Method and device for determining reason of abnormal travel event, electronic equipment and storage medium

Abstract

The invention provides a reason determination method and device for an abnormal travel event, electronic equipment and a storage medium, and relates to the technical field of artificial intelligence such as semantic understanding, large language models and intelligent navigation. The method comprises the steps of obtaining a current travel plan and historical travel preferences of a user; determining an abnormal travel event existing in the current travel plan by using the historical travel preference; determining an event site corresponding to the abnormal travel event, and obtaining public information corresponding to the event site; and inputting the abnormal travel event, the public information and the abnormal reason generation indication as first prompt information into a preset first large language model to obtain an output reason description corresponding to the abnormal travel event. According to the method, a difference part is determined as an abnormal travel event by comparing a current travel plan with historical travel preferences, and then the abnormal travel event, public information corresponding to an event site of the abnormal travel event and an abnormal reason generation instruction are jointly used as prompt information to be input into a large language model. And the reason description corresponding to the abnormal travel event is obtained through analysis under indication by means of the first large language model, so that the doubt of the user on the provided travel planning result is eliminated, and the credibility is improved.

Description

Technical Field

[0001] The present disclosure relates to the field of data processing technology, specifically to the field of artificial intelligence technology such as semantic understanding, large language models, and intelligent navigation, and especially to a method, device, electronic device, computer-readable storage medium, and computer program product for determining the cause of an abnormal travel event. Background Art

[0002] When using electronic maps for navigation services, existing technologies are often limited to generating travel route plans based on real-time road data (such as congestion status, traffic restrictions, and distance), but the decision-making logic behind the generated travel route plans is not explained to users. This defect, especially when there is a difference between the current recommended route and historical travel routes, will directly cause users to question the accuracy of the navigation service. Summary of the Invention

[0003] The embodiments of the present disclosure provide a method, device, electronic device, computer-readable storage medium, and computer program product for determining the cause of an abnormal travel event.

[0004] In the first aspect, an embodiment of the present disclosure proposes a method for determining the cause of an abnormal travel event, including: obtaining the user's current travel plan and historical travel preferences; using the historical travel preferences to determine the abnormal travel events existing in the current travel plan; determining the event location corresponding to the abnormal travel event, and obtaining public information corresponding to the event location; inputting the abnormal travel event, public information and abnormal cause generation indication as the first prompt information into a preset first language model, and obtaining an output of the cause description corresponding to the abnormal travel event.

[0005] On the second aspect, an embodiment of the present disclosure proposes a device for determining the cause of an abnormal travel event, including: a current plan and historical preference acquisition unit, configured to acquire the user's current travel plan and historical travel preferences; an abnormal travel event determination unit, configured to use historical travel preferences to determine the abnormal travel event existing in the current travel plan; an event location determination and public information acquisition unit, configured to determine the event location corresponding to the abnormal travel event, and acquire public information corresponding to the event location; a cause explanation generation unit, configured to input the abnormal travel event, public information and abnormal cause generation indication as the first prompt information into a preset first language model, and obtain the output cause explanation corresponding to the abnormal travel event.

[0006] In a third aspect, an embodiment of the present disclosure provides an electronic device comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can implement the method for determining the cause of an abnormal travel event as described in the first aspect when executing the instructions.

[0007] In a fourth aspect, an embodiment of the present disclosure provides a non-transitory computer-readable storage medium storing computer instructions, which are used to enable a computer to implement the method for determining the cause of an abnormal travel event as described in the first aspect when executed.

[0008] In a fifth aspect, an embodiment of the present disclosure provides a computer program product comprising a computer program, which, when executed by a processor, can implement the steps of the method for determining the cause of an abnormal travel event as described in the first aspect.

[0009] The solution for determining the cause of abnormal travel events provided by the present disclosure, upon obtaining a user's current travel plan, compares and analyzes the current travel plan with historical travel preferences. Based on the differences, the solution first identifies abnormal travel events within the current travel plan. It then attempts to obtain public information associated with the event locations corresponding to the abnormal travel events. The abnormal travel event, the public information, and an abnormal cause generation instruction for analyzing possible abnormal causes are then input as first prompt information into a first language model. The solution then uses the first language model to analyze and obtain a cause explanation corresponding to the abnormal travel event. By providing corresponding cause explanations for abnormal travel events that may raise user concerns, the solution alleviates user doubts about the provided travel plan results and enhances their credibility.

[0010] It should be understood that the contents described in this section are not intended to identify the key or important features of the embodiments of the present disclosure, nor are they intended to limit the scope of the present disclosure. Other features of the present disclosure will become readily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] Other features, objects and advantages of the present disclosure will become more apparent from a reading of the detailed description of non-limiting embodiments made with reference to the following drawings: Figure 1 is an exemplary system architecture in which the present disclosure may be applied; Figure 2 A flowchart of a method for determining the cause of an abnormal travel event provided by an embodiment of the present disclosure; Figure 3A flowchart of a method for analyzing and obtaining abnormal travel events including abnormal road events and abnormal lane events provided in an embodiment of the present disclosure; Figure 4 A flowchart of a method for analyzing and obtaining multiple lane abnormal events provided by an embodiment of the present disclosure; Figure 5 A flowchart of a method for processing a reason explanation by voice broadcast provided in an embodiment of the present disclosure; Figure 6 A structural block diagram of a device for determining the cause of an abnormal travel event provided by an embodiment of the present disclosure; Figure 7 A schematic structural diagram of an electronic device suitable for executing a method for determining the cause of an abnormal travel event provided by an embodiment of the present disclosure. DETAILED DESCRIPTION

[0012] The following description of exemplary embodiments of the present disclosure is made in conjunction with the accompanying drawings, including various details of the embodiments of the present disclosure to facilitate understanding, which should be considered as merely exemplary. Therefore, it should be recognized by those skilled in the art that various changes and modifications can be made to the embodiments described herein without departing from the scope and spirit of the present disclosure. Similarly, for the sake of clarity and conciseness, descriptions of well-known functions and structures are omitted in the following description. It should be noted that the embodiments in the present disclosure and the features in the embodiments can be combined with each other unless there is a conflict.

[0013] In the technical solutions disclosed herein, the collection, storage, use, processing, transmission, provision and disclosure of user personal information involved comply with the provisions of relevant laws and regulations and do not violate public order and good morals.

[0014] Figure 1 An exemplary system architecture 100 is shown to which embodiments of the method, apparatus, electronic device, and computer-readable storage medium for determining causes of abnormal travel events disclosed herein may be applied.

[0015] like Figure 1 As shown, system architecture 100 may include terminal devices 101, 102, and 103, a network 104, and a server 105. Terminal device 101 represents a smart mobile terminal, terminal device 102 represents a vehicle-mounted terminal installed in a vehicle, and terminal device 103 represents a work terminal. Network 104 is a medium that provides a communication link between terminal devices 101, 102, and 103 and server 105. Network 104 may include various connection types, such as wired or wireless communication links or fiber optic cables.

[0016] Users can use terminal devices 101, 102, and 103 to interact with server 105 via network 104 to receive or send messages, etc. Various applications for enabling information communication between the terminal devices 101, 102, and 103 and server 105 can be installed, such as map navigation applications, large language model tool applications, and instant messaging applications.

[0017] Terminal devices 101, 102, 103 and server 105 can be hardware or software. When terminal devices 101, 102, 103 are hardware, they can be various electronic devices with display screens, including but not limited to smartphones, tablet computers, vehicle-mounted terminals, laptop computers, desktop computers, etc.; when terminal devices 101, 102, 103 are software, they can be installed in the electronic devices listed above, and they can be implemented as multiple software or software modules, or as a single software or software module, without specific limitations here. When server 105 is hardware, it can be implemented as a distributed server cluster consisting of multiple servers, or as a single server; when the server is software, it can be implemented as multiple software or software modules, or as a single software or software module, without specific limitations here.

[0018] The terminal devices 101, 102, 103 and the server 105 can provide various services through various built-in applications. Taking the map navigation application that can provide travel navigation services as an example, the terminal devices 101, 102, 103 or the server 105 can achieve the following effects when running the map navigation application: first, obtain the user's current travel plan and historical travel preferences; then, use the historical travel preferences to determine the abnormal travel events in the current travel plan; then, determine the event location corresponding to the abnormal travel event, and obtain the public information corresponding to the event location; finally, input the abnormal travel event, public information and abnormal cause generation indication as the first prompt information into the preset first language model, and obtain the output cause description corresponding to the abnormal travel event.

[0019] Because determining abnormal travel events and analyzing their causes in conjunction with associated public information requires significant computing resources and significant computational power, the methods for determining the causes of abnormal travel events provided in the subsequent embodiments of this disclosure are generally performed by a server 105 possessing significant computing power and resources. Accordingly, the apparatus for determining the causes of abnormal travel events is also generally located within server 105. However, it should also be noted that, if terminal devices 101, 102, and 103 also possess sufficient computing power and resources, terminal devices 101, 102, and 103 may also utilize a map navigation application installed thereon to perform the various computations previously assigned to server 105, thereby outputting the same results as server 105. In particular, in the presence of multiple terminal devices with varying computing power, if the map navigation application determines that the terminal device it is in possesses significant computing power and resources, it may allow the terminal device to perform the aforementioned computations, thereby appropriately alleviating the computational burden on server 105. Accordingly, the apparatus for determining the causes of abnormal travel events may also be located within terminal devices 101, 102, and 103. In this case, the exemplary system architecture 100 may also not include the server 105 and the network 104 .

[0020] It should be understood that Figure 1 The number of terminal devices, networks and servers in the embodiment is merely illustrative. Any number of terminal devices, networks and servers may be provided as required.

[0021] Please refer to Figure 2 , Figure 2 This is a flowchart of a method for determining the cause of an abnormal travel event provided by an embodiment of the present disclosure, wherein process 200 includes the following steps: Step 201: Obtain the user's current travel plan and historical travel preferences; This step aims to determine the execution subject of the method (e.g. Figure 1 The server 105 shown obtains the user's current travel plan and historical travel preferences.

[0022] The current travel plan is a travel route plan generated by the map navigation application based on the user's currently input starting and ending points. The travel route plan can be in an unexecuted state (i.e., obtained before the user travels), in an ongoing state (i.e., the user has traveled according to the travel route plan but has not yet reached the destination), or in a completed state (i.e., the user has traveled according to the travel route plan and has just reached the destination). The historical travel preferences are determined based on the user's historical travel history and personalized travel preferences. For example, they may include historical travel plans, historical preferred travel modes, and historical driving habits (e.g., preference for driving in the fast lane, preference for driving in the middle lane of multiple parallel through lanes, historical average driving speed, preference for highways or urban roads, etc.).

[0023] Step 202: using historical travel preferences to determine abnormal travel events in the current travel plan; Building on step 201, this step aims to allow the aforementioned execution entity to use historical travel preferences to identify abnormal travel events in the current travel plan. Specifically, based on the user's historical travel history and personalized travel preferences as recorded in the historical travel preferences, the execution entity determines whether the current travel plan contains any abnormalities (e.g., roads or recommended lanes that differ from those included in historical travel plans with the same starting and ending points, or portions that do not match the user's personalized choices). These abnormalities are then identified as abnormal travel events. These abnormalities are considered "abnormal" because they represent a mismatch between the user's current travel plan and historical travel preferences due to time differences, resulting in a mismatch in the user's behavioral continuity. For example, if user X's historical travel preferences determine that he frequently traveled from location A to location D, and his personalized preference for highways would result in a historical route plan from location A → highway B → ordinary road C → location D, however, when user X re-issues a travel request from location A to location D, the current plan instead goes from location A → ordinary road E → ordinary road C → location D.

[0024] Comparing the current travel plan with historical travel plans reveals that Highway B, which user X used to take frequently from location A to ordinary road C, is now not recommended. This clearly differs from user X's historical experience, raising questions about the accuracy of the current travel plan and whether it is the most appropriate route. Therefore, the ordinary road E from location A to ordinary road C and the corresponding Highway B can be used to form an abnormal travel event. In this example, since the anomaly primarily arises from differences in road level, this abnormal travel event can also be identified as a road abnormality event. Furthermore, if there is no difference in road level, but there is a difference in lane level on the same road, this abnormal travel event can be identified as a lane abnormality event.

[0025] It should be noted that since abnormal travel events are primarily determined by comparing historical travel preferences to unreasonable portions of the current travel plan, if historical travel preferences are completely inadequate to determine whether the current travel plan contains unreasonable portions, the current travel plan should be deemed to contain no abnormal travel events. For example, if the current travel plan is located in an area not previously covered by historical travel preferences, then it can be determined that there are no abnormal travel events in the current travel plan. For example, if user X has previously traveled only within city M and their historical travel preferences are limited to city A, if user X travels to city N for a new trip, the area they are in will be significantly different, with no consistent starting and ending points from previous trips. Therefore, the current travel plan for this trip in city N will likely be deemed to contain no abnormal travel events. This is because the trips in city N are all new trips, and the possibility of an abnormal travel event is only considered if their current travel plan includes preferences that are not subject to regional variations.

[0026] Step 203: Determine the event location corresponding to the abnormal travel event, and obtain public information corresponding to the event location; Based on step 202, this step aims to determine the event location corresponding to the abnormal travel event by the above-mentioned execution entity and obtain public information corresponding to the event location.

[0027] Continuing with the previous example, if the abnormal travel event is a road-level abnormal event, the event location could be a road in the current travel plan that differs from the historical travel plan (for example, Ordinary Road E in the above example). For example, Ordinary Road E is a new road between Point A and Road C that is smoother and has a shorter travel time. In this case, it is not the original Highway B that has a problem, but rather that Ordinary Road E is an option that has never been considered. Alternatively, it could be a road in the historical travel plan that differs from the current travel plan (for example, Highway B in the above example). For example, Highway B is temporarily closed when the current travel plan is generated. In this case, it indicates that Highway B has a problem, and the only option is to switch to an alternative road that was not previously selected.

[0028] After determining the location of the event, you can try to obtain public information corresponding to the location of the event from multiple preset information acquisition channels. These information acquisition channels may include: road administration information acquisition channels (used to obtain road administration information released by road administration, such as construction, temporary closures or blockages, regional traffic restrictions, etc.), travel notes sharing channels (used to obtain travel experience information released by other travel users on various travel notes sharing platforms), real-time event announcement channels (used to obtain event-related information released by various event organizers on event information release platforms), and at least one of the temporary chat room channels bound to the location (used to obtain relevant information on whether there is an emergency on the road section).

[0029] Step 204: The abnormal travel event, public information, and abnormal cause generation indication are input into a preset first language model as first prompt information to obtain an outputted cause description corresponding to the abnormal travel event.

[0030] On the basis of step 203, this step is intended to have the above-mentioned execution subject input the abnormal travel event, public information and abnormal cause generation indication as the first prompt information into the preset first language model, so as to obtain the output of the cause explanation corresponding to the abnormal travel event with the help of the data processing capability of the first language model. It can be understood that the abnormal travel event as part of the first prompt information is used to inform the first language model of the object that is considered to be abnormal (for example, it is currently recommended that I take a road that I have never taken before, or it is currently recommended that I take a new lane on the road I have taken before that I am not used to taking, etc.), and the public information as another copy is used to give the first language model a specific analysis of the source of the reason why the object that caused the abnormality is considered to be abnormal. The last copy of the abnormal cause generation indication is used to clearly convey the user's needs to the first language model, so that the first language model can correctly use the abnormal travel event and public information with the clear user needs to output the cause explanation that the user expects. The cause explanation can include the following: The original road is congested, the original road is closed so a detour is required, empty vehicles cannot enter the departure level, according to the latest requirements all pick-up vehicles need to stop at the South Station pick-up entrance, a certain road is a new road, passes through a popular location, there are temporary activities nearby that lead to large flow of people, etc.

[0031] To deepen the understanding of how the first language model specifically processes the input first prompt information to output the reason explanation, a specific implementation method is provided herein based on the first language model and using it as the execution subject through the following embodiment: First, the first large language model determines the expressed cause generation intention based on the abnormal cause generation indication in the first prompt information; then, the first large language model determines the causal relationship between the public information and the abnormal travel event under the cause generation intention; then, the first large language model generates a cause description corresponding to the abnormal travel event based on the causal relationship under the cause generation intention.

[0032] The causal relationship refers to extracting or identifying the cause that led to the abnormal travel event from public information, and the abnormal travel event caused by the cause is the "result".

[0033] Furthermore, after obtaining the explanation of the cause by calling the first language model, the content to be published containing the explanation of the cause can also be published in a temporary chat room corresponding to the location of the event; wherein, the content to be published includes: event type, explanation of the cause (for example, the original recommended road is temporarily closed or the normal traffic is blocked due to the high density of people at a temporary activity) and estimated duration of impact (for example, the impact will last for 1 hour, etc.), and event types include: road abnormality events or lane abnormality events.

[0034] The method for determining the cause of an abnormal travel event provided by the disclosed embodiments, upon obtaining a user's current travel plan, compares and analyzes the current travel plan with historical travel preferences. Based on the differences, the method first determines abnormal travel events present in the current travel plan. It then attempts to obtain public information associated with the event location corresponding to the abnormal travel event. The abnormal travel event, the public information, and an abnormal cause generation indication for analyzing possible abnormal causes are then input as first prompt information into a first large language model. The method then uses the first large language model to analyze and obtain a cause explanation corresponding to the abnormal travel event. In other words, by providing corresponding cause explanations for abnormal travel events that may raise user concerns, the method can alleviate user doubts about the provided travel plan results and enhance their credibility.

[0035] To better understand how to identify abnormal travel events, please refer to Figure 3 , Figure 3A flowchart of a method for analyzing abnormal travel events including road abnormal events and lane abnormal events provided in an embodiment of the present disclosure. Figure 3 , which shows that abnormal travel events can be subdivided into two categories: one is road abnormal events caused by differences at the road level, and the other is lane abnormal events caused by differences at the lane level.

[0036] This embodiment provides a method for determining abnormal road events through steps 301 to 303: Step 301: extracting historical travel plans with the same starting point and end point as the current travel plan from historical travel preferences; That is, the historical travel plan proposed in this embodiment and the current travel plan have the same starting point and end point.

[0037] Step 302: Determine a first road sequence based on the current travel plan, and determine a second road sequence based on the historical travel plan; This step involves the execution entity determining a first road sequence consisting of multiple roads that need to be traversed from the starting point to the end point based on the current travel plan, and a second road sequence consisting of multiple roads that need to be traversed from the starting point to the end point based on historical travel plans. In other words, the (first / second) road sequence includes multiple roads arranged in the order in which they are traversed.

[0038] Step 303: In response to the first road sequence and the second road sequence being not completely identical, determining that there is a road abnormality event in the current travel plan.

[0039] Based on step 302, this step is intended to determine that there is a road anomaly event in the current travel plan when the above-mentioned execution entity finds that the multiple roads arranged in the order of passing included in the first road sequence are not completely the same as the multiple roads arranged in the order of passing included in the second road sequence.

[0040] On this basis, the parts of the first road sequence that are different from those in the second road sequence, as well as the parts of the second road sequence that are different from those in the first road sequence, can be specifically identified as abnormal roads, and a preset range area centered on the abnormal road can be determined as the event location corresponding to the road abnormality event, thereby determining a comprehensive and accurate event location.

[0041] This embodiment provides a method for determining lane departure abnormality events through steps 301-302 and steps 304-305: Step 301: extracting historical travel plans with the same starting point and end point as the current travel plan from historical travel preferences; Step 302: Determine a first road sequence based on the current travel plan, and determine a second road sequence based on the historical travel plan; Step 304: In response to the first road sequence being identical to the second road sequence, determining a first recommended lane sequence based on the current travel plan, and determining a second recommended lane sequence based on the historical travel plan; Unlike step 303, this embodiment assumes that the first and second road sequences are identical (i.e., not only do the roads in the two sequences need to be identical, but the order of the roads in each sequence must also be identical). The execution entity determines a first recommended lane sequence based on the current travel plan and a second recommended lane sequence based on historical travel plans. The (first / second) recommended lane sequences contain multiple recommended lanes corresponding to the multiple roads arranged in sequential order.

[0042] Step 305: In response to the first recommended lane sequence and the second recommended lane sequence being not completely identical, it is determined that a lane anomaly event exists in the current travel plan.

[0043] Based on step 304 , this step is based on the situation that the first recommended lane sequence and the second recommended lane sequence are not completely the same, and aims to determine whether there is a lane anomaly event in the current travel plan.

[0044] It should be understood that there is no obvious causal or dependency relationship between the solutions provided by this embodiment for road abnormality events and lane abnormality events, and they can be subdivided into two different embodiments in the above manner. Figure 3 It only exists as a preferred embodiment that includes both solutions.

[0045] Compared with road abnormality events caused by road-level differences, lane abnormality events caused by lane-level differences may be subdivided into multiple lane abnormality events due to more complex reasons. Figure 4 , Figure 4 This is a flow chart of a method for analyzing and obtaining multiple lane abnormal events provided by an embodiment of the present disclosure. The process 400 includes the following steps: Step 401: Determine some recommended lanes in the first recommended lane sequence that are different from those in the second recommended lane sequence as suspected abnormal lanes; Step 402: Determine some of the recommended lanes in the second recommended lane sequence that correspond to the suspected abnormal lanes as historical reference lanes; The above two steps aim to select the suspected abnormal lanes (extracted from the first recommended lane sequence corresponding to the current travel plan) and the historical reference lanes (extracted from the second recommended lane sequence corresponding to the historical travel plan) corresponding to the distinguishing or different parts of the two recommended lane sequences in the past and current respectively.

[0046] Step 403: In response to the suspected abnormal lane and the corresponding historical reference lane being different merging lanes in the same driving direction, determining the number of lane intervals between the suspected abnormal lane and the corresponding historical reference lane; This step is based on the situation where the suspected abnormal lane and the corresponding historical reference lane are different merging lanes with the same driving direction, and is intended for the above-mentioned execution entity to determine the number of lane intervals between the suspected abnormal lane and the corresponding historical reference lane.

[0047] A road often has multiple lanes, each typically corresponding to at least one direction of travel. For example, on a three-lane road in certain scenarios, the left lane corresponds to a left turn, the middle lane corresponds to a straight-ahead direction, and the right lane corresponds to a right turn. In this case, each direction of travel has only one lane. On some five-lane roads, there is only one lane each for left and right turns, but the three middle lanes are all straight-ahead lanes. In this case, the three middle lanes will serve as different merging lanes for the same direction of travel as described in this embodiment. Assuming the suspected abnormal lane is the leftmost through lane of the three middle lanes and the historical reference lane is the rightmost through lane of the three middle lanes, the lane interval in this case is 1, meaning that the middle through lane is separated.

[0048] Step 404: In response to the number of lane intervals exceeding the preset number of intervals, determining the suspected abnormal lane as a first abnormal lane, and determining that a first lane abnormal event corresponding to the first abnormal lane exists in the current travel plan; This step is based on the situation where the lane interval number determined in step 403 exceeds the preset interval number. The purpose of this step is for the above-mentioned execution entity to determine the suspected abnormal lane as the first abnormal lane due to the larger lane interval number between it and the historical reference lane, and to determine that there is a first lane abnormal event corresponding to the first abnormal lane in the current travel plan.

[0049] Step 405: In response to the suspected abnormal lane and the corresponding historical reference lane having different driving directions, the suspected abnormal lane is determined to be a second abnormal lane, and a second lane abnormal event corresponding to the second abnormal lane is determined to exist in the current travel plan; This step is based on the fact that the suspected abnormal lane and the corresponding historical reference lane have different driving directions. That is, the suspected abnormal lane and the historical reference lane do not belong to different merging lanes with the same driving direction, but point to different driving directions respectively. In this case, due to a sufficiently large difference, the above-mentioned execution entity will determine the suspected abnormal lane as the second abnormal lane, and determine that there is a second lane abnormal event corresponding to the second abnormal lane in the current travel plan.

[0050] Step 406: In response to the number of lane intervals not exceeding the preset number of intervals, determining a set speed difference between the actual driving in the suspected abnormal lane and the corresponding historical reference lane in the set driving speed range; Different from the situation in step 404 where the number of lane intervals exceeds the preset number of intervals, this step is based on the situation where the number of lane intervals does not exceed the preset number of intervals. It is intended for the above-mentioned execution entity to determine the set speed difference between the actual driving in the suspected abnormal lane and the corresponding historical reference lane in the set driving speed range.

[0051] The set speed ranges described in this step are speed ranges set by the road administration for each merging lane traveling in the same direction based on their positional relationships. For example, on a highway with four straight lanes, the leftmost straight lane is often set as the overtaking lane, which has the highest speed range. The remaining straight lanes from left to right of the overtaking lane will usually have speed ranges with successively lower speed values ​​to accommodate various driving needs.

[0052] Step 407: In response to the set speed difference exceeding the preset speed difference, determining the suspected abnormal lane as a third abnormal lane, and determining that a third lane abnormal event corresponding to the third abnormal lane exists in the current travel plan; This step is based on the situation where the set speed difference determined in step 406 exceeds the preset speed difference. The purpose of this step is for the above-mentioned execution entity to determine that the suspected abnormal lane is the third abnormal lane due to the sufficient driving speed difference, and to determine that there is a third lane abnormal event corresponding to the third abnormal lane in the current travel plan.

[0053] Step 408: In response to the number of lane intervals not exceeding the preset number of intervals, determining the actual average speed or actual time consumed in traveling on the suspected abnormal lane; Different from the set speed difference calculated in step 406, although this step is also based on the situation that the number of lane intervals does not exceed the preset number of intervals, the actual average speed or actual time consumed in driving on the suspected abnormal lane is determined by the above-mentioned execution entity, that is, the corresponding current travel plan should be in the execution state at this time, that is, the user is already driving according to the current travel plan.

[0054] Step 409: In response to the actual average speed being less than the historical average speed of the historical driving on the corresponding historical reference lane, or the actual driving time being greater than the historical driving time on the corresponding historical reference lane, the suspected abnormal lane is determined to be the fourth abnormal lane, and it is determined that there is a fourth lane abnormal event corresponding to the fourth abnormal lane in the current travel plan.

[0055] This step is based on the situation where the actual average speed is lower than the historical average speed of the historical driving on the corresponding historical reference lane, or the actual time is higher than the historical time of the historical driving on the corresponding historical reference lane. The purpose of this step is for the above-mentioned execution entity to determine that the suspected abnormal lane is indeed abnormal because the actual average speed is slower than the historical average speed or the actual time is higher than the historical time. Therefore, the suspected abnormal lane is determined to be the fourth abnormal lane, and it is determined that there is a fourth lane abnormal event corresponding to the fourth abnormal lane in the current travel plan.

[0056] Figure 4 The illustrated embodiment includes four different lane abnormality events, covering four scenarios: corresponding to different driving directions; corresponding to the same driving direction but with a large number of lane intervals; the number of lane intervals is not large but the set speed difference is too large; and the number of lane intervals is not large but the actual speed or actual time is significantly higher than the historical situation, so as to cover various possible lane abnormality situations as comprehensively as possible.

[0057] Based on any of the above embodiments, considering that the generation of the cause explanation can be completed with the help of the preset first language model, the abnormal event analysis task provided in step 202 of process 200 can also be completed with the help of a preset second language model with similar capabilities. For example, the current travel plan, historical travel preferences, and abnormal event analysis instructions can be input as second prompt information into the preset second language model to obtain the output of abnormal travel events existing in the current travel plan. To deepen the understanding of how the second language model specifically processes the input second prompt information to output the analyzed abnormal travel events, a specific implementation method is also provided here based on the second language model and using it as the execution subject through the following embodiment: First, the second largest language model determines the expressed abnormal event analysis intention based on the abnormal event analysis indication in the second prompt information; then, the second largest language model determines the difference information between the current travel plan and the historical travel preference under the abnormal event analysis intention; then, the second largest language model generates abnormal travel events existing in the current travel plan based on the difference information under the abnormal event analysis intention.

[0058] This discrepancy information encompasses all the road- and lane-level discrepancies mentioned in the previous embodiments, and will not be detailed here. This embodiment attempts to identify more comprehensive and accurate abnormal travel events by replacing manual, pre-defined rules with a large language model with stronger and more comprehensive processing capabilities to identify discrepancies between current travel plans and historical travel preferences.

[0059] Based on any of the above embodiments, after obtaining the reason explanation output by the first language model, if the historical travel preferences include a prompt information preference type, the reason explanation may be adjusted according to the prompt information preference type, and the adjusted reason explanation may be presented to the user according to the prompt information preference type. The prompt information preference type may include at least one of a text presentation type, an image presentation type, and a voice broadcast type.

[0060] For example, when the prompt information preference type only includes the image presentation type, the reason description can be presented in the form of a corresponding image or animation; when the prompt information preference type includes not only the image presentation type but also the voice broadcast type, some characteristics of the voice broadcast can also be combined to generate the content to be broadcast for broadcast.

[0061] Compared with the text presentation type and image presentation type, the voice broadcast type often requires more complex processing methods. Please refer to Figure 5 , Figure 5 This is a flowchart of a method for processing a reason explanation by voice broadcast provided in an embodiment of the present disclosure. In the case where the prompt information preference type includes a voice broadcast type, the process 500 includes the following steps: Step 501: Determine the target broadcast speed and the upper limit of the number of words in the voice broadcast; Step 502: adjusting the length of the explanation of the reason according to the upper limit of the number of words to be broadcasted, and obtaining the content to be broadcasted; Step 503: announcing the content to be announced at the target announcement speed.

[0062] In this embodiment, the above-mentioned execution entity may first determine the target broadcast speed and the upper limit of the number of words for voice broadcast, and then adjust the content length of the reason explanation output by the first largest language model according to the upper limit of the number of words for voice broadcast to obtain the content to be broadcast. In the process of adjustment, the key content of the reason explanation may be placed as far forward as possible (for example, placing it at the very beginning of the overall content), and then arrange the detailed explanation supporting the key content in the subsequent part, so as to convey the conclusion to the user in a timely manner through the front-placed key content; then, the content to be broadcast is broadcast at the target broadcast speed.

[0063] Furthermore, the content to be announced may be announced using a selected voice announcement tone according to the historical preferences extracted from the historical travel preferences.

[0064] To deepen the understanding of the solutions provided by the above embodiments, this embodiment also provides an implementation process description in conjunction with a specific example: Assume that user X is driving from location A to station F. Before setting off, user X uses a map navigation application to generate a current route plan from location A to station F. User X also confirms based on past travel experience that the current route plan is reasonable and has been planned and taken in the past.

[0065] Therefore, user X will drive according to the current route plan, but when driving to the area where Road E is located, abnormal congestion occurs, causing driving to slow down. Faced with the unexpected abnormal congestion event, user X can raise a question or query to the in-vehicle terminal, "Why is Road E so congested?" When the map navigation application installed on the in-vehicle terminal receives this question or query, it can collect public information related to the area where Road E is located through multiple pre-maintained information acquisition channels, and finally collect information from a travel diary platform that a park in the area where Road E is located recently held a flower and green plant exhibition, which attracted a large number of tourists to come and view and publish a large number of browsing notes.

[0066] Based on the above situation, map navigation applications can output the following voice broadcast: There is a flower and plant exhibition recently in XX Park near the road section you are currently traveling on. There are many tourists parking and waiting on the roadside, which will cause the road section to continue to be congested for ZZ minutes.

[0067] After this report, user X will understand the cause of the abnormal congestion and decide whether to issue a new route planning request based on the actual situation.

[0068] Further references Figure 6 As an implementation of the methods shown in the above figures, the present disclosure provides an embodiment of a device for determining the cause of an abnormal travel event. Figure 2 Corresponding to the method embodiment shown, the device can be specifically applied to various electronic devices.

[0069] like Figure 6As shown, the apparatus 600 for determining the cause of an abnormal travel event in this embodiment may include: a current plan and historical preference acquisition unit 601, an abnormal travel event determination unit 602, an event location determination and public information acquisition unit 603, and a cause explanation generation unit 604. The current plan and historical preference acquisition unit 601 is configured to acquire the user's current travel plan and historical travel preferences; the abnormal travel event determination unit 602 is configured to determine an abnormal travel event in the current travel plan using historical travel preferences; the event location determination and public information acquisition unit 603 is configured to determine the event location corresponding to the abnormal travel event and acquire public information corresponding to the event location; and the cause explanation generation unit 604 is configured to input the abnormal travel event, public information, and abnormal cause generation indication as first prompt information into a preset first language model to output a cause explanation corresponding to the abnormal travel event.

[0070] In this embodiment, the specific processing and technical effects of the abnormal travel event cause determination device 600: the current plan and historical preference acquisition unit 601, the abnormal travel event determination unit 602, the event location determination and public information acquisition unit 603, and the cause description generation unit 604 can be referred to respectively. Figure 2 The relevant descriptions of steps 201-204 in the corresponding embodiment are not repeated here.

[0071] In some other optional implementations of this embodiment, the abnormal travel event determining unit 602 may include: a historical travel plan extraction subunit, configured to extract historical travel plans having the same starting point and end point as the current travel plan from historical travel preferences; a road sequence determination subunit configured to determine a first road sequence based on a current travel plan and a second road sequence based on a historical travel plan; wherein the road sequence includes a plurality of roads arranged in a sequential order of travel; The road abnormality event determining subunit is configured to determine that a road abnormality event exists in the current travel plan in response to the first road sequence and the second road sequence being not completely the same.

[0072] In some other optional implementations of this embodiment, the event location determination and public information acquisition unit 603 may include an event location determination subunit configured to determine the event location corresponding to the abnormal travel event, and the event location determination subunit is further configured to: In response to the abnormal travel event being a road abnormality event, determining a portion of roads in the first road sequence that are different from those in the second road sequence, and a portion of roads in the second road sequence that are different from those in the first road sequence, as abnormal roads; A preset range area centered on the abnormal road is determined as the event location corresponding to the road abnormality event.

[0073] In some other optional implementations of this embodiment, the abnormal travel event determining unit 602 may further include: a lane sequence determination subunit configured to, in response to the first road sequence and the second road sequence being identical, determine a first recommended lane sequence based on the current travel plan and determine a second recommended lane sequence based on the historical travel plan; wherein the recommended lane sequence includes a plurality of recommended lanes arranged corresponding to the plurality of roads arranged in sequence according to the travel order; The lane abnormality event determining subunit is configured to determine that a lane abnormality event exists in the current travel plan in response to the first recommended lane sequence and the second recommended lane sequence being not completely the same.

[0074] In some other optional implementations of this embodiment, the lane abnormality event determination subunit may include: a suspected abnormal lane determining module configured to determine a portion of the recommended lanes in the first recommended lane sequence that are different from those in the second recommended lane sequence as suspected abnormal lanes; a historical reference lane determining module configured to determine a portion of the recommended lanes in the second recommended lane sequence corresponding to the suspected abnormal lanes as historical reference lanes; a lane interval number determination module configured to determine a lane interval number between the suspected abnormal lane and the corresponding historical reference lane in response to the suspected abnormal lane and the corresponding historical reference lane being different merging lanes in the same driving direction; The first lane abnormal event determination module is configured to, in response to the number of lane intervals exceeding a preset number of intervals, determine the suspected abnormal lane as a first abnormal lane, and determine that a first lane abnormal event corresponding to the first abnormal lane exists in the current travel plan.

[0075] In some other optional implementations of this embodiment, the lane abnormality event determination subunit may further include: The second lane abnormal event determination module is configured to determine the suspected abnormal lane as a second abnormal lane in response to the suspected abnormal lane and the corresponding historical reference lane having a different driving direction, and determine that there is a second lane abnormal event corresponding to the second abnormal lane in the current travel plan.

[0076] In some other optional implementations of this embodiment, the lane abnormality event determination subunit may further include: a set speed difference determining module configured to determine, in response to the number of lane intervals not exceeding a preset number of intervals, a set speed difference between actual driving in the suspected abnormal lane and a corresponding historical reference lane in a set driving speed interval; The third lane abnormal event determination module is configured to, in response to the set speed difference exceeding the preset speed difference, determine the suspected abnormal lane as the third abnormal lane, and determine that there is a third lane abnormal event corresponding to the third abnormal lane in the current travel plan.

[0077] In some other optional implementations of this embodiment, the lane abnormality event determination subunit may further include: an actual average speed or time-consuming determination module, configured to determine an actual average speed or actual time-consuming driving on the suspected abnormal lane in response to the number of lane intervals not exceeding a preset number of intervals; The fourth lane abnormal event determination module is configured to determine the suspected abnormal lane as the fourth abnormal lane in response to the actual average speed being less than the historical average speed of historical driving on the corresponding historical reference lane, or the actual driving time being greater than the historical driving time on the corresponding historical reference lane, and determine that there is a fourth lane abnormal event corresponding to the fourth abnormal lane in the current travel plan.

[0078] In some other optional implementations of this embodiment, the device 600 for determining the cause of an abnormal travel event may further include: The determining unit is configured to determine that there is no abnormal travel event in the current travel plan in response to the area where the current travel plan is located being an area not involved in the historical travel preferences.

[0079] In some other optional implementations of this embodiment, the abnormal travel event determining unit 602 is further configured to: The current travel plan, historical travel preferences and abnormal event analysis instructions are input into the preset second language model as the second prompt information to obtain the output of abnormal travel events existing in the current travel plan.

[0080] In some other optional implementations of this embodiment, the process of generating, by the second largest language model, an abnormal travel event existing in the current travel plan based on the input second prompt information includes: The second language model determines the abnormal event analysis intention expressed according to the abnormal event analysis instruction in the second prompt information; The second language model determines the difference between current travel plans and historical travel preferences under the intention of abnormal event analysis; The second language model generates abnormal travel events that exist in the current travel plan based on difference information under the intention of abnormal event analysis.

[0081] In some other optional implementations of this embodiment, the event location determination and public information acquisition unit 603 includes a public information acquisition subunit configured to acquire public information corresponding to the event location, and the public information acquisition subunit is further configured to: Obtain public information corresponding to the event location from a preset information acquisition channel; wherein the information acquisition channel includes: at least one of a road administration information acquisition channel, a travel notes sharing channel, a real-time event announcement channel, and a temporary chat room channel bound to a location.

[0082] In some other optional implementations of this embodiment, the device 600 for determining the cause of an abnormal travel event may further include: The publishing unit is configured to publish the content to be published including the cause description in a temporary chat room corresponding to the event location; wherein the content to be published includes: event type, cause description and estimated impact duration, and the event type includes: road abnormality event or lane abnormality event.

[0083] In some other optional implementations of this embodiment, the process of generating, by the first language model, a cause explanation corresponding to the abnormal travel event based on the input first prompt information includes: The first language model determines the expressed cause generation intention according to the abnormal cause generation indication in the first prompt information; The first language model determines the causal relationship between public information and abnormal travel events under the intention of cause generation; The first language model generates reason explanations corresponding to abnormal travel events based on causal associations under the intention of cause generation.

[0084] In some other optional implementations of this embodiment, the device 600 for determining the cause of an abnormal travel event may further include: The adjustment unit is configured to adjust the reason description according to the prompt information preference type in response to the prompt information preference type included in the historical travel preferences, and present the adjusted reason description to the user according to the prompt information preference type; wherein the prompt information preference type includes: at least one of: text presentation type, image presentation type, and voice broadcast type.

[0085] In some other optional implementations of this embodiment, the adjustment unit is further configured to: In response to the prompt information preference type including the voice broadcast type, determining a target broadcast speech speed and an upper limit of the number of words in the voice broadcast; Adjust the length of the explanation of the cause according to the upper limit of the number of words for voice broadcast to obtain the content to be broadcast; wherein the key content of the explanation of the cause is located at the beginning of the content to be broadcast; The content to be reported should be broadcast at the target broadcast speed.

[0086] This embodiment, as an apparatus embodiment corresponding to the above-mentioned method embodiment, provides a device for determining the cause of an abnormal travel event. Upon obtaining a user's current travel plan, the device compares and analyzes the current travel plan with historical travel preferences. Based on the differences, the device first determines abnormal travel events within the current travel plan. The device then attempts to obtain public information associated with the location of the event corresponding to the abnormal travel event. The device then inputs the abnormal travel event, the public information, and an abnormal cause generation indication for analyzing possible abnormal causes into a first large language model as first prompt information. The device then analyzes the abnormal travel event under the indication using the first large language model to obtain a cause explanation corresponding to the abnormal travel event. This means that by providing a corresponding cause explanation for abnormal travel events that may raise user concerns, user doubts about the provided travel plan results can be alleviated and credibility enhanced.

[0087] According to an embodiment of the present disclosure, the present disclosure also provides an electronic device, which includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor so that when the at least one processor executes, it can implement the method for determining the cause of an abnormal travel event described in any of the above embodiments.

[0088] According to an embodiment of the present disclosure, the present disclosure further provides a readable storage medium storing computer instructions, which are used to enable a computer to implement the method for determining the cause of an abnormal travel event described in any of the above embodiments when executed.

[0089] According to an embodiment of the present disclosure, the present disclosure further provides a computer program product, which, when executed by a processor, can implement the method for determining the cause of an abnormal travel event described in any of the above embodiments.

[0090] Figure 6 A schematic block diagram of an example electronic device 600 that can be used to implement embodiments of the present disclosure is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital assistants, cellular phones, smartphones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are provided as examples only and are not intended to limit the implementation of the present disclosure described and / or claimed herein.

[0091] like Figure 6As shown, device 600 includes a computing unit 601, which can perform various appropriate actions and processes according to a computer program stored in a read-only memory (ROM) 602 or a computer program loaded from a storage unit 608 into a random access memory (RAM) 603. RAM 603 may also store various programs and data required for the operation of device 600. Computing unit 601, ROM 602, and RAM 603 are interconnected via a bus 604. An input / output (I / O) interface 605 is also connected to bus 604.

[0092] Various components in device 600 are connected to I / O interface 605, including an input unit 606, such as a keyboard, mouse, etc.; an output unit 607, such as various types of displays, speakers, etc.; a storage unit 608, such as a magnetic disk, optical disk, etc.; and a communication unit 609, such as a network card, modem, wireless communication transceiver, etc. The communication unit 609 allows device 600 to exchange information / data with other devices via a computer network such as the Internet and / or various telecommunication networks.

[0093] The computing unit 601 can be any general-purpose and / or specialized processing component with processing and computing capabilities. Some examples of the computing unit 601 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various specialized artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. The computing unit 601 performs the various methods and processes described above, such as the method for determining the cause of an abnormal travel event. For example, in some embodiments, the method for determining the cause of an abnormal travel event can be implemented as a computer software program tangibly embodied in a machine-readable medium, such as the storage unit 608. In some embodiments, part or all of the computer program can be loaded and / or installed onto the device 600 via the ROM 602 and / or the communication unit 609. When the computer program is loaded into the RAM 603 and executed by the computing unit 601, one or more steps of the method for determining the cause of an abnormal travel event described above can be performed. Alternatively, in other embodiments, the computing unit 601 can be configured to perform the method for determining the cause of an abnormal travel event through any other suitable means (e.g., via firmware).

[0094] Various embodiments of the systems and techniques described above can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), system-on-chip systems (SOCs), programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments can include being implemented in one or more computer programs that are executable and / or interpreted on a programmable system that includes at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0095] The program code for implementing the method of the present disclosure can be written in any combination of one or more programming languages. These program codes can be provided to a processor or controller of a general-purpose computer, a special-purpose computer, or other programmable data processing device so that when the program code is executed by the processor or controller, the functions / operations specified in the flow chart and / or block diagram are implemented. The program code can be executed entirely on the machine, partially on the machine, as a stand-alone software package, partially on the machine and partially on a remote machine, or entirely on a remote machine or server.

[0096] In the context of the present disclosure, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, apparatus, or device. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples of machine-readable storage media may include an electrical connection based on one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), optical fibers, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0097] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user can provide input to the computer. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0098] The systems and techniques described herein can be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such back-end components, middleware components, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include a local area network (LAN), a wide area network (WAN), and the Internet.

[0099] A computer system may include a client and a server. The client and server are generally remote from each other and typically interact via a communication network. This client-server relationship arises through computer programs running on the respective computers and establishing a client-server relationship with each other. The server may be a cloud server, also known as a cloud computing server or cloud host. This is a hosting product within the cloud computing service ecosystem that addresses the management difficulties and limited scalability of traditional physical hosting and virtual private server (VPS) services.

[0100] According to the technical solution of the disclosed embodiment, when a user's current travel plan is obtained, the current travel plan is compared and analyzed with historical travel preferences. Based on the differences, abnormal travel events within the current travel plan are first identified. Public information associated with the event locations corresponding to the abnormal travel events is then attempted to be obtained. The abnormal travel event, the public information, and an abnormal cause generation indication for analyzing possible abnormal causes are then input as first prompt information into a first large language model. The first large language model then analyzes the indication to obtain a cause explanation corresponding to the abnormal travel event. In other words, by providing corresponding cause explanations for abnormal travel events that may raise user concerns, user doubts about the provided travel plan results can be alleviated and credibility improved.

[0101] It should be understood that the various forms of the processes shown above can be used to reorder, add, or delete steps. For example, the steps described in this disclosure can be performed in parallel, sequentially, or in a different order, as long as the desired results of the technical solutions disclosed in this disclosure can be achieved. This is not a limitation herein.

[0102] The above specific embodiments do not constitute a limitation on the scope of protection of this disclosure. Those skilled in the art will appreciate that various modifications, combinations, sub-combinations, and substitutions may be made based on design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this disclosure shall be included within the scope of protection of this disclosure.

Claims

1. A method for determining the cause of an abnormal travel event, comprising: Obtain the user's current travel plan and historical travel preferences; Determining abnormal travel events in the current travel plan using the historical travel preferences; Determining an event location corresponding to the abnormal travel event, and obtaining public information corresponding to the event location; The abnormal travel event, the public information and the abnormal cause generation indication are input into a preset first language model as first prompt information to obtain an outputted cause description corresponding to the abnormal travel event.

2. The method according to claim 1, wherein The determining of abnormal travel events in the current travel plan by using the historical travel preferences includes: Extracting a historical travel plan having the same starting point and end point as the current travel plan from the historical travel preferences; Determining a first road sequence according to the current travel plan, and determining a second road sequence according to the historical travel plan; wherein the road sequence includes a plurality of roads arranged in order of passing; In response to the first road sequence and the second road sequence being not completely identical, it is determined that a road abnormality event exists in the current travel plan.

3. The method according to claim 2, wherein: Determining the event location corresponding to the abnormal travel event includes: In response to the abnormal travel event being the road abnormality event, determining a portion of roads in the first road sequence that are different from those in the second road sequence, and a portion of roads in the second road sequence that are different from those in the first road sequence, as abnormal roads; A preset range area centered on the abnormal road is determined as an event location corresponding to the abnormal road event.

4. The method according to claim 2, wherein: The determining of abnormal travel events in the current travel plan by using the historical travel preferences further includes: In response to the first road sequence and the second road sequence being identical, determining a first recommended lane sequence based on the current travel plan, and determining a second recommended lane sequence based on the historical travel plan; wherein the recommended lane sequence includes a plurality of recommended lanes arranged corresponding to the plurality of roads arranged in sequence according to the travel order; In response to the first recommended lane sequence and the second recommended lane sequence being not completely identical, it is determined that a lane abnormality event exists in the current travel plan.

5. The method according to claim 4, wherein The determining that a lane abnormality event exists in the current travel plan includes: determining some recommended lanes in the first recommended lane sequence that are different from those in the second recommended lane sequence as suspected abnormal lanes; determining a portion of the recommended lanes in the second recommended lane sequence corresponding to the suspected abnormal lane as a historical reference lane; In response to the suspected abnormal lane and the corresponding historical reference lane being different merging lanes in the same driving direction, determining a lane interval number between the suspected abnormal lane and the corresponding historical reference lane; In response to the lane interval number exceeding a preset interval number, the suspected abnormal lane is determined to be a first abnormal lane, and it is determined that a first lane abnormal event corresponding to the first abnormal lane exists in the current travel plan.

6. The method according to claim 4, wherein: The determining whether a lane abnormality event exists in the current travel plan further includes: In response to the suspected abnormal lane and the corresponding historical reference lane having a different driving direction, the suspected abnormal lane is determined to be a second abnormal lane, and a second lane abnormal event corresponding to the second abnormal lane is determined to exist in the current travel plan.

7. The method according to claim 4, wherein: The determining whether a lane abnormality event exists in the current travel plan further includes: In response to the number of lane intervals not exceeding the preset number of intervals, determining a set speed difference between actual driving in the suspected abnormal lane and a corresponding historical reference lane in a set driving speed interval; In response to the set speed difference exceeding the preset speed difference, the suspected abnormal lane is determined to be a third abnormal lane, and a third lane abnormal event corresponding to the third abnormal lane is determined to exist in the current travel plan.

8. The method according to claim 4, wherein The determining whether a lane abnormality event exists in the current travel plan further includes: In response to the lane interval number not exceeding the preset interval number, determining an actual average speed or actual time consumed in traveling on the suspected abnormal lane; In response to the actual average speed being less than the historical average speed of historical driving on the corresponding historical reference lane, or the actual driving time being greater than the historical driving time on the corresponding historical reference lane, the suspected abnormal lane is determined to be a fourth abnormal lane, and it is determined that a fourth lane abnormal event corresponding to the fourth abnormal lane exists in the current travel plan.

9. The method according to claim 1, further comprising: In response to the area where the current travel plan is located being an area not involved in the historical travel preferences, it is determined that the abnormal travel event does not exist in the current travel plan.

10. The method according to any one of claims 2, 4 to 9, wherein: The determining of abnormal travel events in the current travel plan by using the historical travel preferences includes: The current travel plan, the historical travel preferences and the abnormal event analysis indication are input as second prompt information into a preset second language model to obtain output abnormal travel events existing in the current travel plan.

11. The method according to claim 10, wherein: The process of generating, by the second language model, an abnormal travel event existing in the current travel plan based on the input second prompt information includes: The second largest language model determines the abnormal event analysis intention expressed according to the abnormal event analysis instruction in the second prompt information; Determining, under the second language model, difference information between the current travel plan and the historical travel preference based on the abnormal event analysis intention; The second largest language model generates an abnormal travel event present in the current travel plan based on the difference information under the abnormal event analysis intention.

12. The method according to claim 1, wherein The obtaining of public information corresponding to the event location includes: Obtain public information corresponding to the event location from a preset information acquisition channel; wherein the information acquisition channel includes: at least one of a road information acquisition channel, a travel notes sharing channel, a real-time event announcement channel, and a temporary chat room channel bound to a location.

13. The method according to claim 12, further comprising: The content to be published including the cause description is published in a temporary chat room corresponding to the event location; wherein the content to be published includes: event type, cause description and estimated impact duration, and event type includes: road abnormality event or lane abnormality event.

14. The method according to claim 1, wherein The process of generating a cause explanation corresponding to the abnormal travel event based on the input first prompt information by the first language model includes: The first large language model determines the expressed cause generation intention according to the abnormal cause generation indication in the first prompt information; Determining the causal relationship between the public information and the abnormal travel event under the cause generation intention under the first language model; The first language model generates a cause description corresponding to the abnormal travel event based on the causal association under the cause generation intention.

15. The method according to claim 14, further comprising: In response to the prompt information preference type included in the historical travel preferences, the reason description is adjusted according to the prompt information preference type, and the adjusted reason description is presented to the user according to the prompt information preference type; wherein the prompt information preference type includes: at least one of: text presentation type, image presentation type, and voice broadcast type.

16. The method according to claim 15, wherein The adjusting the reason description according to the prompt information preference type and presenting the adjusted reason description to the user according to the prompt information preference type includes: In response to the prompt information preference type including the voice broadcast type, determining a target broadcast speech speed and an upper limit on the number of words in the voice broadcast; Adjusting the content length of the reason explanation according to the upper limit of the number of words to be broadcasted by voice to obtain the content to be broadcasted; wherein the key content of the reason explanation is located at the beginning of the content to be broadcasted; The content to be announced is announced at the target announcement speed.

17. A device for determining the cause of an abnormal travel event, comprising: A current travel plan and historical travel preference acquisition unit configured to acquire the user's current travel plan and historical travel preferences; an abnormal travel event determining unit, configured to determine abnormal travel events existing in the current travel plan by using the historical travel preferences; an event location determination and public information acquisition unit, configured to determine an event location corresponding to the abnormal travel event and acquire public information corresponding to the event location; The cause explanation generating unit is configured to input the abnormal travel event, the public information and the abnormal cause generation indication as the first prompt information into a preset first language model, and obtain the output cause explanation corresponding to the abnormal travel event.

18. An electronic device comprising: at least one processor; as well as a memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method for determining the cause of an abnormal travel event according to any one of claims 1 to 16.

19. A non-transitory computer-readable storage medium storing computer instructions, wherein the computer instructions are used to cause the computer to execute the method for determining the cause of an abnormal travel event according to any one of claims 1 to 16.

20. A computer program product, comprising a computer program, wherein when the computer program is executed by a processor, the computer program implements the steps of the method for determining the cause of an abnormal travel event according to any one of claims 1 to 16.

Images