Itinerary generation method and device, electronic equipment and readable storage medium

Abstract

Embodiments of the present disclosure provide a trip generation method and device, electronic equipment and readable storage medium. The method comprises: obtaining candidate access objects belonging to a target region, and determining the theme of the candidate access objects; for each theme, determining the time matching degree between the target access time and each candidate access object according to the preset start time and the preset end time of each candidate access object corresponding to the theme; calculating the quality score of the candidate access object according to the characteristic information of the candidate access object; for each theme, selecting the target access object from the candidate access objects corresponding to the theme according to the time matching degree and the quality score, and adding the target access object corresponding to the target access time to the trip information corresponding to the theme. By evaluating the candidate access objects and selecting the target access objects to add to the trip information, the artificial cost can be reduced, and the efficiency and timeliness can be improved.

Description

Technical Field

[0001] The embodiments of this disclosure relate to the field of computer processing technology, and more particularly to a process generation method, apparatus, electronic device, and readable storage medium. Background Technology

[0002] In daily life, people plan their trips in advance, specifying when to go and where to go to ensure the quality of their experience. Currently, itineraries are primarily planned manually. Because itinerary planning involves route planning, time allocation, and quality assessment of the places visited, manual itinerary planning is costly, inefficient, and lacks timeliness. Summary of the Invention

[0003] The embodiments of this disclosure provide a trip generation method, apparatus, electronic device, and readable storage medium, which can evaluate candidate access objects and select target access objects to add to trip information, thereby helping to reduce labor costs and improve efficiency and timeliness.

[0004] According to a first aspect of the embodiments of this disclosure, a route generation method is provided, the method comprising:

[0005] Obtain candidate access objects belonging to the target area, and determine the topic of the candidate access objects;

[0006] For each topic, the time matching degree between the target access time and each candidate access object is determined based on the preset start time and preset end time of each candidate access object corresponding to the topic;

[0007] The quality score of the candidate access object is calculated based on the feature information of the candidate access object;

[0008] For each topic, a target access object is selected from the candidate access objects corresponding to the topic based on the time matching degree and the quality score, and the target access object and the target access time are added to the itinerary information corresponding to the topic.

[0009] According to a second aspect of the embodiments of this disclosure, a trip generation apparatus is provided, the apparatus comprising:

[0010] The topic determination module is used to obtain candidate access objects belonging to the target area and determine the topic of the candidate access objects;

[0011] The time matching degree determination module is used to determine the time matching degree between the target access time and each candidate access object for each topic, based on the preset start time and preset end time of each candidate access object corresponding to the topic.

[0012] The quality score determination module is used to calculate the quality score of the candidate access object based on the feature information of the candidate access object.

[0013] The itinerary addition module is used to select a target access object from the candidate access objects corresponding to the topic for each topic based on the time matching degree and the quality score, and add the target access object and the target access time to the itinerary information corresponding to the topic.

[0014] According to a third aspect of the embodiments of this disclosure, an electronic device is provided, comprising:

[0015] A processor, a memory, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the aforementioned process generation method.

[0016] According to a fourth aspect of the embodiments of the present disclosure, a readable storage medium is provided, characterized in that, when the instructions in the storage medium are executed by a processor of an electronic device, the electronic device is able to perform the aforementioned process generation method.

[0017] This disclosure provides a method and apparatus for generating itineraries. The method includes: acquiring candidate visit objects belonging to a target area and determining the topics of the candidate visit objects; for each topic, determining a time matching degree between a target visit time and each candidate visit object based on a preset start time and a preset end time corresponding to the topic; calculating a quality score of the candidate visit objects based on their feature information; for each topic, selecting a target visit object from the candidate visit objects corresponding to the topic based on the time matching degree and the quality score, and adding the target visit object and the target visit time to the itinerary information corresponding to the topic. By evaluating candidate visit objects and selecting target visit objects to add to the itinerary information, it is helpful to reduce labor costs and improve efficiency and timeliness. Attached Figure Description

[0018] To more clearly illustrate the technical solutions of the embodiments of this disclosure, the accompanying drawings used in the description of the embodiments of this disclosure will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the embodiments of this disclosure. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0019] Figure 1 A flowchart illustrating the steps of a process generation method in one embodiment of this disclosure is shown.

[0020] Figure 2 A flowchart illustrating the steps of a process generation method according to another embodiment of this disclosure is shown;

[0021] Figure 3 A structural diagram of a trip generation apparatus according to one embodiment of the present disclosure is shown;

[0022] Figure 4 A structural diagram of a trip generation apparatus according to another embodiment of the present disclosure is shown;

[0023] Figure 5 A structural diagram of an electronic device according to one embodiment of the present disclosure is shown. Detailed Implementation

[0024] The technical solutions of the embodiments of this disclosure will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of this disclosure. All other embodiments obtained by those skilled in the art based on the embodiments of this disclosure without creative effort are within the protection scope of the embodiments of this disclosure.

[0025] Example 1

[0026] Reference Figure 1 The flowchart illustrating the steps of a process generation method in one embodiment of this disclosure is as follows.

[0027] Step 101: Obtain candidate access objects belonging to the target area and determine the topic of the candidate access objects.

[0028] The embodiments of this disclosure can be applied to trip information specifying access to a target area, to assist users in efficiently and effectively accessing candidate access objects within that target area. The methods of the embodiments of this disclosure can be executed by a backend server, and a client interface can also be configured for users to select target areas.

[0029] The target area can be a business district, shopping mall, or other area defined by rules. The embodiments of this disclosure can generate itinerary information for the target area, so that users can play in the target area and save playtime.

[0030] Candidate access objects can be such as restaurants, tourist attractions, etc. In practical applications, all access objects can be pre-stored, along with their location information. This allows the system to determine whether an access object is a candidate for the target area based on its location information.

[0031] The themes of candidate visit objects can be predetermined by humans and stored together with location information. It can be understood that the themes of candidate visit objects can be categorized according to certain rules, such as parent-child, education, couples, etc., thereby obtaining itinerary information for different themes.

[0032] Step 102: For each topic, determine the time matching degree between the target access time and each candidate access object based on the preset start time and preset end time of each candidate access object corresponding to the topic.

[0033] The preset start and end times can be the earliest and latest access times for the candidate access objects. For example, for a restaurant, the preset start and end times can be 11:00 AM, 12:00 PM, or 5:00 PM to 7:00 PM, while some special candidate access objects may have specific business hours.

[0034] Specifically, the time matching degree between the target access time and the candidate access object can be determined based on whether the target access time falls between a preset start time and a preset end time. If it does, the time matching degree is set to a large value; otherwise, it is set to 0. Alternatively, a more accurate time matching degree can be determined based on the target access time's position between the preset start time and the preset end time. For example, the time matching degree is highest when the target access time is at the very midpoint between the preset start time and the preset end time; the closer the target access time is to the preset start time or the preset end time, the lower the time matching degree.

[0035] It is understood that the target access time is the time when the candidate access object is to be accessed. In the initial state, the target access time can be a preset start time for playing, for example, the start time of playing can be set to 07:00 and the end time of playing can be set to 19:00, so that the embodiments of this disclosure can generate itinerary information from 07:00 to 19:00. Of course, in a piece of itinerary information, different target access times are for different candidate access objects.

[0036] Step 103: Calculate the quality score of the candidate access object based on its feature information.

[0037] The characteristic information of the candidate access object may include, but is not limited to: the candidate access object's historical access volume, historical rating, and distance to the most recent candidate access object.

[0038] Specifically, the quality score (QS) of the candidate access object can be a weighted value of the feature information, as shown in the following formula:

[0039]

[0040] Where I is the number of feature information, w i The weight corresponding to the i-th feature information is... CI i f represents the value of the i-th feature information. i (CI i The value CI of the i-th feature information i Converted to a quality score, for certain feature information, a higher value indicates a better quality candidate, such as historical visit volume and historical ratings. i (CI i The function f can be a positive function of the feature information as variables. In its simplest form, the feature information values ​​can be directly used as the function's output, i.e.: f i (CI i ) = CI i Of course, it can also be used for CI. i Perform the conversion, but ensure that the function's output value matches CI. i The relationship is positively correlated; however, for another part of the feature information, the larger the value, the worse the quality of the candidate access object. For example, the distance between the candidate access object and the nearest candidate access object, thus f i (CI i The function f can be the inverse function of the feature information values. The simplest approach is to directly use the reciprocal of the feature information values ​​as the function's output, i.e.: f i (CI i )=1 / CI i Of course, it can also be applied to 1 / CI. i Perform the conversion, but ensure that the function's output value matches CI. i They form an inverse functional relationship.

[0041] Step 104: For each topic, select a target access object from the candidate access objects corresponding to the topic based on the time matching degree and the quality score, and add the target access object and the target access time to the itinerary information corresponding to the topic.

[0042] Specifically, for a target access time, candidate access objects with a high time matching degree and high quality score can be selected and added to the trip information.

[0043] In addition, to further ensure the high quality of travel information, candidate access objects with a time matching degree less than a certain matching degree threshold or a quality score less than a certain quality score threshold can be removed.

[0044] The embodiments disclosed herein can select target access objects from candidate access objects for each topic, thereby generating trip information for that topic, and realizing topic-based information formation.

[0045] In summary, the embodiments of this disclosure provide a trip generation method, which includes: acquiring candidate visit objects belonging to a target area and determining the theme of the candidate visit objects; for each theme, determining the time matching degree between a target visit time and each candidate visit object based on a preset start time and a preset end time corresponding to the theme; calculating the quality score of the candidate visit objects based on the feature information of the candidate visit objects; for each theme, selecting a target visit object from the candidate visit objects corresponding to the theme based on the time matching degree and the quality score, and adding the target visit object and the target visit time to the trip information corresponding to the theme. By evaluating candidate visit objects and selecting target visit objects to add to the trip information, it is helpful to reduce labor costs and improve efficiency and timeliness.

[0046] Example 2

[0047] Reference Figure 2 The flowchart illustrating the specific steps of the process generation method in another embodiment of this disclosure is as follows.

[0048] Step 201: Obtain candidate access objects belonging to the target area, and calculate the cosine similarity between the feature vector of the candidate access object and the feature vector of the candidate topic.

[0049] In this model, both the feature vectors of candidate access objects and candidate topics describe the candidate access objects and candidate topics from the same dimension, resulting in two feature vectors with the same dimension. Each feature can be obtained from a pre-trained existing vector dictionary, and then the vectors corresponding to features from multiple dimensions are concatenated to form the feature vector. Generating feature vectors is a relatively mature technique and will not be elaborated upon here.

[0050] Specifically, the cosine similarity CS can be calculated using the following formula:

[0051]

[0052] Where J is the dimension of the feature vector, FV1 j FV2 represents the value of the feature vector of the candidate access object in the j-th dimension. j Let be the value of the feature vector of the candidate topic in the j-th dimension.

[0053] Because after the feature vector is normalized Therefore, formula (2) becomes the following formula:

[0054]

[0055] Step 202: If the cosine similarity is greater than or equal to a preset similarity threshold, then the candidate topic is determined as the topic of the candidate access object.

[0056] The preset similarity threshold can be set according to the actual application scenario, and the embodiments disclosed herein do not impose any restrictions on it.

[0057] It is understood that if the cosine similarity is less than a preset similarity threshold, then the candidate topic is determined not to be the topic of the candidate access object.

[0058] In the embodiments of this disclosure, after determining the topic of each candidate access object, the candidate access objects are clustered according to the topic to obtain one or more candidate access objects for each topic. Then, the candidate access objects in each topic can be filtered, for example, removing candidate access objects with low ratings and poor access rates. Furthermore, the category of the candidate access object can be considered during the removal process, retaining candidate access objects of a specified category regardless of their ratings or access volume. For example, restaurants can be designated as a specified category, requiring that the itinerary information include restaurants. Of course, the specified category can also be set to other categories, and the embodiments of this disclosure do not limit this.

[0059] The embodiments of this disclosure can determine the topic of a candidate access object based on a feature vector composed of multiple dimensions, which helps to improve the accuracy of the topic.

[0060] Step 203: For each candidate access object of the topic, if the target access time is greater than the preset start time of the candidate access object, or if the target access time is less than the preset end time of the candidate access object, then the time matching degree between the target access time and the candidate access object is determined to be the minimum time matching degree.

[0061] Step 204: For each candidate access object of the topic, if the target access time is greater than the midpoint between the preset start time and the preset end time of the candidate access object, and the target access time is less than or equal to the preset end time, then the time matching degree between the target access time and the candidate access object is determined based on the difference between the preset end time of the candidate access object and the target access time.

[0062] Step 205: For each candidate access object of the topic, if the target access time is less than or equal to the midpoint between the preset start time and the preset end time of the candidate access object, and the target access time is less than or equal to the preset end time, then the time matching degree between the target access time and the candidate access object is determined based on the difference between the target access time and the preset start time of the candidate access object.

[0063] Specifically, steps 203 to 205 yield the following formula:

[0064]

[0065] Where TMD is the time matching degree, t is the target access time, and TMD min For the minimum time matching degree, such as 0 or a smaller value, t max t min These are the preset start and preset end times for the candidate access objects.

[0066] The embodiments disclosed herein can accurately express the time matching degree based on functional relationships.

[0067] Alternatively, in another embodiment of this disclosure, the time matching degree between the target access time and each of the candidate access objects is updated through the following steps A1 to A2:

[0068] Step A1: For each candidate access object, if the candidate access object is the target access object, then during the process of generating the itinerary information, the time matching degree between the subsequent target access time and the candidate access object is adjusted to 0.

[0069] In the embodiments of this disclosure, the target access time is updated as new target access objects are added to the trip information. For example, the initial target access time is 07:00, and the corresponding target access object is D1. If the access duration of the target access object is 2 hours, the target access time is updated to 09:00. At this time, a new target access object is determined, and so on, with the target access time continuously updated. Thus, for a target access time of 07:00, 09:00 is the subsequent target access time. That is, after the target access object D1 is added to the trip information, the time matching degree between the target access time 09:00 and the candidate access object D1 is directly set to 0, thereby avoiding adding D1 to the trip information again, and thus preventing duplicate target access objects from appearing in the same trip information.

[0070] Of course, it should be noted that for another trip information, D1 can be added to the trip information.

[0071] Step A2: If the candidate access object and the target access object belong to the same category, then during the generation of the trip information and other trip information, the time matching degree between the target access object and the candidate access object is reduced.

[0072] The categories can be set according to uniform rules, including but not limited to: restaurants, water shows, cinemas, and shopping. For example, if a candidate object is added to a trip information as a target candidate object, then for other candidate objects in the same category, after calculating the time matching degree between the candidate object and the target object, the time matching degree will be appropriately reduced to decrease the probability that the candidate object will be identified as the target object.

[0073] Specifically, the time matching degree can be reduced according to certain strategies. For example, it can be reduced proportionally according to certain parameters, as shown in the following formula:

[0074] TMD'=g·TMD (5)

[0075] Where g is the descent parameter, which is less than 1 and greater than 0; TMD is the time matching degree obtained by formula (4); and TMD' is the updated time matching degree. In practical applications, a suitable descent parameter g can be selected. For example, g can be 0.5, thereby reducing the time matching degree to half of its original value.

[0076] Furthermore, when setting the descent parameter, a smaller descent parameter can be set for the current trip information to significantly reduce the time matching degree during the generation of the current trip information, while a larger descent parameter can be set for the other trip information to slightly reduce the time matching degree during the generation of the other trip information.

[0077] The embodiments of this disclosure can avoid the same target access object appearing in the same trip information and minimize the possibility of the same target access object appearing between different trip information, thereby achieving the diversity of trip information.

[0078] Step 206: Calculate the quality score of the candidate access object based on its feature information.

[0079] This step can be referred to in the detailed explanation of step 103, and will not be repeated here.

[0080] Step 207: Perform a weighted calculation on the time matching degree and the quality score to obtain the comprehensive score of the candidate access object.

[0081] Specifically, for candidate access objects that do not update their time matching degree using formula (5), the comprehensive score TC can be calculated using the following formula:

[0082] TC = TMD·QS (6)

[0083] or,

[0084] TC = w tmd ·TMD+w qs QS (7)

[0085] For candidate access objects whose time matching degree is updated through formula (5), the comprehensive score TC can be calculated according to the following formula:

[0086] TC=TMD'·QS (8)

[0087] or,

[0088] TC = w tmd ·TMD'+w qs QS (9)

[0089] Where TMD is the result calculated by formula (4), TMD' is the result after being updated by formula (5), QS is the result calculated by formula (1), and w tmd For the weights of TMD, w qs The weights of QS, 1>w tmd >0,1>w qs >0, and w tmd +w qs =1.

[0090] Of course, formulas (6) to (9) can be further transformed to make the overall score a suitable value, as long as the following relationship is guaranteed: if the time matching degree is larger, the quality score is larger, and the overall score is larger; if the time matching degree is smaller, the quality score is smaller, and the overall score is smaller.

[0091] Step 208: For each topic, select the candidate access object with the highest comprehensive score and the time matching degree greater than or equal to the preset time matching degree threshold from the candidate access objects corresponding to the topic as the target access object.

[0092] The time matching threshold can be set according to the actual application scenario, and the embodiments disclosed herein do not impose any restrictions on it.

[0093] The embodiments of this disclosure can select the candidate access object with the highest comprehensive score from the candidate access objects with a time matching degree greater than a certain threshold as the target access object, which can further ensure the high quality of the itinerary information.

[0094] Step 209: Obtain the previous access object from the itinerary information corresponding to the topic.

[0095] In the embodiments of this disclosure, multiple target access objects can be added to the trip information. After adding a target access object, the target access time needs to be updated to shift it forward. Thus, the previous access object becomes the target access object corresponding to the previous target access time. For example, first, a target access object OBJ1 with a target access time of 07:00 is added to the trip information; then, a target access object OBJ2 is added to the trip information, and at this time, the target access time needs to be updated so that the previous access object is OBJ1.

[0096] Step 210: Calculate the transfer duration based on the distance between the previous accessed object and the target accessed object.

[0097] Specifically, each access object has a geographical location. The distance between two geographical locations can be calculated using Euclidean distance, and then the distance is divided by the speed to obtain the transfer time. For example, if the distance between the previous access object OBJ1 and the target access object OBJ2 is DIS, and the transfer method is by vehicle with a speed of V, then the time required to transfer from the previous access object OBJ1 to the target access object OBJ2 is DIS / V.

[0098] Step 211: Determine the expected end time based on the transfer duration and the preset access duration of the target access object.

[0099] The preset access duration is the time required to access the target object, which can be set based on experience. For example, if the target object is a restaurant, the preset access duration can be 30 minutes; if the target object is a park, the preset access duration can be 3 hours.

[0100] Specifically, the expected end time can be determined using the following formula:

[0101] t'=t+t vis +t tra (10)

[0102] Where t' is the expected end time, t is the target access time, and t vis t is the preset access duration. tra For transfer duration.

[0103] Step 212: If the expected end time is less than or equal to the preset trip end time, then add the target access object and the target access time to the trip information corresponding to the topic, and update the target access time to the expected end time.

[0104] The embodiments of this disclosure can determine in advance whether the expected end time after accessing the target access object exceeds the preset trip end time before adding the target access object, so as to ensure the time accuracy of the trip information and avoid the actual access end time of the trip exceeding the preset trip end time.

[0105] Furthermore, embodiments of this disclosure can also update the target access time after adding a target access object, that is, the time when the target access object is completed, i.e., the expected end time, as the new target access time, so as to continue adding target access objects accessed at the new target access time.

[0106] Optionally, in another embodiment of this disclosure, the itinerary information includes multiple target access objects, each target access object having a preset tag, and the method further includes steps B1 to B3 to add target tags to the itinerary information:

[0107] Step B1: Calculate the ratio of the number of times each tag appears in the trip information to the total number of times all tags appear.

[0108] Specifically, for one of the labels, the ratio RTO can be calculated using the following formula. k :

[0109]

[0110] Among them, TMS kLet TMS1 be the number of occurrences of the k-th tag, and K be the number of tags in the trip information. For example, for a trip information, there are five target access objects OBJ1, OBJ2, OBJ3, OBJ4, and OBJ5. OBJ1 corresponds to tag LBL1, OBJ2 corresponds to tags LBL2 and LBL3, OBJ3 corresponds to tags LBL1, LBL2, and LBL3, OBJ4 corresponds to tags LBL1 and LBL3, and OBJ5 corresponds to tags LBL2 and LBL3. Therefore, K = 3, the occurrence count of LBL1 is 2 (TMS1), the occurrence count of LBL2 is 3 (TMS2), and the occurrence count of LBL3 is 4 (TMS3).

[0111] Step B2: For each tag, the ratio is weighted using the preset tag weight to obtain the quality score of the tag.

[0112] Specifically, the quality score of the label can be calculated using the following formula:

[0113] LQS k =w k ·RTO k (12)

[0114] Among them, LQS k For the quality score of the k-th label, w k The preset label weight for the k-th label can be set according to the actual application scenario.

[0115] Embodiments of this disclosure can adjust the quality scores of tags by weighting them so that more important tags are assigned larger weights and thus have higher quality scores.

[0116] Step B3: Select the target label for the trip information from the labels based on the quality score of the labels.

[0117] Specifically, one or more tags with the highest quality scores can be used as the target tags for trip information.

[0118] Embodiments of this disclosure can determine target tags from the tags of the target access object in the trip information, making it easier for users to make decisions based on the tags.

[0119] Step 213: If the target access time is less than the preset trip end time, and there are objects among the candidate access objects of the topic that have not been added to the trip information, then the following steps are executed repeatedly for each topic: determining the time matching degree between the target access time and each candidate access object according to the preset start time and preset end time of each candidate access object corresponding to the topic, and the subsequent steps.

[0120] In embodiments of this disclosure, if the target access time is greater than or equal to the preset trip end time, or if there are no objects in the candidate access objects of the topic that have not been added to the trip information, then adding new target access objects to the trip information is stopped.

[0121] In practical applications, a maximum number of target access objects can also be set. If the number of target access objects in the trip information is less than the maximum number, target access objects can continue to be added; otherwise, the addition of target access objects will stop.

[0122] It is understood that in the embodiments of this disclosure, steps 203 to 212 are to generate a trip information for a topic. After generating a trip information, since the time matching degree is adjusted, new trip information can be generated according to the candidate access objects of the topic. This process is repeated to obtain multiple trip information until the number of trip information reaches the maximum value, or the time matching degree of all candidate access objects of the topic is adjusted to 0 by step A1.

[0123] The embodiments of this disclosure can continue to add new target access objects to the trip information when the target access time has not reached the trip end time and there are still remaining candidate access objects, so as to achieve as many accesses as possible within a reasonable time, which helps to improve the user's sense of fulfillment.

[0124] In summary, based on Embodiment 1, the embodiments of this disclosure provide another itinerary generation method. In addition to the beneficial effects of Embodiment 1, it can also determine the topic of candidate access objects based on feature vectors composed of multiple dimensions, which helps to improve the accuracy of the topic; it can also accurately express the time matching degree based on functional relationships; it can also avoid the same target access object in the same itinerary information and minimize the possibility of the same target access object appearing between different itinerary information, thus realizing the diversity of itinerary information; it can also avoid the actual access end time of the itinerary exceeding the preset itinerary end time; it can also determine the target tag from the tags of the target access object in the itinerary information, which facilitates users to make decisions based on the tags; and it can also generate multiple itinerary information for a topic.

[0125] Example 3

[0126] Reference Figure 3 The diagram shows a structural diagram of a trip generation apparatus according to another embodiment of this disclosure, as detailed below.

[0127] The topic determination module 301 is used to obtain candidate access objects belonging to the target area and determine the topic of the candidate access objects.

[0128] The time matching degree determination module 302 is used to determine the time matching degree between the target access time and each candidate access object for each topic, based on the preset start time and preset end time of each candidate access object corresponding to the topic.

[0129] The quality score determination module 303 is used to calculate the quality score of the candidate access object based on the feature information of the candidate access object.

[0130] The itinerary addition module 304 is used to select a target access object from the candidate access objects corresponding to the topic based on the time matching degree and the quality score for each topic, and add the target access object and the target access time to the itinerary information corresponding to the topic.

[0131] In summary, the embodiments of this disclosure provide a trip generation device, the device comprising: a topic determination module, configured to acquire candidate visit objects belonging to a target area and determine the topic of the candidate visit objects; a time matching degree determination module, configured to, for each topic, determine the time matching degree between a target visit time and each candidate visit object based on a preset start time and a preset end time corresponding to the topic; a quality score determination module, configured to calculate the quality score of the candidate visit objects based on the feature information of the candidate visit objects; and a trip addition module, configured to, for each topic, select a target visit object from the candidate visit objects corresponding to the topic based on the time matching degree and the quality score, and add the target visit object and the target visit time to the trip information corresponding to the topic.

[0132] Example 3 is a device embodiment corresponding to Example 1. For detailed description, please refer to Example 1, which will not be repeated here.

[0133] Example 4

[0134] Reference Figure 4 The diagram shows a structural diagram of a process generation apparatus in one embodiment of this disclosure, as detailed below.

[0135] A topic determination module 401 is used to acquire candidate access objects belonging to a target area and determine the topic of the candidate access objects; optionally, in an embodiment of this disclosure, the topic determination module 401 includes:

[0136] The cosine similarity calculation submodule 4011 is used to calculate the cosine similarity between the feature vector of the candidate access object and the feature vector of the candidate topic.

[0137] The topic determination module 4012 is used to determine the candidate topic as the topic of the candidate access object if the cosine similarity is greater than or equal to a preset similarity threshold.

[0138] A time matching degree determination module 402 is used to determine, for each topic, the time matching degree between the target access time and each candidate access object based on a preset start time and a preset end time corresponding to the topic; optionally, in an embodiment of this disclosure, the time matching degree determination module 402 includes:

[0139] The first time matching degree determination submodule 4021 is used to determine the time matching degree between the target access time and the candidate access object as the minimum time matching degree for each candidate access object of the topic if the target access time is greater than the preset start time of the candidate access object, or if the target access time is less than the preset end time of the candidate access object.

[0140] The second time matching degree determination submodule 4022 is used for each candidate access object of the topic, if the target access time is greater than the midpoint between the preset start time and the preset end time of the candidate access object, and the target access time is less than or equal to the preset end time, then the time matching degree between the target access time and the candidate access object is determined based on the difference between the preset end time of the candidate access object and the target access time.

[0141] The third time matching degree determination submodule 4023 is used for each candidate access object of the topic, if the target access time is less than or equal to the intermediate time between the preset start time and the preset end time of the candidate access object, and the target access time is less than or equal to the preset end time, then the time matching degree between the target access time and the preset start time of the candidate access object is determined based on the difference between the target access time and the preset start time of the candidate access object.

[0142] The quality score determination module 403 is used to calculate the quality score of the candidate access object based on the feature information of the candidate access object.

[0143] A trip adding module 404 is configured to, for each topic, select a target access object from the candidate access objects corresponding to the topic based on the time matching degree and the quality score, and add the target access object and the target access time to the trip information corresponding to the topic; optionally, in another embodiment of this disclosure, the trip adding module 404 includes:

[0144] The comprehensive score calculation submodule 4041 is used to perform a weighted calculation on the time matching degree and the quality score to obtain the comprehensive score of the candidate access object.

[0145] The target object determination submodule 4042 is used to select, for each topic, the candidate access object with the highest comprehensive score and a time matching degree greater than or equal to a preset time matching degree threshold from the candidate access objects corresponding to the topic as the target access object.

[0146] The previous access object acquisition submodule 4043 is used to obtain the previous access object from the trip information corresponding to the topic, which is the access object before the target access object.

[0147] The transfer duration calculation submodule 4044 is used to calculate the transfer duration based on the distance between the previous accessed object and the target accessed object.

[0148] The expected end time determination submodule 4045 is used to determine the expected end time based on the transfer duration and the preset access duration of the target access object.

[0149] The target access time update submodule 4046 is used to add the target access object and the target access time to the trip information corresponding to the topic if the expected end time is less than or equal to the preset trip end time, and update the target access time to the expected end time.

[0150] The loop execution module 405 is used to perform the following steps in a loop for each topic: if the target access time is less than a preset trip end time, and there are objects among the candidate access objects of the topic that have not been added to the trip information, then determine the time matching degree between the target access time and each candidate access object and the subsequent steps based on the preset start time and preset end time of each candidate access object corresponding to the topic.

[0151] Alternatively, in another embodiment of this disclosure, the time matching degree between the target access time and each of the candidate access objects is updated by the following module:

[0152] The first time matching degree adjustment module is used to adjust the time matching degree between the subsequent target access time and the time of the candidate access object to 0 during the process of generating the trip information if the candidate access object is the target access object.

[0153] The second time matching degree adjustment module is used to reduce the time matching degree between the target access object and the candidate access object when the candidate access object and the target access object belong to the same category, during the process of generating the trip information and other trip information.

[0154] Optionally, in another embodiment of this disclosure, the itinerary information includes multiple target access objects, each target access object having a preset tag, and the device further includes the following modules:

[0155] The frequency ratio calculation module is used to calculate the ratio of the frequency of each tag in the trip information to the total frequency of all tags.

[0156] The quality score calculation module is used to perform a weighted calculation on the ratio of each tag using the preset tag weight to obtain the quality score of the tag.

[0157] The target label generation module is used to select target labels for the trip information from the labels based on the quality scores of the labels.

[0158] In summary, based on Embodiment 3, the embodiments of this disclosure provide another itinerary generation device. In addition to the beneficial effects of Embodiment 3, it can also determine the topic of candidate access objects based on feature vectors composed of multiple dimensions, which helps to improve the accuracy of the topic; it can also accurately express the time matching degree based on functional relationships; it can also avoid the same target access object in the same itinerary information and minimize the possibility of the same target access object appearing between different itinerary information, thus realizing the diversity of itinerary information; it can also avoid the actual access end time of the itinerary exceeding the preset itinerary end time; it can also determine the target tag from the tags of the target access object in the itinerary information, which makes it convenient for users to make decisions based on the tags; and it can also generate multiple itinerary information for a topic.

[0159] Example 4 is a device embodiment corresponding to Example 2. For detailed description, please refer to Example 2, which will not be repeated here.

[0160] Embodiments of this disclosure also provide an electronic device, with reference to Figure 5 It includes: a processor 501, a memory 502, and a computer program 5021 stored in the memory 502 and executable on the processor. When the processor 501 executes the program, it implements the process generation method of the foregoing embodiments.

[0161] Embodiments of this disclosure also provide a readable storage medium that, when instructions in the storage medium are executed by a processor of an electronic device, enables the electronic device to perform the process generation method of the foregoing embodiments.

[0162] As the device embodiment is basically similar to the method embodiment, the description is relatively simple, and relevant parts can be found in the description of the method embodiment.

[0163] The algorithms and displays provided herein are not inherently related to any particular computer, virtual system, or other device. Various general-purpose systems can also be used in conjunction with the teachings herein. The required structure for constructing such systems is apparent from the above description. Furthermore, the embodiments of this disclosure are not directed to any particular programming language. It should be understood that the embodiments of this disclosure described herein can be implemented using various programming languages, and the above description of specific languages ​​is for the purpose of disclosing the best mode of implementation of the embodiments of this disclosure.

[0164] Numerous specific details are set forth in the specification provided herein. However, it will be understood that embodiments of the present disclosure may be practiced without these specific details. In some instances, well-known methods, structures, and techniques have not been shown in detail so as not to obscure the understanding of this specification.

[0165] Similarly, it should be understood that, in order to streamline this disclosure and aid in understanding one or more of the various inventive aspects, in the foregoing description of exemplary embodiments of the present disclosure, various features of the embodiments of the present disclosure are sometimes grouped together in a single embodiment, figure, or description thereof. However, this approach to disclosure should not be construed as reflecting an intention that the claimed embodiments of the present disclosure require more features than expressly recited in each claim. Rather, as reflected in the following claims, inventive aspects lie in fewer than all features of a single foregoing disclosed embodiment. Therefore, the claims following the detailed description are hereby expressly incorporated into that detailed description, wherein each claim itself is a separate embodiment of the present disclosure.

[0166] Those skilled in the art will understand that modules in the device of the embodiments can be adaptively changed and placed in one or more devices different from that embodiment. Modules, units, or components in the embodiments can be combined into a single module, unit, or component, and further, they can be divided into multiple sub-modules, sub-units, or sub-components. Except where at least some of such features and / or processes or units are mutually exclusive, any combination can be used to combine all features disclosed in this specification (including the accompanying claims, abstract, and drawings) and all processes or units of any method or device so disclosed. Unless expressly stated otherwise, each feature disclosed in this specification (including the accompanying claims, abstract, and drawings) may be replaced by an alternative feature that serves the same, equivalent, or similar purpose.

[0167] The various component embodiments of this disclosure can be implemented in hardware, or as software modules running on one or more processors, or a combination thereof. Those skilled in the art will understand that microprocessors or digital signal processors (DSPs) can be used in practice to implement some or all of the functions of some or all of the components in the stroke generation apparatus according to the embodiments of this disclosure. Embodiments of this disclosure can also be implemented as device or apparatus programs for performing some or all of the methods described herein. Such programs implementing embodiments of this disclosure can be stored on a computer-readable medium or can be in the form of one or more signals. Such signals can be downloaded from an Internet website, provided on a carrier signal, or provided in any other form.

[0168] It should be noted that the above embodiments are illustrative of embodiments of this disclosure and not restrictive of embodiments of this disclosure, and that those skilled in the art can devise alternative embodiments without departing from the scope of the appended claims. In the claims, any reference signs placed between parentheses should not be construed as limiting the claims. The word "comprising" does not exclude the presence of elements or steps not listed in a claim. The word "a" or "an" preceding an element does not exclude the presence of a plurality of such elements. Embodiments of this disclosure can be implemented by means of hardware comprising several different elements and by means of a suitably programmed computer. In the unit claims enumerating several means, several of these means may be embodied by the same item of hardware. The use of the words first, second, and third, etc., does not indicate any order. These words can be interpreted as names.

[0169] Those skilled in the art will understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0170] The above description is only a preferred embodiment of the present disclosure and is not intended to limit the embodiments of the present disclosure. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of the embodiments of the present disclosure should be included within the protection scope of the embodiments of the present disclosure.

[0171] The above description is merely a specific implementation of the embodiments of this disclosure, but the protection scope of the embodiments of this disclosure is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the technical scope disclosed in the embodiments of this disclosure should be included within the protection scope of the embodiments of this disclosure. Therefore, the protection scope of the embodiments of this disclosure should be determined by the protection scope of the claims.

Claims

1. A method of generating a trip, characterized by, The method comprises: acquiring candidate access objects belonging to a target area, and determining subjects of the candidate access objects; for each subject, determining a time matching degree between a target access time and each candidate access object corresponding to the subject according to a preset start time and a preset end time of each candidate access object corresponding to the subject; calculating a quality score of each candidate access object according to feature information of the candidate access object; for each subject, selecting a target access object from the candidate access objects corresponding to the subject according to the time matching degree and the quality score, and adding the target access object corresponding to the target access time to itinerary information corresponding to the subject; the step of adding the target access object corresponding to the target access time to the itinerary information corresponding to the subject comprises: acquiring an access object before the target access object from the itinerary information corresponding to the subject to obtain a previous access object; calculating a transfer duration according to a distance between the previous access object and the target access object; determining an expected end time according to the transfer duration and a preset access duration of the target access object; if the expected end time is less than or equal to a preset itinerary end time, adding the target access object corresponding to the target access time to the itinerary information corresponding to the subject, and updating the target access time to the expected end time; after the step of adding the target access object corresponding to the target access time to the itinerary information corresponding to the subject, the method further comprises: if the target access time is less than the preset itinerary end time, and there is an object in the candidate access objects of the subject that has not been added to the itinerary information, cyclically executing the steps of determining a time matching degree between a target access time and each candidate access object corresponding to the subject according to a preset start time and a preset end time of each candidate access object corresponding to the subject for each subject and the subsequent steps; the step of selecting a target access object from the candidate access objects corresponding to the subject according to the time matching degree and the quality score for each subject comprises: performing weighted operation on the time matching degree and the quality score to obtain a comprehensive score of the candidate access object; for each subject, selecting a candidate access object with the highest comprehensive score and a time matching degree greater than or equal to a preset time matching degree threshold from the candidate access objects corresponding to the subject as a target access object.

2. The method of claim 1, wherein, the step of determining a time matching degree between a target access time and each candidate access object corresponding to the subject according to a preset start time and a preset end time of each candidate access object corresponding to the subject comprises: If the target access time is greater than the preset start time of the candidate access object or the target access time is less than the preset end time of the candidate object, the time matching degree of the target access time and the candidate access object is determined as a minimum time matching degree; If the target access time is greater than the intermediate time of the preset start time and the preset end time of the candidate access object and the target access time is less than or equal to the preset end time, the time matching degree of the target access time and the candidate access object is determined according to a difference between the preset end time of the candidate access object and the target access time; If the target access time is less than or equal to the intermediate time of the preset start time and the preset end time of the candidate access object and the target access time is less than or equal to the preset end time, the time matching degree of the target access time and the candidate access object is determined according to a difference between the target access time and the preset start time of the candidate access object.

3. The method of claim 1, wherein, The time matching degree of the target access time and each candidate access object is updated by the following steps: If the candidate access object is the target access object, the time matching degree of the target access time and the candidate access object is adjusted to 0 in the process of generating the itinerary information; if the candidate access object and the target access object belong to the same category, the time matching degree of the target access object and the candidate access object is reduced in the process of generating the itinerary information and the remaining itinerary information.

4. The method of claim 1, wherein, The itinerary information includes a plurality of target access objects, and the target access objects are preset with labels, and the method further includes: calculating a ratio of the occurrence times of each label in the itinerary information to the total occurrence times of the labels; for each label, performing a weighted operation on the ratio by using a preset label weight of the label to obtain a quality score of the label; selecting a target label of the itinerary information from the labels according to the quality scores of the labels.

5. The method of claim 1, wherein, The step of determining the theme of the candidate access object includes: calculating a cosine similarity between a feature vector of the candidate access object and a feature vector of a candidate theme; if the cosine similarity is greater than or equal to a preset similarity threshold, the candidate theme is determined as the theme of the candidate access object.

6. A trip generating device characterized by comprising: The device includes: a theme determination module configured to obtain candidate access objects in a target region and determine themes of the candidate access objects; a time matching degree determination module configured to determine, for each theme, a time matching degree of a target access time and each candidate access object according to a preset start time and a preset end time of each candidate access object corresponding to the theme; and a target access object determination module configured to determine a target access object in the target region according to the time matching degree of the target access time and each candidate access object corresponding to each theme. a quality score determination module configured to calculate a quality score of the candidate visiting object according to the characteristic information of the candidate visiting object; a trip adding module configured to, for each of the themes, select a target visiting object from the candidate visiting objects corresponding to the theme according to the time matching degree and the quality score, and add the target visiting object and the target visiting time corresponding to the target visiting object into the trip information corresponding to the theme; the step of adding the target visiting object and the target visiting time corresponding to the target visiting object into the trip information corresponding to the theme comprises: obtaining a previous visiting object before the target visiting object from the trip information corresponding to the theme, to obtain a last visiting object; calculating a transfer duration according to a distance between the last visiting object and the target visiting object; determining an expected end time according to the transfer duration and a preset visiting duration of the target visiting object; if the expected end time is less than or equal to a preset trip end time, adding the target visiting object and the target visiting time corresponding to the target visiting object into the trip information corresponding to the theme, and updating the target visiting time as the expected end time; after the step of adding the target visiting object and the target visiting time corresponding to the target visiting object into the trip information corresponding to the theme, the method further comprises: if the target visiting time is less than the preset trip end time, and there is an object in the candidate visiting objects of the theme that has not been added into the trip information, then cyclically performing the steps of, for each of the themes, determining a target visiting time and a time matching degree of each of the candidate visiting objects corresponding to the theme according to a preset start time and a preset end time of each of the candidate visiting objects corresponding to the theme, and selecting a target visiting object from the candidate visiting objects corresponding to the theme according to the time matching degree and the quality score; the step of selecting a target visiting object from the candidate visiting objects corresponding to the theme according to the time matching degree and the quality score comprises: performing a weighted operation on the time matching degree and the quality score to obtain a comprehensive score of the candidate visiting object; for each of the themes, selecting a candidate visiting object with the highest comprehensive score and a time matching degree greater than or equal to a preset time matching degree threshold from the candidate visiting objects corresponding to the theme as a target visiting object.

7. An electronic device, comprising: comprise: a processor, a memory, and a computer program stored in the memory and executable on the processor, wherein the processor implements the trip generation method according to one or more of claims 1-5 when executing the program.

8. A readable storage medium, characterized by, When the instructions in the storage medium are executed by the processor of the electronic device, the electronic device can execute the trip generation method according to one or more of claims 1-5.

Images