Trip planning method and device, electronic equipment and computer readable storage medium

Abstract

The invention provides an itinerary planning method and apparatus, an electronic device and a computer readable storage medium. The method comprises the steps of extracting itinerary features in a target material; wherein the target material is a third-party resource containing travel information; converting the stroke characteristics into a set format; transmitting the travel features in the set format to the navigation application, and obtaining feature information corresponding to the travel features based on the navigation application; and generating a travel route plan according to the travel route features and the feature information. According to the method, the travel features in the target material are directly extracted, the extracted travel features are converted into the set format, the corresponding feature information can be obtained from the navigation application through the set format, then the travel plan is generated according to the travel features and the feature information, a user does not need to manually input related route information in the whole process, and the user experience is improved. The method achieves the automatic generation of the itinerary plan, and improves the intelligence and convenience of itinerary plan generation.

Description

Technical Field

[0001] The present application relates to the field of intelligent planning, and more specifically, to a trip planning method, device, electronic device, and computer-readable storage medium. Background Art

[0002] In travel planning, itinerary planning is a crucial function that helps users efficiently arrange travel routes, estimate travel time and costs, and thus improve the convenience and comfort of travel. However, traditional itinerary planning methods generally rely on users to manually enter information about waypoints, a process that is not only cumbersome but also provides a poor user experience. Specifically, users need to find and enter the name, address or other relevant identification information of each place passed through one by one. This process is not only time-consuming and laborious, but also prone to inaccurate itinerary planning due to incorrect or missing information input. Summary of the invention

[0003] In view of this, the purpose of the embodiments of the present application is to provide a trip planning method, device, electronic device and computer-readable storage medium, which can improve the intelligence and convenience of trip planning generation.

[0004] In a first aspect, an embodiment of the present application provides a method for itinerary planning, comprising: extracting itinerary features from a target material; wherein the target material is a third-party resource containing itinerary information; converting the itinerary features into a set format; transmitting the itinerary features in the set format to a navigation application, and obtaining feature information corresponding to the itinerary features based on the navigation application; generating an itinerary plan based on the itinerary features and the feature information.

[0005] In the above implementation process, by directly extracting the itinerary features in the target material and converting the extracted itinerary features into a set format, the corresponding feature information can be obtained from the navigation application through the set format, and then the itinerary plan is generated according to the itinerary features and the feature information. The entire process does not require the user to manually enter the relevant route information, thereby realizing automatic generation of the itinerary plan and improving the intelligence and convenience of itinerary plan generation.

[0006] In one embodiment, extracting the travel features in the target material includes: updating the feature weights of the feature extraction words in the Intern VL model according to the extraction requirements, the feature extraction words are configured to extract the travel features in the target material; extracting the travel features in the target material by updating the feature extraction words with the updated weights.

[0007] In the above implementation process, by updating the feature weights of feature extraction words according to extraction requirements, the feature weights of feature extraction words can be related to the actual needs of users, thereby obtaining feature extraction words that better meet user needs and improving the accuracy and flexibility of feature extraction words. In addition, by extracting itinerary features through feature extraction words with updated weights, the accuracy and satisfaction of itinerary feature extraction can be improved, thereby improving user experience.

[0008] In one embodiment, the feature extraction words include: location features, and the extraction of itinerary features in the target material includes: extracting location features in each route in the target material; converting the itinerary features into a set format includes: converting the location features and route numbers in each route into a set format to obtain one or more arrays; wherein each array includes a route number and the location features in the route corresponding to the route number.

[0009] In the above implementation process, by extracting location features according to routes, the location features in each route can be extracted, thereby improving the completeness of location feature extraction. In addition, since location feature extraction is relatively easy, the difficulty of itinerary feature extraction can be reduced, thereby improving extraction efficiency.

[0010] In one embodiment, the feature extraction words include: location features and time features; the extraction of itinerary features in the target material includes: extracting the time features in the target material and the location features in each route; the conversion of the itinerary features into a set format includes: determining the location features corresponding to each of the time features; generating a corresponding number of routes according to the time features; converting the time features and the location features in each route into a set format to obtain one or more arrays.

[0011] In the above implementation process, by extracting location features according to time features, location features under various time features can be extracted, thereby improving the completeness of location feature extraction. Furthermore, a trip plan can be generated by jointly using time features and location features, thereby planning a trip according to time and improving the completeness of the trip plan.

[0012] In one embodiment, before converting the travel features into a set format, the method further includes: if the target material includes multiple routes, determining the number of identical location features in each route; when the number of identical location features in the multiple routes exceeds a set number threshold, retaining one route among the multiple routes whose number of identical location features exceeds the set number threshold; wherein the location features in the retained one or more routes are different.

[0013] In the above implementation process, when the number of identical place features in multiple routes exceeds a set threshold, only one route is retained, and the place features in the retained route are different, which can reduce the overlap rate of places in the route and improve the accuracy of itinerary planning.

[0014] In one embodiment, after generating the itinerary plan according to the itinerary characteristics and the characteristic information, the method further includes: adjusting the itinerary according to the positional relationship of the itinerary characteristics in the itinerary plan; wherein the positional relationship includes: one or more of actual position, relative position and itinerary distance.

[0015] In the above implementation process, after the itinerary planning is generated, the itinerary is adjusted according to the positional relationship of the itinerary features in the itinerary planning to improve the accuracy and rationality of the generated itinerary planning.

[0016] In one embodiment, the trip features include: location points; adjusting the trip according to the positional relationship of the trip features in the trip planning includes: filtering the location points whose actual locations in the trip planning are outside a location restriction range; and / or excluding the location points whose total trip distance exceeds a reasonable driving range; and / or filtering the location points whose relative positions between adjacent location points are outside a distance restriction range.

[0017] In the above implementation process, by further filtering the location points in the itinerary planning according to one or more restriction methods such as the location restriction range, the reasonable driving range and the distance restriction range, the itinerary planning can be adjusted to improve the accuracy and rationality of the final itinerary planning and improve the user experience.

[0018] In the second aspect, an embodiment of the present application also provides a itinerary planning device, including: an extraction module for extracting itinerary features from a target material, wherein the target material is a third-party resource containing itinerary information; a conversion module for converting the itinerary features into a set format; a transmission module for transmitting the itinerary features in a set format to a navigation application, and obtaining feature information corresponding to the itinerary features based on the navigation application; and a generation module for generating a itinerary plan based on the itinerary features and the feature information.

[0019] In a third aspect, an embodiment of the present application further provides an electronic device, comprising: a processor and a memory, wherein the memory stores machine-readable instructions executable by the processor, and when the electronic device is running, the machine-readable instructions are executed by the processor to perform the steps of the method in the above-mentioned first aspect, or any possible implementation of the first aspect.

[0020] In a fourth aspect, an embodiment of the present application further provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps of the itinerary planning method in the above-mentioned first aspect, or any possible implementation manner of the first aspect are executed.

[0021] In order to make the above-mentioned objects, features and advantages of the present application more obvious and understandable, embodiments are given below and described in detail with reference to the attached drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the embodiments will be briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present application and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.

[0023] Figure 1 A schematic diagram of the interaction between a third-party application, an electronic device, and a navigation application provided in an embodiment of the present application;

[0024] Figure 2 A block diagram of an electronic device provided in an embodiment of the present application;

[0025] Figure 3 A flowchart of a trip planning method provided in an embodiment of the present application;

[0026] Figure 4 The target material provided for the embodiment of the present application is a schematic diagram of a strategy picture in a book;

[0027] Figure 5 A schematic diagram of the functional modules of the itinerary planning device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0028] The technical solutions in the embodiments of the present application will be described below in conjunction with the accompanying drawings in the embodiments of the present application.

[0029] It should be noted that similar reference numerals and letters represent similar items in the following drawings, so once an item is defined in one drawing, it does not need to be further defined and explained in subsequent drawings. At the same time, in the description of this application, the terms "first", "second", etc. are only used to distinguish the description and cannot be understood as indicating or implying relative importance.

[0030] Traditionally, navigation apps require users to manually enter route information to generate a travel plan for navigation. However, the manual entry method requires users to manually enter the specific information of each route point, which is not only time-consuming and laborious, but also prone to inaccurate planning results or poor user experience due to information entry errors.

[0031] In view of this, the present application proposes an itinerary planning method, whereby users can directly upload target materials such as text content, pictures or videos, directly extract the itinerary route in the target material and generate relevant route locations, location scenery pictures, etc. for display, and intelligently generate itinerary plans based on user preferences and itinerary requirements. The entire process does not require users to manually enter relevant route information, thus realizing automatic generation of itinerary plans and improving the intelligence and convenience of itinerary plan generation.

[0032] To facilitate understanding of this embodiment, the operating environment of a trip planning method disclosed in the embodiment of the present application is first introduced in detail.

[0033] like Figure 1 , which is a schematic diagram of the interaction between a third-party application, an electronic device, and a navigation application provided in an embodiment of the present application. The electronic device is connected to one or more third-party applications and one or more navigation applications through a network to perform data communication or interaction.

[0034] The electronic device here can be a network server, a database server, etc., or a personal computer (PC), a tablet computer, a smart phone, a personal digital assistant (PDA), etc. The electronic device can be selected according to actual conditions.

[0035] The third-party application mentioned above can be a reference application for users to make itinerary planning strategies, for example, a certain audio, a certain book, a certain home, etc. The third-party application can be selected according to the actual situation.

[0036] It is understandable that when a user browses a third-party application and finds a travel guide that he likes, he can upload the travel information such as the travel guide video, travel guide picture or travel guide text in the third-party application to the electronic device.

[0037] After obtaining the itinerary information, the electronic device processes the itinerary information and extracts itinerary features from the itinerary information. The electronic device may also transmit the itinerary features to a navigation application and obtain feature information corresponding to each itinerary feature in the navigation application.

[0038] After acquiring the characteristic information, the electronic device generates a trip plan based on the trip characteristics and the corresponding characteristic information.

[0039] The above-mentioned navigation application is a kind of map software that can be used for navigation, for example, Baidu Map, Deutsche Map, and Apple Map, etc. The navigation application can be selected according to the actual situation.

[0040] In one embodiment, after generating the itinerary plan, the electronic device may transmit the itinerary plan to a navigation application so that the navigation application can generate a navigation route according to the itinerary plan.

[0041] To facilitate understanding of this embodiment, the electronic device that executes the itinerary planning method disclosed in the embodiment of the present application is introduced in detail below.

[0042] like Figure 2 , which is a block diagram of an electronic device. The electronic device 100 may include a memory 111 and a processor 113. A person skilled in the art may understand that Figure 2 The structure shown is only for illustration and does not limit the structure of the electronic device 100. For example, the electronic device 100 may further include Figure 2 More or fewer components as shown, or with Figure 2 Different configurations shown.

[0043] The memory 111 and the processor 113 are directly or indirectly electrically connected to each other to achieve data transmission or interaction. For example, these elements can be electrically connected to each other via one or more communication buses or signal lines. The processor 113 is used to execute the executable module stored in the memory.

[0044] The memory 111 may be, but not limited to, a random access memory (RAM), a read only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable read-only memory (EEPROM), etc. The memory 111 is used to store programs, and the processor 113 executes the program after receiving the execution instruction. The method executed by the electronic device 100 defined by the process disclosed in any embodiment of the present application can be applied to the processor 113, or implemented by the processor 113.

[0045] The processor 113 may be an integrated circuit chip with signal processing capability. The processor 113 may be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it may also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components. The methods, steps and logic block diagrams disclosed in the embodiments of the present application may be implemented or executed. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0046] The electronic device 100 in this embodiment can be used to execute each step in each method provided in the embodiment of the present application. The implementation process of the itinerary planning method is described in detail below through several embodiments.

[0047] See also Figure 3 , is a flow chart of the itinerary planning method provided in the embodiment of the present application. Figure 3 The specific process shown is described in detail.

[0048] Step S201, extracting travel features from target material.

[0049] The target material is a third-party resource containing itinerary information. For example, the target material is a guide picture in a book (such as Figure 4 As shown in the figure), the target material is a strategy video in a certain audio, or the target material is a strategy text in a certain nest, etc. The target material can be selected according to the actual situation.

[0050] It is understandable that when browsing the third-party application, the user can directly transmit the browsed target material to the electronic device. After acquiring the target material, the electronic device processes the target material and extracts the travel features in the target material.

[0051] Among them, different types of target materials have different corresponding processing methods.

[0052] For example, if the target material is a picture and the feature extraction model does not support multimodality, the picture content can be first identified as text content through OCR technology, and the identified text content can be transmitted to the feature extraction model.

[0053] If the target material is a video and the feature extraction model does not support multimodality, you can take screenshots of the video key frames at each set duration and transmit them to the feature extraction model. Then, through OCR technology, you can identify the image content as text content and transmit the identified text content to the feature extraction model.

[0054] If the target material is a video and the feature extraction model supports multi-modality (including video modality), the video address can be directly transmitted to the feature extraction model, and the feature extraction model directly extracts the travel features from the video.

[0055] If the target material is a picture and the feature extraction model supports multi-modality (including picture modality), the picture address can be directly transmitted to the feature extraction model, and the feature extraction model directly extracts the travel features from the picture.

[0056] The above-mentioned processing method of the target material is only exemplary, and the processing method of the target material can be selected according to actual conditions.

[0057] The itinerary features here refer to feature information related to the itinerary, such as location point, place name, attraction name, landmark, time, itinerary direction, route number, etc. The itinerary features can be adjusted according to actual conditions.

[0058] In one embodiment, the travel features in the target material may be extracted in sequence.

[0059] Step S202, converting the travel characteristics into a set format.

[0060] The setting format here is a format that can be recognized by the navigation application, for example, json format. The setting format can be selected according to actual conditions.

[0061] Exemplarily, the steps of converting text into json format can be as follows: determine the format of text data; use the file operation function in the programming language (such as Python) to read the contents of the text file. For example, in Python, you can use the built-in open function to read the file; according to the format of the text data, determine the corresponding parsing logic; for simple key-value pairs, you can use string operation functions (such as split) to parse each line of content; for complex nested structures, you may need to write recursive functions or use regular expressions to parse. Store the parsed data in an appropriate data structure, such as a dictionary, list, etc.; use the json library provided by the programming language (such as the json module in Python) to convert the data structure into a string in json format. For example, in Python, you can use the json.dumps() function to convert a dictionary or list into a json string.

[0062] Step S203: transmitting the itinerary characteristics in a set format to the navigation application, and acquiring characteristic information corresponding to the itinerary characteristics based on the navigation application.

[0063] The characteristic information here refers to the location information corresponding to each corresponding trip feature, for example, longitude and latitude information, distance information, and direction information. The characteristic information can be selected according to actual conditions.

[0064] It is understandable that after the navigation application obtains the itinerary features in the set format, it can query the location of the location in the navigation application according to the location in the itinerary features, and then output the latitude and longitude information and direction information corresponding to the location. Of course, if the itinerary features include multiple locations, the navigation application can output the distance information between each two adjacent locations in the multiple itinerary features after obtaining the multiple itinerary features.

[0065] Step S204, generating a trip plan based on the trip characteristics and characteristic information.

[0066] The itinerary planning here is configured to be used for navigation by a navigation application, and the itinerary planning may include one or more routes.

[0067] In one embodiment, the itinerary plan may be stored in a memory of the navigation application, and the itinerary plan may also be marked at a corresponding position of the navigation application according to the route. The form of the generated itinerary plan may be selected according to actual conditions.

[0068] In the above implementation process, by directly extracting the itinerary features in the target material and converting the extracted itinerary features into a set format, the corresponding feature information can be obtained from the navigation application through the set format, and then the itinerary plan is generated according to the itinerary features and the feature information. The entire process does not require the user to manually enter the relevant route information, thereby realizing automatic generation of the itinerary plan and improving the intelligence and convenience of itinerary plan generation.

[0069] In a possible implementation, step S201 includes: updating feature weights of feature extraction words in the Intern VL model according to extraction requirements; and extracting itinerary features in the target material by using the feature extraction words with updated weights.

[0070] Among them, the Intern VL model is an open source multimodal large language model that aims to narrow the gap in multimodal understanding capabilities between open source and proprietary commercial models.

[0071] In one embodiment, before step S201, the method further includes: optimizing multiple hyperparameters in the Intern VL model, such as sampling temperature, maximum number of generated flags, maximum number of processed flags, and repeated penalties, etc. The hyperparameters can be selected according to actual conditions.

[0072] For example, the sampling temperature can be optimized by finding a suitable temperature value through experiments and parameter adjustment. Generally speaking, if the generated results need to be more diverse, a higher temperature value can be selected; if a more stable and accurate result is required, a lower temperature value can be selected. Usually, cross-validation is performed on the training set to select a better temperature value.

[0073] The optimization method of duplicate penalty can be: by adjusting the duplicate penalty to reduce the possibility of the model generating duplicate tokens, the penalty coefficient can be obtained through experiments. The value of the penalty coefficient is between 0 and 1.

[0074] The optimization method using the beam search sampling method can be obtained by experimentally trying different beam widths.

[0075] The hyperparameter optimization method in the above Intern VL model is only exemplary, and the hyperparameter optimization method can be adjusted according to actual conditions.

[0076] The feature extraction words here are configured to extract the travel features in the target material. The feature extraction words may include: location features, time features, direction features, etc. The feature extraction words may be selected according to actual conditions.

[0077] Among them, the travel features extracted corresponding to different types of target materials may be different.

[0078] For example, if the target material is a picture, the extracted itinerary features may be elements such as landmarks and attractions.

[0079] If the target material is a video, the extracted itinerary features can be elements such as locations and activity scenes.

[0080] If the target material is text, the extracted itinerary features can be elements such as locations and activity scenes.

[0081] The above-mentioned itinerary features extracted from the target material are only exemplary, and the itinerary features extracted from the target material can be selected according to actual conditions.

[0082] The extraction requirements here may be the user's historical preferences, the user's historical behaviors, the data source, etc. The extraction requirements may be selected based on actual conditions.

[0083] In one embodiment, updating the feature weights of feature extraction words in the Intern VL model according to the extraction requirements may include: increasing the feature weights of feature extraction words consistent with the user's preferences according to the user's historical preferences.

[0084] In another embodiment, updating the feature weights of feature extraction words in the Intern VL model according to extraction requirements may also include: determining the importance of each data type, and setting different feature weights for the corresponding feature extraction words according to the importance of each data type. For example, setting the weight of text expression to be greater than the weight of image expression.

[0085] Optionally, the mutual influence of related features in the trip can be improved according to the correlation between the features.

[0086] In one embodiment, step S201 further includes: obtaining actual travel results and user feedback, and adjusting the fusion weights of various existence forms of the target material according to the actual travel results and user feedback to improve the rationality of the travel and user satisfaction.

[0087] For example, if the first target material is a type of identification image containing clear location text and clear date marks, and the second target material is a trip picture containing various irregular connection marks, and the recognition effect of the latter is weaker than that of the former, a higher weight can be given to the type of identification image, thereby satisfying the rationality of the entire trip and user satisfaction.

[0088] In the above implementation process, by updating the feature weights of feature extraction words according to extraction requirements, the feature weights of feature extraction words can be related to the actual needs of users, thereby obtaining feature extraction words that better meet user needs and improving the accuracy and flexibility of feature extraction words. In addition, by extracting itinerary features through feature extraction words with updated weights, the accuracy and satisfaction of itinerary feature extraction can be improved, thereby improving user experience.

[0089] In a possible implementation, step S201 includes: extracting location features in each route in the target material.

[0090] The place features here refer to features used to represent a place, such as place names, place images, landmarks, etc.

[0091] It can be understood that if the target material includes multiple routes, the location features in each route are extracted respectively.

[0092] In one embodiment, the location features may be extracted sequentially according to the order in which each location information appears in the target material.

[0093] Optionally, when performing location feature extraction, only relevant location features need to be extracted, without the need for additional inspection and cleaning, and without the need to determine whether the identified location is reasonable.

[0094] In one embodiment, step S202 includes: converting the location features and route numbers in each route into a set format to obtain one or more arrays.

[0095] Each array includes a route number and a location feature in the route corresponding to the route number.

[0096] It is understandable that when the target material includes multiple routes, when extracting the itinerary features in the target material, it is necessary to extract the corresponding route number and the location features under the route number according to the route. When performing the setting format conversion, it is necessary to convert the route number and the location features to the corresponding setting format respectively.

[0097] Exemplarily, the location features and route numbers in the target material are extracted in sequence, and the location features and route numbers are converted into json format. For example, if the target material contains two routes, the corresponding json can be as follows:\n\njson\n{\n\"1\":[\"Location 1\",\"Location 2\"],\n\"2\":[\"Location 3\",\"Location 4\",\"Location 5\"]\n}\n. Among them, key is the corresponding route number, and there are several routes corresponding to several keys. n is an array of locations (where the same location is not allowed to appear in the same array).

[0098] In the above implementation process, by extracting location features according to routes, the location features in each route can be extracted, thereby improving the completeness of location feature extraction. In addition, since location feature extraction is relatively easy, the difficulty of itinerary feature extraction can be reduced, thereby improving extraction efficiency.

[0099] In a possible implementation, step S201 includes: extracting time features in the target material and location features in each route.

[0100] The time feature here refers to the time-related features of the trip, such as the number of days of the trip, the date of the trip, the length of stay at each location, etc. The time feature can be selected according to the actual situation.

[0101] It should be understood that if the target material also includes time features related to the journey, the corresponding time features can also be extracted when the journey features are extracted.

[0102] In one embodiment, step S202 includes: determining the location feature corresponding to each time feature; generating a corresponding number of routes according to the time feature; and converting the time feature and location feature in each route into a set format to obtain one or more arrays.

[0103] Each time feature may correspond to one or more location features. When extracting itinerary features, corresponding itinerary features may be extracted according to the time features.

[0104] If the target material contains obvious date identifiers (such as Day1\first day\date), a corresponding number of routes can be generated (if there are n date identifiers, n routes will be generated, and the number of corresponding route sequence keys is also n).

[0105] It is understandable that when the target material includes multiple dates, when extracting the itinerary features in the target material, it is necessary to extract the corresponding date identifier and the location features under the date identifier according to the date identifier. When performing the setting format conversion, it is necessary to convert the date identifier and the location features to the corresponding setting format respectively.

[0106] Exemplarily, if there are connecting lines or guide signs in the target material, the location features can be extracted in sequence when extracting itinerary features, and both the location features and the time features can be converted into json format. For example, if the target material contains two routes, the corresponding json can be as follows: \t\tjson\t{\t\"1\":[\"Location 1\",\"Location 2\"],\t\"2\":[\"Location 3\",\"Location 4\",\"Location 5\"]\t}\t. Among them, key is the corresponding route number, and there are several routes corresponding to several keys. The value is an array of locations (where the same location is not allowed to appear in the same array), and t is the time feature.

[0107] In the above implementation process, by extracting location features according to time features, location features under various time features can be extracted, thereby improving the completeness of location feature extraction. Furthermore, a trip plan can be generated by jointly using time features and location features, thereby planning a trip according to time and improving the completeness of the trip plan.

[0108] In a possible implementation, before step S202, the method further includes: if the target material includes multiple routes, determining the number of identical location features in each route; when the number of identical location features in the multiple routes exceeds a set number threshold, retaining one route among the multiple routes in which the number of identical location features exceeds the set number threshold.

[0109] The set quantity threshold here refers to the number set in advance that the same location feature is not allowed to exceed. For example, the set quantity threshold is half of the total location features in the line, and the set quantity threshold is 3, 5, 10, etc. The set quantity threshold can be set according to actual conditions.

[0110] It is understandable that, in order to reduce the overlap of locations in the routes, when the number of identical location features in multiple routes exceeds a set number threshold, only one route is retained, wherein the location features in the one or more retained routes are different.

[0111] The place feature here may be a place name, a landmark, a place image, etc. Each place feature in the retained one or more routes is used to represent a location point.

[0112] In the above implementation process, when the number of identical place features in multiple routes exceeds a set threshold, only one route is retained, and the place features in the retained route are different, which can reduce the overlap rate of places in the route and improve the accuracy of itinerary planning.

[0113] In a possible implementation, after step S204, the method further includes: adjusting the itinerary according to the positional relationship of the itinerary features in the itinerary planning.

[0114] The position relationship includes one or more of actual position, relative position and travel distance.

[0115] It is understandable that after the itinerary plan is generated, the itinerary plan may be adjusted according to the positional relationship between the various location points in the itinerary plan.

[0116] For example, if only one location point in a certain itinerary plan is located in Province A, and the other location points are all located in Province B, and there are multiple provinces and cities between Province A and Province B. In this case, it can be determined that the location point located in Province A may have an error, and the location point can be filtered to form the final itinerary plan.

[0117] If the distance between two adjacent location points in a certain itinerary planning exceeds the maximum allowed distance limit, in this case, the distance relationship between the location points can be analyzed, and the location points with a larger distance can be filtered out to form the final itinerary planning.

[0118] The above-mentioned itinerary planning adjustment method is only exemplary, and the itinerary planning adjustment method can be selected according to actual conditions.

[0119] In the above implementation process, after the itinerary planning is generated, the itinerary is adjusted according to the positional relationship of the itinerary features in the itinerary planning to improve the accuracy and rationality of the generated itinerary planning.

[0120] In one possible implementation, correcting the itinerary according to the positional relationship of itinerary features in the itinerary planning includes: filtering location points in the itinerary planning whose actual locations are outside the location limit range; and / or excluding location points whose total itinerary distance exceeds a reasonable driving range; and / or filtering location points whose relative positions between adjacent location points are outside the distance limit range.

[0121] The location restriction range here can be determined by geo-fencing technology, such as attribute-based geo-fencing, network signal-based geo-fencing, geographic feature-based geo-fencing, etc. The geo-fencing technology can be selected according to actual conditions.

[0122] It should be understood that if there are location points outside the location restriction range in the itinerary planning, it means that the location points are beyond the reasonable range of the itinerary planning. In this case, these location points outside the location restriction range can be filtered out, and location points that better meet the needs can be selected for itinerary planning.

[0123] It is understandable that a total travel distance limit can be set. After the travel plan is generated, the total travel distance of the generated travel plan is calculated, and it is determined whether the total travel distance exceeds the reasonable driving range. If it is determined that the total travel distance exceeds the reasonable driving range, the location points with a longer distance are filtered out.

[0124] The above distance limit range refers to the maximum distance allowed between adjacent location points.

[0125] If the relative positions between adjacent location points are outside the distance limit, the extracted adjacent location points can be analyzed and location points with more reasonable distances can be selected for itinerary planning.

[0126] In the above implementation process, by further filtering the location points in the itinerary planning according to one or more restriction methods such as the location restriction range, the reasonable driving range and the distance restriction range, the itinerary planning can be adjusted to improve the accuracy and rationality of the final itinerary planning and improve the user experience.

[0127] Based on the same application concept, the embodiment of the present application also provides a trip planning device corresponding to the trip planning method. Since the principle of solving the problem by the device in the embodiment of the present application is similar to that of the aforementioned trip planning method embodiment, the implementation of the device in this embodiment can refer to the description in the embodiment of the above method, and the repeated parts will not be repeated.

[0128] See also Figure 5 , is a functional module diagram of the itinerary planning device provided in the embodiment of the present application. Each module in the itinerary planning device in this embodiment is used to execute each step in the above method embodiment. The itinerary planning device includes an extraction module 501, a conversion module 502, a transmission module 503, and a generation module 504; wherein,

[0129] The extraction module 501 is used to extract itinerary features from target material, where the target material is a third-party resource containing itinerary information.

[0130] The conversion module 502 is used to convert the travel characteristics into a set format.

[0131] The transmission module 503 is used to transmit the travel characteristics in a set format to the navigation application, and obtain characteristic information corresponding to the travel characteristics based on the navigation application.

[0132] The generation module 504 is used to generate a trip plan according to the trip characteristics and the characteristic information.

[0133] In a possible implementation, the extraction module 501 is further used to: update the feature weights of the feature extraction words in the Intern VL model according to the extraction requirements, wherein the feature extraction words are configured to extract the itinerary features in the target material; and extract the itinerary features in the target material by updating the feature extraction words after the weights are updated.

[0134] In a possible implementation manner, the extraction module 501 is specifically configured to extract location features in each route in the target material.

[0135] In a possible implementation, the conversion module 502 is specifically used to: convert the location features and route numbers in each route into a set format to obtain one or more arrays; wherein each array includes a route number and the location features in the route corresponding to the route number.

[0136] In a possible implementation manner, the extraction module 501 is specifically configured to extract time features in the target material and location features in each route.

[0137] In a possible implementation, the conversion module 502 is specifically used to: determine the location feature corresponding to each of the time features; generate a corresponding number of routes according to the time features; and convert the time features and the location features in each route into a set format to obtain one or more arrays.

[0138] In a possible implementation, the itinerary planning device further includes a filtering module, which is used to: if the target material includes multiple routes, determine the number of identical location features in each route; if the number of identical location features in the multiple routes exceeds a set number threshold, retain one route among the multiple routes whose number of identical location features exceeds the set number threshold; wherein the location features in the retained one or more routes are different.

[0139] In a possible implementation, the itinerary planning device further includes an adjustment module for adjusting the itinerary according to the positional relationship of the itinerary features in the itinerary planning; wherein the positional relationship includes one or more of an actual position, a relative position, and a itinerary distance.

[0140] In one possible implementation, the adjustment module is specifically used to: filter the location points in the itinerary planning whose actual locations are outside the location limit range; and / or exclude the location points whose total trip distance exceeds a reasonable driving range; and / or filter the location points whose relative positions between adjacent location points are outside the distance limit range.

[0141] In addition, an embodiment of the present application also provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps of the itinerary planning method described in the above method embodiment are executed.

[0142] The computer program product of the itinerary planning method provided in the embodiment of the present application includes a computer-readable storage medium storing program code, and the instructions included in the program code can be used to execute the steps of the itinerary planning method described in the above method embodiment. For details, please refer to the above method embodiment, which will not be repeated here.

[0143] In several embodiments provided in the present application, it should be understood that the disclosed devices and methods can also be implemented in other ways. The device embodiments described above are merely schematic. For example, the flowcharts and block diagrams in the accompanying drawings show the possible architecture, functions and operations of the devices, methods and computer program products according to multiple embodiments of the present application. In this regard, each box in the flowchart or block diagram can represent a module, a program segment or a part of a code, and the module, a program segment or a part of a code contains one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two consecutive boxes can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flowchart, and the combination of boxes in the block diagram and / or flowchart can be implemented with a dedicated hardware-based system that performs a specified function or action, or can be implemented with a combination of dedicated hardware and computer instructions.

[0144] In addition, the functional modules in the various embodiments of the present application may be integrated together to form an independent part, or each module may exist separately, or two or more modules may be integrated to form an independent part.

[0145] If the function is implemented in the form of a software function module and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application is essentially or the part that contributes to the prior art or the part of the technical solution can be embodied in the form of a software product, which is stored in a storage medium and includes several instructions to enable a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM, Read-Only Memory), a random access memory (RAM, Random Access Memory), a disk or an optical disk. It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply that there is any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprises" or any other variation thereof are intended to cover non-exclusive inclusion, so that a process, method, article or apparatus that includes a series of elements includes not only those elements, but also includes other elements not explicitly listed, or also includes elements inherent to such process, method, article or apparatus. In the absence of more restrictions, the elements defined by the sentence "includes..." do not exclude the presence of other identical elements in the process, method, article or apparatus that includes the elements.

[0146] The above description is only a preferred embodiment of the present application and is not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present application shall be included in the protection scope of the present application. It should be noted that similar numbers and letters represent similar items in the following drawings, so once an item is defined in one drawing, it does not need to be further defined and explained in the subsequent drawings.

[0147] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. A trip planning method, characterized in that: include: Extracting itinerary features from target material; wherein the target material is a third-party resource containing itinerary information; Converting the stroke characteristics into a set format; Transmitting the trip characteristics in a set format to a navigation application, and obtaining characteristic information corresponding to the trip characteristics based on the navigation application; Generate a trip plan based on the trip characteristics and the characteristic information.

2. The method according to claim 1, characterized in that The step of extracting the travel features from the target material includes: Update the feature weight of the feature extraction word in the Intern VL model according to the extraction requirements, wherein the feature extraction word is configured to extract the itinerary features in the target material; The travel feature in the target material is extracted by updating the feature extraction words after weighting.

3. The method according to claim 2, characterized in that in, The feature extraction words include: location features, and the itinerary features extracted from the target material include: Extracting location features in each route in the target material; The converting the itinerary features into a set format includes: converting the location features and the route sequence number in each route into a set format to obtain one or more arrays; Each array includes a route number and a location feature in the route corresponding to the route number.

4. The method according to claim 2, characterized in that: in, The feature extraction words include: location features and time features; The step of extracting the travel features from the target material includes: Extracting time features in the target material and location features in each route; The step of converting the stroke characteristics into a set format comprises: Determine the location feature corresponding to each of the time features; Generate a corresponding number of routes according to the time characteristics; The time feature and the location feature in each route are converted into a set format to obtain one or more arrays.

5. The method according to claim 3 or 4, characterized in that: Before converting the stroke characteristics into a set format, the method further includes: If the target material includes multiple routes, determining the number of identical location features in each route; When the number of identical location features in the plurality of routes exceeds a set number threshold, retaining one of the plurality of routes in which the number of identical location features exceeds the set number threshold; Among them, the characteristics of the places in one or more of the retained routes are different.

6. The method according to claim 1, characterized in that After generating the itinerary plan according to the itinerary characteristics and the characteristic information, the method further includes: adjusting the itinerary according to the positional relationship of the itinerary features in the itinerary planning; The position relationship includes one or more of actual position, relative position and travel distance.

7. The method according to claim 6, characterized in that in, The travel characteristics include: location points; The adjusting the itinerary according to the positional relationship of the itinerary features in the itinerary planning includes: Filtering the location points in the itinerary planning whose actual locations are outside the location restriction range; and / or, Excluding the location points where the total distance of the trip exceeds the reasonable driving range; and / or, The position points whose relative positions between adjacent position points are outside the distance limit range are filtered.

8. A trip planning device, characterized in that: include: An extraction module, used to extract itinerary features from a target material, where the target material is a third-party resource containing itinerary information; A conversion module, used for converting the stroke characteristics into a set format; a transmission module, used for transmitting the trip characteristics in a set format to the navigation application, and obtaining characteristic information corresponding to the trip characteristics based on the navigation application; A generation module is used to generate a trip plan based on the trip characteristics and the characteristic information.

9. An electronic device, characterized in that: include: A processor and a memory, wherein the memory stores machine-readable instructions executable by the processor, and when the electronic device is running, the machine-readable instructions are executed by the processor to perform the steps of any method described in claims 1 to 7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are executed.

Images