
[0088] It should be noted that if there are multiple target locations outside the vehicle, it is determined whether the location information matches multiple target locations outside the vehicle. If none of the multiple target locations outside the vehicle match the location information, step 1033 is executed. If one of the multiple target locations outside the vehicle matches the location information, step 1034 is executed.
[0089] For example: The first query is "Is the location ahead XX?", where "location" is the POI type and "XX" is the location information. Searching the POI recall area by "location" yields multiple target vehicle locations. Then, XX is matched with the target vehicle locations to determine if any of the target vehicle locations match XX. As another example: The first query is "Is the area ahead XX residential area?", where "residential area" is the POI type and "XX" is the location information. Searching the POI recall area by "residential area" yields target vehicle locations. Then, XX is matched with the target vehicle locations to determine if any of the target vehicle locations match XX.
[0090] Step 1033: If the location information does not match the target vehicle location, generate a second voice prompt based on the target vehicle location and the information that the location information does not match the target vehicle location. The voice prompt related to the target vehicle location is the second voice prompt.
[0091] If the location information does not match multiple target locations outside the vehicle, a second voice prompt is generated and broadcast based on the mismatch information and the target locations outside the vehicle. This second voice prompt can indicate that no POI type location information was found. For example, if the first inquiry is "Is XX Hospital ahead?", the second voice prompt is "I did not find XX Hospital ahead of the vehicle." Alternatively, the second voice prompt can indicate that no POI type location information was found, but multiple target locations outside the vehicle corresponding to the POI type were found. For example, if the first inquiry is "Is XX Hospital ahead?", the second voice prompt is "I did not find XX Hospital ahead of the vehicle, but there are multiple other hospitals ahead, namely Hospital A, Hospital B, and Hospital C."
[0092] Step 1034: If the location information matches the target location outside the vehicle, generate a third voice prompt based on the location information and the information that the location information matches the target location outside the vehicle. The voice prompt related to the target location outside the vehicle is the third voice prompt.
[0093] If the location information matches the first target location among multiple target locations outside the vehicle (i.e., the location information is included in multiple target locations outside the vehicle), then a third voice prompt is generated and broadcast based on the matching information and the location information. This third voice prompt can indicate that a POI-type location has been found. For example, if the first inquiry is "Is there XX Hospital ahead?", the third voice prompt will be "There is XX Hospital ahead of the vehicle." This third voice prompt can also indicate that multiple target locations outside the vehicle corresponding to a POI type have been found, where the first target location outside the vehicle is the location information. For example, if the first inquiry is "Is there XX Hospital ahead?", the third voice prompt will be "There are multiple hospitals ahead of the vehicle, namely Hospital A, Hospital B, and Hospital C, where Hospital A is the XX Hospital you are looking for."
[0094] The above embodiments generate different types of voice prompts based on different situations, and can provide targeted answers to the user's first inquiry, thereby improving the user experience.
[0095] As another optional specific embodiment, the third item above generates descriptive information related to the target location outside the vehicle based on the target location outside the vehicle, and feeds back the descriptive information to the user, specifically including:
[0096] Step 1035: If the target vehicle location includes a preset vehicle location, generate second query information for the target vehicle location, wherein the preset vehicle location represents a location of the target type.
[0097] Step 1036: If descriptive information related to the target vehicle location is generated within a preset time period, the descriptive information is fed back to the user.
[0098] After obtaining the target location outside the vehicle, it is determined whether the target location outside the vehicle includes a preset location outside the vehicle (such as a scenic spot POI). If the target location outside the vehicle includes a preset location outside the vehicle, a second query is automatically generated about the target location outside the vehicle (i.e., the preset location outside the vehicle). This second query is a request for information about the scenic spot, such as: Please introduce scenic spots A and B. Adding colons and commas to the second query can prevent users from accidentally triggering the query through voice.
[0099] Furthermore, based on the second query information, a description of the target vehicle's external location is generated. If the description is generated within a preset time period, the description is broadcast.
[0100] If descriptive information is generated within a preset timeframe during the voice prompt playback, the descriptive information will continue to be played after the voice prompt, ensuring a seamless transition between the two rounds of queries. This effectively presents the results of both rounds as a single query, enhancing the richness and intelligence of the query outcome. Furthermore, a waiting period can be set after the descriptive information is played, after which the user will automatically exit the voice playback page.
[0101] If no description information is generated within the preset time, in order to avoid discontinuity between the voice prompts and the description information, the description information will no longer be generated or, even if it is generated, it will no longer be broadcast, i.e., the description information will be released.
[0102] It should be noted that the voice image used to broadcast voice prompts can be the same as or different from the voice image used to broadcast descriptive information.
[0103] Further, if step 1035 includes a preset location outside the vehicle as part of the target location outside the vehicle, generating second query information for the target location outside the vehicle includes:
[0104] If the target vehicle-exterior location includes N preset vehicle-exterior locations, and there is an inclusion relationship between the interest surfaces of at least two of the N preset vehicle-exterior locations, then the smaller preset vehicle-exterior location among the preset vehicle-exterior locations with the inclusion relationship is removed to obtain P preset vehicle-exterior locations, and the second query information of the P preset vehicle-exterior locations is generated.
[0105] Where N and P are both positive integers, and N is greater than P.
[0106] If there are multiple target off-vehicle locations, and at least two of the target off-vehicle locations have an inclusion relationship (i.e., a parent-child relationship) between their AOIs (i.e., the AOI of one target off-vehicle location is part of the AOI of another target off-vehicle location), then the target off-vehicle location corresponding to the smaller AOI is directly removed (i.e., the child target off-vehicle location is removed, and only the parent target off-vehicle location is displayed). In this way, the sub-facilities in the area can be identified. By processing all target off-vehicle locations with inclusion relationships in the multiple target off-vehicle locations in the above way, P target off-vehicle locations are obtained after all processing, and P second query information related to the target off-vehicle locations is generated, which can avoid the duplicate generation of second query information.
[0107] The second inquiry information can be one second inquiry information corresponding to one target location outside the vehicle, or P target locations outside the vehicle can correspond to a total second inquiry information.
[0108] As another optional specific embodiment, the voice interaction information is obtained through a target voice acquisition device, and the method further includes:
[0109] Step 104: Upon receiving the first instruction from the target voice acquisition device, execute the first instruction;
[0110] Step 105: If a second instruction is received from a non-target voice acquisition device, and the instruction type of the second instruction is a preset instruction type, then the second instruction is not executed; if the instruction type of the second instruction is a non-preset instruction type, then the second instruction is executed.
[0111] Executing a preset instruction type will interrupt the feedback of relevant information about the target location outside the vehicle.
[0112] If the first query information is obtained through a target voice acquisition device (e.g., the voice acquisition device corresponding to the driver), the target voice acquisition device can control the currently displayed map card and the voice broadcast content. If the user's first command is obtained through the target voice acquisition device, the first command will be executed regardless of whether its command type is a preset command type. That is, if the command type of the first command is a command type that requires voice broadcast, the current voice broadcast will be stopped and the content related to the first command will be broadcast; if the command type of the first command is a command type that requires display on the screen, the current map card display will be stopped and the content related to the first command will be displayed.
[0113] If a user's second command is obtained through a non-target voice acquisition device (such as a voice acquisition device in the front passenger seat or rear seat), and the command type of the second command is a preset command type, then the second command will not be executed to avoid other non-driving seats accidentally interrupting the current map card display and voice broadcast. That is, the second command obtained through a non-target voice acquisition device will not affect the current voice broadcast and map card display. If the command type of the second command is not a preset command type, then the second command will be executed if the second command will not affect the current voice broadcast and map card display.
[0114] The process of determining the location information outside the vehicle is illustrated below through a specific embodiment:
[0115] When a user inquires about location information outside the vehicle via voice interaction, a circle is drawn with the location of the vehicle (i.e., the target vehicle) at the time the query (i.e., the voice interaction) is triggered as the center, and the area within the circle x meters (i.e., the first distance) is valid.
[0116] Recall Scope: Supports voice queries from eight directions: left, right, front, rear, left front, left rear, right front, and right rear. For the direction definitions, the front, rear, left, and right directions are centered on the vehicle's position, with the front of the car directly in front being 0 degrees, plus or minus 45 degrees equal to "front," and so on for other directions. Similarly, the left front, left rear, right front, and right rear directions are centered on the vehicle's position, with the front of the car directly in front being 0 degrees, minus 90 degrees equal to "left front," plus 90 degrees equal to "right front," and so on for other directions.
[0117] When a user triggers a query, the vehicle system will respond with a location outside the vehicle in the direction specified by the user via a voice map card. At the same time, the system will display the vehicle's location, the location outside the vehicle, and the AOI (Area of Interest) on the voice map card, allowing the user to perceive the location and distance relationship between the vehicle and the location inquired about while obtaining the answer.
[0118] When users ask for location-based points of interest (POIs) outside the vehicle, the system supports voice-based question-and-answer functionality, allowing users to specify directions such as left, right, front, back, left front, left back, right front, and right back via voice commands.
[0119] The following explains the
Off-site Recall Strategy
[0120] Scope: Draw a circle within x meters of the vehicle's location when the query is triggered. The area within this circle is the effective recall range.
[0121] Direction: Front, back, left, and right are defined with the vehicle's position as the center. The front of the vehicle is directly in front, which is 0 degrees. Adding or subtracting 45 degrees gives "front". Other directions follow the same principle.
[0122] Left front, left rear, right front, and right rear are defined with the vehicle's position as the center. The front of the vehicle is 0 degrees, minus 90 degrees is "left front", and plus 90 degrees is "right front", and so on for other directions.
[0123] Recall method: Within a specified direction range, recall POI results of the specified location type. If there are multiple matching results, all of them will be recalled, regardless of possible precise directions or whether the user can see them.
[0124] The following explains the matching and response strategy:
[0125] 1. When no direction is specified for questions and answers outside the vehicle, the default matching method is based on the direction the vehicle is facing:
[0126] (1) If there is a matching result, reply to the user: "The {xx type} in front of the vehicle is {xx}" ----- generate the card (i.e. generate the corresponding map card), and reply with the description template.
[0127] (2) If no match is found, the fallback reply to the user is: "I did not find the {xx type} you mentioned in front of the vehicle" ----- no card is generated (i.e. no map card is generated), fallback reply.
[0128] II. When there is a specified direction / default forward in the question-and-answer section outside the vehicle, the response strategy is as follows: single result / multiple results / no result:
[0129] (1) When there is a single matching result, reply to the user: "The {xx type} of the vehicle {direction} is {xx}" ----- issue the card, and reply with the description template.
[0130] (2) When there are multiple matching results, reply to the user: "The vehicle {direction} has multiple {location names}, namely {location name 1}, {location name 2}, and {location name 3}" ----- issue card, description template reply.
[0131] (3) If there is no matching result for the corresponding direction, reply to the user: "I did not find the {xx type} you mentioned in vehicle {direction}" ----- no card is issued, a fallback reply.
[0132] 3. For responses to "Is it yes or no", prioritize recalling responses based on "What is it":
[0133] (1) When there is a single matching result, regardless of whether there is a match, the response should remain consistent with "what is it":
[0134] For ordinary POIs (i.e., POIs that are not located in mountains, rivers, lakes, or seas): "The location type of the vehicle's {direction} is {location name}".
[0135] Mountains, Rivers, Lakes and Seas POI: "The {location type} near the vehicle is {location name}".
[0136] (2) When there are multiple matching results:
[0137] Common POI:
[0138] If the "yes / no" question entity (i.e., the location outside the vehicle) is included in the recall list, reply to the user: "The vehicle {direction} has the {location type} {location name} you mentioned."
[0139] If the "Yes or No" question entity is not included in the recall list, reply to the user: "The vehicle {direction} has multiple {location types}, namely {location name 1}, {location name 2}, and {location name 3}."
[0140] Mountains, Rivers, Lakes and Seas POI:
[0141] If the "Yes or No" question entity is included in the recall list, reply to the user: "There is the {location type}{location name} you mentioned near the vehicle."
[0142] If the "Yes or No" question entity is not included in the recall list, reply to the user: "There are multiple {location types} near the vehicle, namely {location name 1}, {location name 2}, and {location name 3}."
[0143] (3) If there is no matching result for the corresponding direction, then reply:
[0144] Regular POI: "I didn't find the {xx type} you mentioned in vehicle {direction}" ----- No card issued, a fallback reply.
[0145] POI (Mountains, Rivers, Lakes, and Seas): "I didn't find the {xx type} you mentioned near the vehicle." ----- No card required, guaranteed response.
[0146] IV. The issue of "mountains, rivers, lakes, and seas":
[0147] (1) Without associating with the user-specified direction, directly reply with the nearest x results (e.g., within xx kilometers).
[0148] If there are multiple results, the reply will be "Help you find that there are multiple {location types} near the car, namely {location name 1}, {location name 2}, and {location name 3}".
[0149] If there is only one result, the reply will be "Help you find the {location type} near the car is {location name}".
[0150] If no results are found, reply with "I didn't find the {xx type} you mentioned near the vehicle."
[0151] 5. For queries or other statements of POI type that are not supported, such as "What is the yellow flower on the left side of the car?", the fallback reply is "I haven't learned this skill yet, I'll try again later."
[0152] The following explains the supported location types:
[0153] Currently, the following location types are supported for questions: park, temple / monastery / Taoist temple, church, mosque, hospital, stadium, school, shopping mall, residential area, tunnel, railway, bridge, building, mountain, river, lake, sea, location, etc.
[0154] The following explains the content of the [Contextual Strategy]:
[0155] When the preceding text is a question-and-answer session about locations outside the vehicle, the following text will introduce / query the attributes of the entity (i.e., the location outside the vehicle) found in the preceding text.
[0156] The following explains the content of the "first inquiry information and supporting statements for the voice response":
[0157] 1. In the query, if the question asks what "poitype" means, then "poitype" refers to the location type or POI type.
[0158] What's on the left? ----- What is it? Recall by "Location".
[0159] What mountain is next to us? ----- What is it? Press "mountain" to recall.
[0160] 2. In the query, is "poitype" a "POI"?
[0161] Is the preceding residential area XX? ----- To confirm, recall by "residential area".
[0162] Is the location on the left XX? --- If yes, click "Location" to recall.
[0163] Third, although it is a yes / no sentence structure, it only contains "poitype":
[0164] Is there a park nearby? ----- What is it? Press "park" to recall.
[0165] 4. When the query contains no positive response, a fallback response is used, such as:
[0166] Is the one before A? ----- Not supported, fallback answer.
[0167] Is the preceding line B? ----- Not supported, fallback answer.
[0168] Is the preceding line a C? ----- Not supported, fallback answer.
[0169] Is the red scenic area in front (this question is not supported) the former site of XX? ----- Not supported, a fallback answer (just like asking "Are the flowers in front sunflowers?").
[0170] 5. It is also supported when the query does not actually contain "poitype", but the POI name contains the "poitype" field, such as:
[0171] Is this XX Hospital on the left? ----- To confirm, press "Hospital".
[0172] 6. When the query explicitly contains a location other than "location", prioritize recall based on other locations, such as:
[0173] What neighborhood is the location on the left? ----- What is it? Recall by "neighborhood".
[0174] Is the location on the left XX residential area? --- If so, recall by "residential area".
[0175] The following is an explanation of the contents of the [Voice Map Card]:
[0176] I. Elements: Vehicle location, single / multiple markers + location name, scale range.
[0177] II. Display Strategy:
[0178] (1) The front of the vehicle is facing upwards;
[0179] (2) The map card does not move with the vehicle icon (i.e., the location marker of the target vehicle), but the vehicle icon (i.e., the location marker of the target vehicle) moves on the map;
[0180] (3) Normal capping between AOIs corresponding to multiple POIs;
[0181] (4) Display the AOI area surface:
[0182] When the number of recall results (i.e., the target vehicle's external location) is equal to 1, the map card displays the complete AOI surface of the POI;
[0183] When the number of recall results is greater than 1, the AOI surface is no longer considered, and only the POI point is displayed in its entirety.
[0184] (5) Areas without AOI, such as mountains, rivers, lakes, seas, railways, and tunnels, will not be displayed;
[0185] (6) Maximum number of POIs of each type that can be displayed: 3;
[0186] (7) Recall distance for each POI type:
[0187] The recall distance in front of and behind bridges / tunnels is 1000 meters, and the recall distance in other directions is 150 meters.
[0188] The recall distance for buildings and locations is 500 meters;
[0189] The recall distance for the mountain, river, lake, sea, and railway projects is 5000 meters.
[0190] The following explains the content of the "Reply for Scenic Spots and Historic Sites" section, where scenic spots and historic sites refer to pre-set locations outside the vehicle:
[0191] When the recalled POIs are scenic spots or landmarks, the system will further retrieve information about the POI from the cloud and reply to the user, increasing the richness and intelligence of the response.
[0192] 1. Conditions
[0193] This process is triggered when the recall location is determined to be a scenic spot.
[0194] II. Multi-location processing strategy
[0195] If there are multiple locations outside the vehicle in the reply, select the one with the location type "scenic spot" and make a request there.
[0196] III. Request query
[0197] "Please introduce the scenic spots: A and B", such as "Please introduce the scenic spots: Square A and Park B";
[0198] The colon ":" is used to avoid the possibility of accidental triggering by users;
[0199] When there are multiple locations, use a comma to separate them;
[0200] The maximum number of requested locations is 3 (i.e., the maximum number of locations displayed on the interface is 3). When multiple locations have a parent-child relationship, if the parent-child relationship can be clearly determined, the parent POI will be displayed and the child POI will not be displayed, in order to determine the child facilities in the area.
[0201] IV. Effective waiting range for the second round
[0202] A request was successfully sent to the cloud;
[0203] At the same time, exiting the map card will end the waiting process;
[0204] Additionally, if the user actively exits the map card in the current audio region, triggers other interruptions, or anything that would affect the display of the current map card or the playback of voice information, the process will be interrupted and will wait.
[0205] From a user perspective, the goal is to treat the two rounds of responses as a single round of experience, and to treat the first and second rounds together as a single-round question-and-answer session.
[0206] If the wait is interrupted, the content of the second round of replies will be released directly without being broadcast.
[0207] V. Second Round of Response Broadcast
[0208] After the model successfully delivers the broadcast content, and within the valid waiting range of the second round, the response content of the second round is broadcast after the broadcast of the first round of map cards;
[0209] The response content of the second-round model does not display its voice map card when it is broadcast; it only broadcasts the text-to-speech (TTS) script content through speech synthesis.
[0210] If the first round of map card broadcasts is not completed, the second round of responses will be broadcast after the first round of broadcasts is completed.
[0211] If, during the waiting period for the first round of broadcasts, the user actively exits the map card or triggers other actions that interrupt the current map card display or voice broadcast, the waiting period ends and the content to be broadcast in the second round is released.
[0212] If a user actively exits the map card or triggers other actions that interrupt the current map card display or voice broadcast during the current second round of broadcasts, the broadcast will be interrupted.
[0213] Regardless of whether the free dialogue switch is enabled, the above expected performance can be met;
[0214] Even without a map card on the rear screen, the second round of broadcasts can still be connected normally. If the user triggers other intentions to interrupt the voice broadcast, the broadcast will be interrupted.
[0215] VI. Interface effects during the second round of broadcasting
[0216] Keep the current map card displayed (if any), and exit after the voice broadcast is completed (following the general timeout policy);
[0217] The voice broadcast image remains unchanged for both rounds;
[0218] Neither the first nor the second round of broadcast content will be displayed on the screen;
[0219] During the second round of broadcasts, general input commands (such as general air conditioning commands, seat adjustment commands, etc.) that do not affect the map card display or voice broadcast commands will not affect the second round of broadcasts and displays.
[0220] If, during the second round of broadcasting, the input command in the current audio region (i.e., the audio region of the target voice acquisition device) affects the map card display or the voice broadcast command, then the second round of broadcasting and display will end.
[0221] During the second round of broadcasting, if an input command outside the current audio region affects the broadcast command, the map card will exit after a timeout (following the general interruption timeout strategy).
[0222] In summary, this embodiment determines the recall direction of points of interest (POIs) based on the user's first query information. Then, it determines the retrieval area of POIs based on the type of POI requested by the user in the first query information and the recall direction. The target off-vehicle location corresponding to the first query information is detected from the retrieval area. This eliminates the need to search in all directions, reducing computational load and providing more accurate query results, thus improving the efficiency of determining off-vehicle location information. Furthermore, a map card is generated based on the target off-vehicle location, allowing the user to intuitively see the range of the retrieved POIs, their relative position to the vehicle, distance, and other information, enhancing the user experience. Additionally, a voice prompt is generated and broadcast based on the first query information and the target off-vehicle location, allowing the user to know the query results without looking at the display screen while driving, improving driving safety. Moreover, after acquiring the user's second command through a non-target voice acquisition device, if the command type of the second command is a preset command type that affects the current voice broadcast and map card display, the second command is not executed. This prevents other passengers from accidentally triggering commands that could interrupt the current map card and voice broadcast.
[0223] The method for determining off-vehicle location information provided in this application can be executed by an off-vehicle location information determining device. This application uses the example of an off-vehicle location information determining device executing the method to illustrate the off-vehicle location information determining device provided in this application.
[0224] like Figure 4 As shown in the figure, this application embodiment also provides a vehicle-external location information determination device 400, specifically including:
[0225] The first acquisition module 401 is used to acquire the user's voice interaction information, which includes: the first inquiry information about the location outside the vehicle;
[0226] The first determining module 402 is used to determine the target off-vehicle location corresponding to the first inquiry information;
[0227] The feedback module 403 is used to obtain relevant information about the target location outside the vehicle and to feed back the relevant information about the target location outside the vehicle to the user.
[0228] Optionally, the first determining module 402 is specifically used for:
[0229] The target direction is determined based on the first query information, where the target direction is the direction of the target vehicle.
[0230] If the first inquiry information includes a location type, the location recall area is determined based on the location type and the target direction;
[0231] Search for the target off-vehicle location corresponding to the location type within the location recall area.
[0232] Optionally, when the first determining module 402 determines the location recall area based on the location type and the target direction, it is specifically used for:
[0233] Draw a circle with the current location of the target vehicle as the center and the first distance corresponding to the location type as the radius to obtain the area of the circle;
[0234] The region in the circle that corresponds to the target direction is defined as the location recall region.
[0235] Optionally, when determining the target direction based on the first query information, the first determining module 402 is specifically used for:
[0236] If the first query information includes a direction and the location type is a preset location type, then the first preset direction is determined to be the target direction.
[0237] If the first query information includes a direction and the location type is not a preset location type, then the direction in the first query information is determined to be the target direction;
[0238] If the first query information does not include a direction, the second preset direction is determined as the target direction.
[0239] Optionally, the feedback acquisition module 403 is specifically used for at least one of the following:
[0240] Based on the target location outside the vehicle, generate map card information related to the target location outside the vehicle, and feed the map card information back to the user. The map card information includes: the location identifier of the target vehicle, the location identifier of the target location outside the vehicle, and the area of interest.
[0241] Based on the target location outside the vehicle, generate voice prompt information related to the target location outside the vehicle, and feed the voice prompt information back to the user;
[0242] Based on the target location outside the vehicle, generate descriptive information related to the target location outside the vehicle, and feed the descriptive information back to the user.
[0243] Optionally, when the feedback acquisition module 403 generates map card information related to the target location outside the vehicle based on the target location outside the vehicle, it is specifically used for:
[0244] If the number of target locations outside the vehicle is greater than 1, obtain the distance between every two target locations outside the vehicle.
[0245] During the process of generating map card information related to multiple target vehicle locations, the interest planes corresponding to two target vehicle locations that are more than a preset distance apart are at least partially covered to maintain the map card scale at the preset scale.
[0246] Optionally, when the feedback acquisition module 403 generates voice prompt information related to the target location outside the vehicle based on the target location outside the vehicle, it is specifically used for:
[0247] If the first inquiry information does not include location information, a first voice prompt is generated based on the target location outside the vehicle, and the voice prompt related to the target location outside the vehicle is the first voice prompt.
[0248] If the first query information includes location information, the location information is matched with the target location outside the vehicle;
[0249] If the location information does not match the target location outside the vehicle, a second voice prompt is generated based on the target location outside the vehicle and the information that the location information does not match the target location outside the vehicle. The voice prompt related to the target location outside the vehicle is the second voice prompt.
[0250] If the location information matches the target location outside the vehicle, a third voice prompt is generated based on the location information and the information that the location information matches the target location outside the vehicle. The voice prompt related to the target location outside the vehicle is the third voice prompt.
[0251] Optionally, when the feedback acquisition module 403 generates descriptive information related to the target location outside the vehicle based on the target location outside the vehicle and feeds the descriptive information back to the user, it is specifically used for:
[0252] If the target vehicle-exterior location includes a preset vehicle-exterior location, a second query information for the target vehicle-exterior location is generated, wherein the preset vehicle-exterior location represents a location of the target type;
[0253] If descriptive information related to the target vehicle location is generated within a preset time period, the descriptive information will be fed back to the user.
[0254] Optionally, when the feedback acquisition module 403 generates the second query information for the target vehicle location, if the target vehicle location includes a preset vehicle location, it is specifically used for:
[0255] If the target vehicle-exterior location includes N preset vehicle-exterior locations, and there is an inclusion relationship between the interest surfaces of at least two of the N preset vehicle-exterior locations, then the smaller preset vehicle-exterior location among the preset vehicle-exterior locations with the inclusion relationship is removed to obtain P preset vehicle-exterior locations, and the second query information of the P preset vehicle-exterior locations is generated.
[0256] Where N and P are both positive integers, and N is greater than P.
[0257] Optionally, the voice interaction information is acquired through a target voice acquisition device, and the device further includes:
[0258] The first execution module is used to execute the first instruction upon receiving a first instruction from the target voice acquisition device;
[0259] The second execution module is configured to, when a second instruction is received from a non-target voice acquisition device, not execute the second instruction if the instruction type of the second instruction is a preset instruction type, and execute the second instruction if the instruction type of the second instruction is a non-preset instruction type.
[0260] Executing a preset instruction type will interrupt the feedback of relevant information about the target location outside the vehicle.
[0261] It should be noted that the above-mentioned vehicle location information determination device provided in this application embodiment can implement all the method steps implemented in the above-mentioned vehicle location information determination method embodiment, and can achieve the same technical effect. Here, the parts that are the same as those in the method embodiment and the beneficial effects will not be described in detail.
[0262] It should be noted that the division of units in the embodiments of this application is illustrative and only represents one logical functional division. In actual implementation, other division methods may be used. Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated units described above can be implemented in hardware or as software functional units.
[0263] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a processor-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) or processor to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.
[0264] like Figure 5 As shown, embodiments of this application also provide an electronic device, including a memory 520, a transceiver 510, and a processor 500:
[0265] Memory 520 is used to store computer programs;
[0266] Transceiver 510 is used to send and receive data under the control of the processor;
[0267] Processor 500 is configured to read a computer program from memory and execute the steps of the method for determining off-vehicle location information as described in any of the above embodiments.
[0268] Among them, Figure 5 In this context, the bus architecture can include any number of interconnected buses and bridges, specifically linking various circuits together, represented by one or more processors (processor 500) and memory (memory 520). The bus architecture can also link various other circuits such as peripheral devices, voltage regulators, and power management circuits, which are well known in the art and therefore will not be described further herein. The bus interface provides an interface. The transceiver 510 can be multiple elements, including transmitters and receivers, providing a unit for communicating with various other devices over transmission media, including wireless channels, wired channels, optical fibers, etc. The processor 500 is responsible for managing the bus architecture and general processing, and the memory 520 can store data used by the processor 500 during operation.
[0269] The processor 500 can be a central processing unit (CPU), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or a complex programmable logic device (CPLD). The processor can also adopt a multi-core architecture.
[0270] The processor executes the method for determining off-vehicle location information provided in this application embodiment by calling a computer program stored in memory, according to the obtained executable instructions. The processor and memory can also be physically separated.
[0271] It should be noted that the electronic device provided in this application embodiment can implement all the method steps implemented in the above-mentioned method embodiment for determining the information of the vehicle's external location, and can achieve the same technical effect. Here, the parts that are the same as those in the method embodiment and the beneficial effects will not be described in detail.
[0272] Embodiments of this application also provide a processor-readable storage medium storing a computer program for causing the processor to execute the above-described method for determining off-vehicle location information.
[0273] The processor-readable storage medium can be any available medium or data storage device that the processor can access, including but not limited to magnetic memory (e.g., floppy disk, hard disk, magnetic tape, magneto-optical disk (MO)), optical memory (e.g., CD, DVD, BD, HVD), and semiconductor memory (e.g., ROM, EPROM, EEPROM, non-volatile memory (NAND FLASH), solid-state drive (SSD)).
[0274] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product implemented on one or more computer-usable storage media (including, but not limited to, disk storage and optical storage) containing computer-usable program code.
[0275] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer-executable instructions. These computer-executable instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart... Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.
[0276] These processor-executable instructions may also be stored in a processor-readable memory that can direct a computer or other programmable data processing device to operate in a particular manner, such that the instructions stored in the processor-readable memory produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.
[0277] These processors can execute instructions that can also be loaded onto a computer or other programmable data processing device, causing a series of operational steps to be performed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable device for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.
[0278] Obviously, those skilled in the art can make various modifications and variations to this application without departing from the spirit and scope of this application. Therefore, if such modifications and variations fall within the scope of the claims of this application and their equivalents, this application also intends to include such modifications and variations.
Claims
1. An information determination method for an off-vehicle location, characterized by, include: Acquire user voice interaction information, which includes: first inquiry information about the location outside the vehicle; Determine the target off-vehicle location corresponding to the first query information; Obtain relevant information about the target location outside the vehicle and then feed that information back to the user.
2. The method of claim 1, wherein, Determining the target off-vehicle location corresponding to the first query information includes: The target direction is determined based on the first query information, where the target direction is the direction of the target vehicle. If the first inquiry information includes a location type, the location recall area is determined based on the location type and the target direction; Search for the target off-vehicle location corresponding to the location type within the location recall area.
3. The method of claim 2, wherein, The step of determining the location recall area based on the location type and the target direction includes: Draw a circle with the current location of the target vehicle as the center and the first distance corresponding to the location type as the radius to obtain the area of the circle; The region in the circle that corresponds to the target direction is defined as the location recall region.
4. The method of claim 2, wherein, Determining the target direction based on the first query information includes: If the first query information includes a direction and the location type is a preset location type, then the first preset direction is determined to be the target direction. If the first query information includes a direction and the location type is not a preset location type, then the direction in the first query information is determined to be the target direction; If the first query information does not include a direction, the second preset direction is determined as the target direction.
5. The method of claim 1, wherein, The step of obtaining relevant information about the target location outside the vehicle and feeding back that information to the user includes at least one of the following: Based on the target location outside the vehicle, generate map card information related to the target location outside the vehicle, and feed the map card information back to the user. The map card information includes: the location identifier of the target vehicle, the location identifier of the target location outside the vehicle, and the area of interest. Based on the target location outside the vehicle, generate voice prompt information related to the target location outside the vehicle, and feed the voice prompt information back to the user; Based on the target location outside the vehicle, generate descriptive information related to the target location outside the vehicle, and feed the descriptive information back to the user.
6. The method of claim 5, wherein, The step of generating map card information related to the target location outside the vehicle, based on the target location outside the vehicle, includes: If the number of target locations outside the vehicle is greater than 1, obtain the distance between every two target locations outside the vehicle. During the process of generating map card information related to multiple target vehicle locations, the interest planes corresponding to two target vehicle locations that are more than a preset distance apart are at least partially covered to maintain the map card scale at the preset scale.
7. The method of claim 5, wherein, The step of generating voice prompt information related to the target location outside the vehicle, based on the target location outside the vehicle, includes: If the first inquiry information does not include location information, a first voice prompt is generated based on the target location outside the vehicle, and the voice prompt related to the target location outside the vehicle is the first voice prompt. If the first query information includes location information, the location information is matched with the target location outside the vehicle; If the location information does not match the target location outside the vehicle, a second voice prompt is generated based on the target location outside the vehicle and the information that the location information does not match the target location outside the vehicle. The voice prompt related to the target location outside the vehicle is the second voice prompt. If the location information matches the target location outside the vehicle, a third voice prompt is generated based on the location information and the information that the location information matches the target location outside the vehicle. The voice prompt related to the target location outside the vehicle is the third voice prompt.
8. The method of claim 5, wherein, The step of generating descriptive information related to the target location outside the vehicle based on the target location outside the vehicle, and feeding the descriptive information back to the user, includes: If the target vehicle-exterior location includes a preset vehicle-exterior location, a second query information for the target vehicle-exterior location is generated, wherein the preset vehicle-exterior location represents a location of the target type; If descriptive information related to the target vehicle location is generated within a preset time period, the descriptive information will be fed back to the user.
9. The method of claim 8, wherein, When the target vehicle location includes a preset vehicle location, a second query for the target vehicle location is generated, including: If the target vehicle-exterior location includes N preset vehicle-exterior locations, and there is an inclusion relationship between the interest surfaces of at least two of the N preset vehicle-exterior locations, then the smaller preset vehicle-exterior location among the preset vehicle-exterior locations with the inclusion relationship is removed to obtain P preset vehicle-exterior locations, and the second query information of the P preset vehicle-exterior locations is generated. Where N and P are both positive integers, and N is greater than P.
10. The method of claim 1, wherein, The voice interaction information is acquired through a target voice acquisition device, and the method further includes: Upon receiving a first instruction from the target voice acquisition device, execute the first instruction; If a second instruction is received from a non-target voice acquisition device, and the instruction type of the second instruction is a preset instruction type, then the second instruction will not be executed; if the instruction type of the second instruction is a non-preset instruction type, then the second instruction will be executed. Executing a preset instruction type will interrupt the feedback of relevant information about the target location outside the vehicle.
11. An information determination device for an off-vehicle location, characterized by comprising: include: The first acquisition module is used to acquire the user's voice interaction information, which includes: the first inquiry information about the location outside the vehicle; The first determining module is used to determine the target off-vehicle location corresponding to the first query information; The feedback module is used to obtain relevant information about the target location outside the vehicle and to feed back the relevant information about the target location outside the vehicle to the user.
12. An electronic device, comprising: It includes a processor and a memory, the memory storing a program or instructions that can run on the processor, the program or instructions being executed by the processor to implement the steps of the method for determining information about off-vehicle locations as described in any one of claims 1-10.
13. A readable storage medium, characterized by, The readable storage medium stores a program or instructions that, when executed by a processor, implement the steps of the method for determining information about locations outside the vehicle as described in any one of claims 1-10.