Route determination method and device, equipment, medium and program product
By receiving origin and destination information and calling the first model of the training sample set, routes that meet the rationality parameters are identified, thus solving the problem of recommending unreasonable routes in path planning and improving the rationality of route recommendations and user experience.
Patent Information
- Application Number
- CN202511073619.X
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-07-31
- Publication Date
- 2025-11-18
AI Technical Summary
Existing path planning methods cannot identify unreasonable routes and may prioritize recommending unreasonable routes.
By receiving the start and end information, the system calls the first model determined based on the rationality parameters of the training sample set, and outputs the target route information that meets the preset conditions for the rationality parameters. The positive samples of the training sample set include sample routes that meet the conditions for the rationality parameters, and the negative samples include sample routes that do not meet the conditions.
The rationality of recommended routes has been improved, user experience has been enhanced, and it has been ensured that recommended routes meet preset conditions.
Smart Images
Figure CN120974185A_ABST
Abstract
Description
TECHNICAL FIELD
[0001] Embodiments of the present disclosure relate to computer technology, and in particular, to a route determination method, device, apparatus, medium and program product. BACKGROUND
[0002] With the development of computer technology and Internet technology, path planning functions are widely used. More and more users determine the best route between the starting point and the ending point with the help of path planning functions. However, the path planning manner in the related art cannot identify unreasonable routes, and there may be a situation of preferentially recommending unreasonable routes. SUMMARY
[0003] Embodiments of the present disclosure provide a route determination method, device, apparatus, medium and program product, which can improve the rationality of recommended routes.
[0004] In a first aspect, embodiments of the present disclosure provide a route determination method, comprising:
[0005] receiving starting point information and ending point information;
[0006] calling a first model based on the starting point information and the ending point information, wherein a training sample set of the first model is determined based on a rationality parameter of a sample route, positive samples of the training sample set include sample routes whose rationality parameters satisfy a first preset condition, and negative samples of the training sample set include sample routes whose rationality parameters do not satisfy the first preset condition;
[0007] outputting target route information containing the starting point information and the ending point information according to a calling result of the first model, wherein a rationality parameter of a target route satisfies the first preset condition.
[0008] In a second aspect, embodiments of the present disclosure further provide a route determination device, comprising:
[0009] an information receiving module configured to receive starting point information and ending point information;
[0010] a model calling module configured to call a first model based on the starting point information and the ending point information, wherein a training sample set of the first model is determined based on a rationality parameter of a sample route, positive samples of the training sample set include sample routes whose rationality parameters satisfy a first preset condition, and negative samples of the training sample set include sample routes whose rationality parameters do not satisfy the first preset condition;
[0011] a route determination module configured to output target route information containing the starting point information and the ending point information according to a calling result of the first model, wherein a rationality parameter of a target route satisfies the first preset condition.
[0012] In a third aspect, the embodiments of the present disclosure further provide an electronic device, the electronic device comprising:
[0013] one or more processors;
[0014] a storage device configured to store one or more programs,
[0015] when the one or more programs are executed by the one or more processors, the one or more processors implement the route determination method according to any embodiment of the present disclosure.
[0016] In a fourth aspect, the embodiments of the present disclosure further provide a storage medium containing computer executable instructions for performing the route determination method according to any embodiment of the present disclosure when executed by a computer processor.
[0017] In a fifth aspect, the embodiments of the present disclosure further provide a computer program product comprising a computer program which, when executed by a processor, implements the route determination method according to any embodiment of the present disclosure.
[0018] The embodiments of the present disclosure provide a route determination method, by receiving start point information and end point information, calling a first model based on the start point information and the end point information, the training sample set of the first model being determined based on a rationality parameter of a sample route, the positive sample of the training sample set including a sample route whose rationality parameter meets a first preset condition, the negative sample of the training sample set including a sample route whose rationality parameter does not meet the first preset condition, and outputting target route information containing the start point information and the end point information according to the calling result of the first model, the rationality parameter of the target route meeting the first preset condition. In the embodiments of the present disclosure, since the positive sample in the training sample set of the first model includes a sample route whose rationality parameter meets the first preset condition, and the negative sample includes a sample route whose rationality parameter does not meet the first preset condition, the first model can be trained based on the training sample set, so that the first model has the ability to identify a route whose rationality parameter meets the first preset condition. By calling the first model to determine a target route whose rationality parameter meets the first preset condition based on the start point information and the end point information, the problem that an unreasonable route may be preferentially recommended in the path planning manner in the related art is solved, the rationality of the recommended target route is improved, and the user experience is improved. BRIEF DESCRIPTION OF DRAWINGS
[0019] The above and other features, advantages, and aspects of the embodiments of the present disclosure will become more apparent when described in connection with the following detailed description in conjunction with the accompanying drawings. Throughout the drawings, same or similar reference numerals can represent same or similar elements. It should be understood that the drawings are schematic and elements and features are not necessarily drawn to scale.
[0020] Figure 1A flowchart of a route determination method provided by an embodiment of the present disclosure;
[0021] Figure 2 A flowchart of a training method of a first model in a route determination method provided by an embodiment of the present disclosure;
[0022] Figure 3 A schematic diagram of a sparse section of a sample route provided by an embodiment of the present disclosure;
[0023] Figure 4 A flowchart of a training method of another first model in a route determination method provided by an embodiment of the present disclosure;
[0024] Figure 5 A structural schematic diagram of a route determination apparatus provided by an embodiment of the present disclosure;
[0025] Figure 6 A structural schematic diagram of an electronic device provided by an embodiment of the present disclosure. DETAILED DESCRIPTION
[0026] Embodiments of the present disclosure will be described in more detail by referring to the drawings. Although certain embodiments of the present disclosure are shown in the drawings, it is understood that the present disclosure can be implemented in various forms and should not be construed as being limited to the embodiments set forth herein, but rather these embodiments are provided so as to more completely and thoroughly understand the present disclosure. It is understood that the drawings and embodiments of the present disclosure are for exemplary purposes only and are not intended to limit the scope of the present disclosure.
[0027] It should be understood that each of the steps recited in the method embodiments of the present disclosure can be executed in different orders and / or in parallel. In addition, the method embodiments can include additional steps and / or omit the execution of the steps shown. The scope of the present disclosure is not limited in this respect.
[0028] The term “comprising” and variations thereof as used herein are open-ended, that is, “including but not limited to”. The term “based on” is “based, at least in part, on”. The term “one embodiment” means “at least one embodiment”; the term “another embodiment” means “at least one additional embodiment”; the term “some embodiments” means “at least some embodiments”. Related definitions are given below in the description of the terms.
[0029] It should be noted that the terms “first”, “second”, and the like mentioned in the present disclosure are merely used to distinguish different devices, modules or units, and are not intended to limit the order or interdependence of the functions performed by these devices, modules or units.
[0030] It should be noted that the modification of "one" and "multiple" mentioned in the present disclosure is illustrative but not restrictive, and those skilled in the art should understand that "one or more" should be understood unless otherwise explicitly indicated in the context.
[0031] The names of the messages or information exchanged between the plurality of devices in the embodiments of the present disclosure are only for illustrative purposes, and are not used to limit the scope of the messages or information.
[0032] It can be understood that, before using the technical solutions disclosed in the embodiments of the present disclosure, the type, use range, use scenario, etc. of the personal information involved in the present disclosure should be informed to the user and the authorization of the user should be obtained through appropriate means according to relevant laws and regulations.
[0033] For example, in response to receiving the active request of the user, the prompt information is sent to the user to explicitly prompt the user that the operation requested to be performed will require obtaining and using the personal information of the user. Thus, the user can voluntarily choose whether to provide the personal information to the software or hardware such as electronic device, application program, server or storage medium, etc. that performs the operation of the technical solutions of the present disclosure according to the prompt information.
[0034] As an optional but non-limiting implementation manner, in response to receiving the active request of the user, the prompt information can be sent to the user in the form of a pop-up window, and the prompt information can be presented in the form of text in the pop-up window. In addition, the pop-up window can also carry selection controls for the user to select "agree" or "disagree" to provide the personal information to the electronic device.
[0035] It can be understood that the above notification and user authorization process is only illustrative, and does not limit the implementation manners of the present disclosure, and other manners meeting the relevant laws and regulations can also be applied to the implementation manners of the present disclosure.
[0036] It can be understood that the data involved in the present technical solution (including but not limited to the data itself, the acquisition or use of the data) should comply with the requirements of the relevant laws and regulations and relevant provisions.
[0037] Figure 1 A flowchart of a route determination method provided by the embodiments of the present disclosure is shown. The embodiments of the present disclosure are applicable to path planning, and the method can be executed by a route determination device. The device can be realized in the form of software and / or hardware, and can be realized by an electronic device, which can be a mobile terminal, a PC terminal or a server, etc.
[0038] As shown in Figure 1 The method comprises:
[0039] S110, receiving start point information and end point information.
[0040] The start point information can be a start point position of a route requested by the route requester. The end point information can be an end point position of the route requested by the route requester. For example, the start point information and the end point information can be address information or coordinate information, etc. The start point information and the end point information can be input by the route requester. Alternatively, the start point information and the end point information can be obtained by an interface of a third-party application. The embodiments of the present disclosure are not limited in this regard.
[0041] In S120, a first model is invoked based on the start point information and the end point information. The training sample set of the first model is determined based on the rationality parameter of the sample route. The positive sample of the training sample set includes the sample route whose rationality parameter meets a first preset condition. The negative sample of the training sample set includes the sample route whose rationality parameter does not meet the first preset condition.
[0042] In some embodiments, the first model can be an artificial intelligence model for route sorting in a route planning engine. The first model is trained based on a training sample set. The training sample set includes a plurality of reference route samples and a plurality of candidate route samples corresponding to each reference route sample. The positive sample in the training sample set is determined based on the sample route whose rationality parameter meets a first preset condition. The negative sample in the training sample set is determined based on the sample route whose rationality parameter does not meet the first preset condition. The rationality parameter includes at least one of a local detour judgment parameter, a reverse judgment parameter, and an inefficient route judgment parameter. The first preset condition is used to determine whether the sample route has at least one of other unreasonable conditions such as local detour, reverse route, or inefficient route. In some embodiments, if the rationality parameter of the route sample meets the first preset condition, the route sample can be used as a positive sample. If the rationality parameter of the route sample does not meet the first preset condition, the route sample can be used as a negative sample. In some embodiments, the route sample includes a reference route sample and a candidate route sample. The route network identifier sequence of the candidate route sample whose rationality parameter meets the first preset condition is compared with that of the reference route sample to obtain a non-overlapping identifier of the route network identifier. The route similarity is determined based on the non-overlapping route network identifier, and the candidate sample with the highest route similarity is used as a positive sample. The candidate route samples of the reference route sample other than the positive sample are used as negative samples.
[0043] The local detour judgment parameter is used to determine whether the route sample has a local detour. The reverse judgment parameter is used to describe the reverse information of the route sample. The inefficient route judgment parameter is used to determine an inefficient route with a longer time or a longer distance by comparing different routes.
[0044] In some embodiments, the sample route includes a reference route sample and a plurality of candidate route samples corresponding to the reference route sample. The similarity of the candidate route samples to the reference route sample satisfies a second preset condition. The reference route sample represents real trajectory information. For example, the reference route sample can include a route walked by a surveyor.
[0045] Exemplarily, the coordinate information of the reference route sample is matched to the road network of the electronic map to obtain a road network identifier sequence corresponding to the reference route sample. Based on the start point information, the end point information and the heat information of the road of the reference route sample, a plurality of candidate route samples similar to the reference route sample are determined. The road network identifier sequence of the candidate route sample can be used to represent the candidate route sample.
[0046] In some embodiments, for any reference route sample, based on a local detour determination parameter, it is determined whether the current reference route sample and the candidate route sample corresponding to the current reference route sample are a local detour route. Based on a reverse determination parameter, reverse information of the current reference route sample and the candidate route sample corresponding to the current reference route sample is determined. Based on the reverse information, a reverse route is determined. For the candidate route sample corresponding to the current reference route sample, the local detour route and the reverse route are excluded to obtain a to-be-compared candidate route sample. For example, the road network identifier sequences corresponding to any two to-be-compared candidate route samples are compared. The comparison result is a difference road segment in which the road network identifier sequences do not coincide. Based on attribute information of a difference road segment with a longer length and attribute information of a difference road segment with a shorter length, it is determined that the to-be-compared candidate route sample containing the difference road segment with the longer length is an inefficient route. The attribute information includes at least one of route length, number of turns and heat information.
[0047] The candidate route sample in which the local detour determination parameter, the reverse determination parameter and the inefficient route determination parameter all satisfy the first preset condition is determined as a target route sample. The similarity of the target route sample to the reference route sample is determined, and the target route sample in which the similarity satisfies a preset condition is taken as a positive sample. The similarity satisfying the preset condition can be, for example, the highest similarity, or the top N ranked similarity, or the similarity reaching a preset threshold, where N is a natural number. The candidate route sample corresponding to the current reference route sample other than the positive sample is taken as a negative sample. The training sample set is constructed in the above manner, and the first model is trained based on the training sample set, so that the first model can identify a target route that is reasonable and similar to the reference route sample.
[0048] Exemplarily, based on the start point information and the end point information, the first model is called, including:
[0049] obtain a plurality of candidate routes including the start point information and the end point information; call the first model to determine a target route from the plurality of candidate routes or determine ranking information of the plurality of candidate routes, wherein the calling result of the first model includes the target route information or the ranking information of the plurality of candidate routes. In the embodiment of the present disclosure, since the first model can identify a target route that is reasonable and similar to the reference route sample, it is ensured that the target route output by the first model takes into account both route rationality and route preference.
[0050] In some embodiments, a plurality of candidate routes are generated based on the start point information and the end point information. Alternatively, a plurality of candidate routes are obtained from a database of a path planning engine based on the start point information and the end point information. The plurality of candidate routes are input into the first model, and the plurality of candidate routes are scored by the first model to determine a target route whose score meets a preset condition, wherein the score meeting the preset condition may, for example, be the highest score, or a score ranking in the top N positions, or a score reaching a preset threshold. Alternatively, the plurality of candidate routes are input into the first model, and the plurality of candidate routes are scored by the first model to determine ranking information of the plurality of candidate routes based on the scores of the candidate routes.
[0051] Alternatively, generating a plurality of candidate routes based on the start point information and the end point includes generating a shortest path based on the start point information and the end point information based on a path planning algorithm. The shortest path is a route between the start point and the end point that has the shortest time or the shortest distance. The plurality of candidate routes are generated based on the shortest path. The candidate routes are suboptimal routes whose start point and end point are the same as the shortest path, but whose time or distance is greater than that of the reference route.
[0052] S130, according to the calling result of the first model, output target route information including the start point information and the end point information, wherein the rationality parameter of the target route meets the first preset condition.
[0053] Since the positive samples of the first model include sample routes whose rationality parameters meet the first preset condition, and the negative samples include sample routes whose rationality parameters do not meet the first preset condition, training the first model based on the positive samples and the negative samples can enable the first model to have the ability to identify a reasonable route that meets the first preset condition. By inputting the plurality of candidate routes into the first model, the target route output by the first model is a route whose rationality parameter meets the first preset condition.
[0054] The calling result of the first model includes target route information or ranking information of the plurality of candidate routes. The target route information output by the first model is obtained, and the target route is displayed in an electronic map. Alternatively, the ranking information of the N candidate routes with the highest scores output by the first model is obtained, and the N candidate routes, time, distance, and other information are sequentially displayed in an electronic map for user selection.
[0055] The technical solution of the embodiments of the present disclosure receives the start point information and the end point information, calls a first model based on the start point information and the end point information, the training sample set of the first model is determined based on the rationality parameter of the sample route, the positive sample of the training sample set includes the sample route whose rationality parameter meets the first preset condition, the negative sample of the training sample set includes the sample route whose rationality parameter does not meet the first preset condition, and the target route information containing the start point information and the end point information is output according to the calling result of the first model, and the rationality parameter of the target route meets the first preset condition. In the embodiments of the present disclosure, since the positive sample in the training sample set of the first model includes the sample route whose rationality parameter meets the first preset condition, and the negative sample includes the sample route whose rationality parameter does not meet the first preset condition, the first model can be trained based on the training sample set, so that the first model has the ability to identify the route whose rationality parameter meets the first preset condition. By calling the first model to determine the target route whose rationality parameter meets the first preset condition based on the start point information and the end point information, the problem that the path planning method in the related art may preferentially recommend an unreasonable route is solved, the rationality of the recommended target route is improved, and the user experience is improved.
[0056] Figure 2 A flowchart of a training method of a first model in a route determination method provided by the embodiments of the present disclosure is shown. The embodiments of the present disclosure specifically limit the training method of the first model on the basis of the above-mentioned embodiments.
[0057] As shown in Figure 2 , the method comprises:
[0058] S210, obtaining the sample route.
[0059] The sample route includes a reference route sample and a candidate route sample.
[0060] Exemplarily, the preferred route provided by a surveyor or the like is obtained as the reference route sample. The position coordinate sequence of the reference route sample is matched to the road network to obtain a road network identifier sequence. The road network identifier sequence is used to associate the reference route sample with the traffic road network in the electronic map. For example, the road network identifier sequence can be the identifier information of the intersection and the road in the traffic road network.
[0061] A plurality of candidate route samples are generated based on the reference route sample by a second model in the path planning engine. The second model can be a path planning algorithm in the path planning engine.
[0062] Generally, the plurality of candidate route samples generated by the second model include unreasonable routes that have at least one of the following characteristics: local obvious detour, reverse, and low efficiency. Since the traditional first model does not have the ability to identify unreasonable routes, it may give high scores to unreasonable routes, and then recommend the unreasonable routes to the user. In order to solve this problem, it is necessary to accurately identify unreasonable routes from sample routes and mark them, so that the first model can have the ability to identify reasonable routes and unreasonable routes.
[0063] S220, determine the local detour judgment parameter, the reverse judgment parameter and the low efficiency route judgment parameter of the sample route.
[0064] Exemplarily, determining the local detour judgment parameter of the sample route comprises: determining a detour segment in the sample route, wherein the detour segment is a route segment with local detour. Based on the start point information and the end point information of the detour segment, a counter segment of the detour segment is determined. Based on the length of the detour segment and the length of the counter segment, the local detour judgment parameter of the sample route is determined.
[0065] Optionally, the counter segment can be the shortest route determined based on the start point information and the end point information of the detour segment. Wherein, the shortest route represents the route with the least time or the shortest distance corresponding to the detour segment.
[0066] In some embodiments, the determination of the detour segment in the sample route comprises: performing a thinning process on the sample route to obtain a plurality of trajectory points in the sample route. Based on the length and distance of the route segment between any two trajectory points in the sample route, a detour proportion of the route segment between the two trajectory points is determined. A plurality of target route segments whose detour proportions satisfy a third preset condition are determined, and a deduplication process is performed based on the inclusion relationship of the plurality of target route segments to obtain the detour segment of the sample route. Wherein, the third preset condition includes that the detour proportion is greater than a preset threshold.
[0067] Optionally, a thinning process is performed on each sample route to obtain a plurality of trajectory points representing the shape of the route. Figure 3 A schematic diagram of a segment of a sample route after thinning is provided by an embodiment of the present disclosure. As shown in FIG. 3, the sample route has a plurality of trajectory points 320 on the local route 310. Figure 3 As described above, the sample route has a plurality of trajectory points 320 on the local route 310. Figure 3The ellipsis in the sample route represents that the sample route includes other road segments in addition to the local route 310, and the other road segments are not drawn. For example, the track points 320 include A point, B point, C point, D point, E point and F point. Based on the route length and straight-line distance between each two track points, the detour ratio of the route segment between the two track points is calculated. For example, the route length between A and C points is determined based on the length of the route segment AB and the length of the route segment BC. The detour ratio between A and C points is obtained by dividing the route length between A and C points by the straight-line distance between A and C points. The target route segment between two points whose detour ratio meets the third preset condition is determined. The target route segments are sorted according to the detour ratio, and a deduplication process is performed between the target route segments according to the inclusion relationship to retain the included target route segment as the detour segment of the current sample route. Referring to Figure 3 , the target route segment between A and E points contains the target route segment between B and E points, and the target route segment between A and E points is deleted from the plurality of target route segments.
[0068] Based on the start point information and the end point information of each target route segment after deduplication, the shortest route corresponding to the current target route segment is generated. The difference segment of the target route segment and the shortest route is determined, and the equivalent length of the difference segment corresponding to the target route segment and the shortest route is calculated. Since the route generated by the second model in the path planning engine may have a reverse segment, in order to suppress the reverse route from being recommended, a preset penalty coefficient can be used to adjust the length of the reverse segment, so that the equivalent length of the route with the reverse is greater than the actual length of the route. For example, for the difference segment of the target route segment with the reverse, the equivalent length of the difference segment of the target route segment is determined based on the sum of the length of the difference segment, the reverse distance and the product of the preset penalty coefficient. For the difference segment of the shortest route with the reverse, the equivalent length of the difference segment of the shortest route is determined based on the sum of the length of the difference segment, the reverse distance and the product of the preset penalty coefficient. The preset penalty coefficient is a natural number greater than 1, which can be set according to actual needs. For the difference segment without the reverse, the equivalent length of the difference segment is determined based on the length of the difference segment. The equivalent length of the difference segment of the target route segment and the equivalent length of the difference segment of the shortest route corresponding to the target route segment are used as the local detour judgment parameter of the sample route. Alternatively, the proportional relationship of the equivalent lengths of the difference segments corresponding to the target route segment and the shortest route corresponding to the target route segment is used as the local detour judgment parameter of the sample route.
[0069] If the deviation amount between the equivalent lengths of the difference segments corresponding to the target route segment and the shortest route meets a first preset condition, it is determined that the local detour judgment parameter of the sample route meets the first preset condition. The first preset condition can include that the length deviation amount is less than a preset deviation threshold. If the deviation amount between the equivalent lengths of the difference segments corresponding to the target route segment and the shortest route is equal to or greater than the preset deviation threshold, it is determined that the local detour judgment parameter of the sample route does not meet the first preset condition.
[0070] Optionally, if the proportional relationship of the equivalent lengths of the difference segments corresponding to the target route segment and the shortest route meets a first preset condition, it is determined that the local detour judgment parameter of the sample route meets the first preset condition. The first preset condition can include that the proportional relationship is less than a preset proportion threshold. If the ratio of the equivalent lengths of the difference segments corresponding to the target route segment and the shortest route is equal to or greater than the preset proportion threshold, it is determined that the local detour judgment parameter of the sample route does not meet the first preset condition.
[0071] The embodiments of the present disclosure can quickly filter out sample routes with detour road segments by calculating the detour proportion of the sample route, and then quickly determine whether the sample route has local detours based on the equivalent lengths of the difference segments corresponding to the route segment between the two trajectory points in the detour road segment of the sample route and the shortest route between the two points, thereby avoiding traversing all sample routes and improving the efficiency of discovering local detour routes.
[0072] In some embodiments, determining the low-efficiency route judgment parameter of the sample route includes:
[0073] In the sample routes in which the local detour judgment parameter and the reverse judgment parameter meet the first preset condition, the route network identifier sequences of any two sample routes are compared to determine the difference road segments corresponding to the two sample routes. The low-efficiency route judgment parameter of the two sample routes is determined based on at least one of the length information of the difference road segments, the number of turns of the difference road segments, and the route heat information of the shorter difference road segment.
[0074] The difference road segment is a route segment in which the route network identifier sequences corresponding to any two sample routes in the sample routes in which the local detour judgment parameter and the reverse judgment parameter meet the first preset condition do not coincide. According to the length of the non-coinciding route segment, the difference road segment can be determined as a longer difference road segment and a shorter difference road segment. It should be noted that the longer difference road segment and the shorter difference road segment represent the same non-coinciding route segment.
[0075] The low-efficiency route judgment parameter is determined by at least one of the following methods:
[0076] The length deviation between the long difference road segment and the short difference road segment is used to determine the low-efficiency route determination parameter. The length of the short difference road segment is used to determine the low-efficiency route determination parameter. The number of turns of the long difference road segment and the number of turns of the short difference road segment are used to determine the low-efficiency route determination parameter. The ratio of the equivalent length of the long difference road segment and the equivalent length of the short difference road segment is used to determine the low-efficiency route determination parameter. The route heat information of the short difference road segment is used to determine the low-efficiency route determination parameter.
[0077] If at least one of the following conditions is met, it is determined that the low-efficiency route determination parameter of the sample route containing the long difference road segment meets the first preset condition:
[0078] If the length deviation between the long difference road segment and the short difference road segment is less than a preset deviation threshold.
[0079] If the length of the short difference road segment is equal to or greater than a preset length threshold.
[0080] If the deviation between the number of turns of the long difference road segment and the number of turns of the short difference road segment is less than a preset number threshold.
[0081] If the ratio of the equivalent length of the long difference road segment and the equivalent length of the short difference road segment is less than a preset ratio threshold.
[0082] If the route heat of the short difference road segment is 0.
[0083] S230, based on the local detour determination parameter, the reverse determination parameter and the low-efficiency route determination parameter, determining the positive sample in the sample route, marking the sample route except the positive sample as negative sample, training the first model based on the positive sample and negative sample.
[0084] In some embodiments, the sample route whose local detour determination parameter, reverse determination parameter and low-efficiency route determination parameter meet the first preset condition can be marked as a positive sample.
[0085] Optionally, the determination manner of the positive sample comprises: determining the candidate route sample whose local detour determination parameter, reverse determination parameter and low-efficiency route determination parameter meet the first preset condition as a target route sample. The positive sample is determined based on the similarity between the target route sample and the reference route sample.
[0086] For example, for the same reference route sample corresponding to the local detour judgment parameter, the reverse judgment parameter and the low efficiency route judgment parameter, the first preset condition of the plurality of candidate route samples, the similarity of the plurality of candidate route samples and the reference route sample is calculated. For example, the similarity of each candidate route sample and the reference route sample can be calculated based on the road network sequence identifier. The candidate route sample with the highest similarity in the plurality of candidate route samples is marked as a positive sample. Alternatively, the plurality of candidate route samples are arranged in descending order according to the similarity, and the top N candidate routes are marked as positive samples, where N is a natural number. Alternatively, the candidate route sample with a similarity exceeding a preset threshold is marked as a positive sample. In the embodiment of the present disclosure, the candidate route sample with the similarity satisfying the preset condition is marked as a positive sample, and the remaining sample route is marked as a negative sample. The first model is trained based on the positive sample and the negative sample.
[0087] The technical scheme of the embodiment of the present disclosure determines the local detour judgment parameter, the reverse judgment parameter and the low efficiency route judgment parameter of the sample route, and realizes the characterization of the rationality parameter of the sample route from the feature parameters of different dimensions of the sample route. For each candidate route sample satisfying the first preset condition of the rationality parameter, the candidate route sample with the similarity of the reference route sample corresponding to the candidate route sample satisfying the preset condition is marked as a positive sample, and the remaining sample route is marked as a negative sample. The first model is trained based on the positive sample and the negative sample, so that the first model can learn the features of the reasonable candidate route sample with the similarity of the reference route sample satisfying the expectation (for example, the most similar). The first model can accurately determine the target route that is reasonable and meets the route preference.
[0088] Figure 4 The flowchart of another training method of the first model in the route determination method provided by the embodiment of the present disclosure is shown in FIG. 10. Figure 4 As shown in FIG. 10, the method comprises:
[0089] S410, obtaining a reference route sample and determining a road network identifier sequence corresponding to the reference route sample.
[0090] For example, the trajectory walked by a surveyor is obtained as a reference route sample. The position coordinate sequence of the reference route sample is matched to the road network by the path planning engine to obtain the road network identifier sequence corresponding to the reference route sample.
[0091] S420, generating a plurality of candidate route samples corresponding to the reference route sample based on the start point information and the end point information of the reference route sample.
[0092] For example, the start point information and the end point information of the reference route sample are input into the second model, and the second model generates a plurality of candidate route samples based on the start point information and the end point information. The plurality of candidate route samples output by the second model are obtained.
[0093] S430, for each reference route sample, determine a local detour judgment parameter of the reference route sample and a plurality of candidate route samples corresponding to the reference route sample, and determine a local detour route whose local detour judgment parameter does not satisfy a first preset condition.
[0094] Exemplarily, for any reference route sample and a plurality of candidate route samples corresponding to the reference route sample, the following steps are used to identify a local detour: Step 1, thinning the reference route sample and the candidate route sample to obtain a trajectory point representing the shape of the route. Step 2, calculating the detour ratio between each two trajectory points. Step 3, screening out the route segment between the two trajectory points whose detour ratio is greater than a preset threshold. Step 4, arranging all the screened route segments in descending order of detour ratio, and performing deduplication processing on the route segments in the arrangement result according to the contained relationship, so as to retain the route segment contained by other route segments among at least two route segments having a containing relationship. Step 5, generating the shortest route between the start point and the end point based on the start point information and the end point information of the deduplicated route segment by using a second model. Step 6, determining the difference segment of the route segment in step 5 and the shortest route corresponding to the route segment. Step 7, calculating the equivalent length of the difference segment corresponding to the route segment, and calculating the equivalent length of the difference segment corresponding to the shortest route. It should be noted that if there is a reverse movement in the route segment, a penalty processing is needed, and the equivalent length of the route segment is increased by the product of the reverse distance and a preset penalty coefficient. If there is a reverse movement in the shortest route, a penalty processing is needed, and the equivalent length of the shortest route is increased by the product of the reverse distance and a preset penalty coefficient. Step 8, if the equivalent length of the route segment is greater than m times the equivalent length of the shortest route, it is determined that there is a local detour in the reference route sample or the candidate route sample containing the route segment. Wherein, m is a natural number greater than 1.
[0095] S440, for each reference route sample, determine a local detour judgment parameter of the reference route sample and a plurality of candidate route samples corresponding to the reference route sample, and determine a local detour route whose local detour judgment parameter does not satisfy a first preset condition.
[0096] S450, for each reference route sample, comparing different candidate route samples after excluding the local detour route and the reverse route, determining an inefficient route judgment parameter based on the comparison result, and determining a target route sample whose inefficient route judgment parameter satisfies a first preset condition.
[0097] Exemplarily, for candidate route samples without local detour and reverse problems, pairwise comparison can be performed, and the comparison steps are as follows: step 1, comparing the road network identifier sequences of the two candidate route samples to obtain the difference road sections between the two candidate routes. Step 2, determining the condition for the candidate route sample containing the longer difference road section to be an inefficient route includes at least one of the following: if the length deviation of the longer difference road section from the length of the shorter difference road section is less than a preset deviation threshold. If the length of the shorter difference road section is equal to or greater than a preset length threshold. If the deviation of the number of turns of the longer difference road section from the number of turns of the shorter difference road section is less than a preset number threshold. If the ratio of the equivalent length of the longer difference road section to the equivalent length of the shorter difference road section is less than a preset proportion threshold. If the route heat of the shorter difference road section is 0.
[0098] S460, for any one reference route sample corresponding to multiple candidate route samples, the similarity between the target route sample and the current reference route sample is calculated, and the target route sample whose similarity meets the preset condition is taken as a positive sample, and the remaining routes are all negative samples.
[0099] Since the same reference route sample corresponds to multiple candidate route samples, the similarity between the target route sample and the reference route sample after excluding the local detour route, the reverse route and the inefficient route is calculated, and the target route sample whose similarity meets the preset condition (for example, the highest similarity, the top N, or reaches a preset threshold) is taken as a positive sample, and the rest can all be negative samples.
[0100] It should be noted that by determining and excluding the local detour route, the reverse route and the inefficient route in the candidate route sample, the probability of local unreasonable remaining routes can be reduced. Then, the similarity between the remaining route and the reference route sample is calculated to determine the positive sample whose similarity meets the preset condition, which can reduce the probability of local unreasonable positive samples while ensuring that the similarity between the positive sample and the reference route sample meets the preset condition.
[0101] S470, based on the positive samples and negative samples corresponding to each reference route sample, a training sample set is formed.
[0102] S480, training the first model based on the training sample set.
[0103] In some embodiments, for a plurality of candidate route samples under a reference route sample, the first model can be trained to score or rank the candidate route samples based on route rationality and similarity to the reference route sample. The route selected by the first model is determined based on the scores or ranking results, and the model loss is calculated based on the deviation of the route selected by the first model from the positive sample. The parameters of the first model are adjusted based on the model loss until the model training end condition is met.
[0104] Optionally, for a plurality of candidate route samples under a reference route sample, the first model can be trained to select a route from the plurality of candidate routes that meets the rationality requirement and has the highest similarity to the reference route sample. The selected route can be given the highest score, or the selected route can be given the highest ranking. The model loss is calculated based on the deviation of the route selected by the first model from the positive sample. The parameters of the first model are adjusted based on the model loss until the model training end condition is met.
[0105] In the embodiments of the present disclosure, when constructing the training sample set of the first model, the unreasonable routes are accurately identified and marked as negative samples, and the reasonable routes similar to the reference route sample are marked as positive samples. Therefore, the first model trained based on the training sample set can rank the reasonable routes similar to the reference route sample before the unreasonable routes, so that the first model can preferentially recommend reasonable routes that meet the route preference.
[0106] Figure 5 A structural schematic diagram of a route determination device provided by the embodiments of the present disclosure is shown in the figure. The device can be implemented in the form of software and / or hardware, and can be implemented by an electronic device, which can be a mobile terminal, a PC terminal, or a server, etc.
[0107] As shown in the figure, the device includes an information receiving module 510, a model calling module 520, and a route determination module 530. Figure 5
[0108] The information receiving module 510 is configured to receive starting point information and ending point information.
[0109] The model calling module 520 is configured to call the first model based on the starting point information and the ending point information. The training sample set of the first model is determined based on the rationality parameter of the sample route. The positive sample of the training sample set includes a sample route whose rationality parameter meets a first preset condition. The negative sample of the training sample set includes a sample route whose rationality parameter does not meet the first preset condition.
[0110] The route determination module 530 is configured to output target route information containing the start point information and the end point information according to the calling result of the first model, wherein the rationality parameter of the target route satisfies the first preset condition.
[0111] Optionally, the model calling module 520 is specifically configured to:
[0112] obtain a plurality of candidate routes including start point information and end point information;
[0113] call the first model to determine a target route from the plurality of candidate routes or determine sorting information of the plurality of candidate routes, wherein the calling result of the first model includes the target route information or the sorting information of the plurality of candidate routes.
[0114] Optionally, the rationality parameter includes at least one of a local detour judgment parameter, a reverse judgment parameter, and an inefficient route judgment parameter.
[0115] Optionally, the first model is trained in the following manner:
[0116] obtain the sample route;
[0117] determine the local detour judgment parameter, the reverse judgment parameter, and the inefficient route judgment parameter of the sample route;
[0118] determine the positive sample in the sample route based on the local detour judgment parameter, the reverse judgment parameter, and the inefficient route judgment parameter, mark the sample route except the positive sample as a negative sample, and train the first model based on the positive sample and the negative sample.
[0119] Optionally, the rationality parameter includes a local detour judgment parameter, and determining the rationality parameter of the sample route includes:
[0120] determining a detour segment in the sample route, wherein the detour segment is a route segment with local detour;
[0121] determining a pair of segments of the detour segment based on start point information and end point information of the detour segment;
[0122] determining the local detour judgment parameter of the sample route based on a length of the detour segment and a length of the pair of segments.
[0123] Optionally, the determination of the detour segment in the sample route includes:
[0124] performing sparse processing on the sample route to obtain a plurality of track points in the sample route;
[0125] determine a detour proportion of a route segment between any two trajectory points in the sample route based on a length and a distance of the route segment between the two trajectory points;
[0126] determine a plurality of target route segments in which the detour proportion meets a third preset condition, perform a deduplication processing based on a containment relationship of the plurality of target route segments, and obtain a detour segment of the sample route.
[0127] Optionally, the rationality parameter includes an inefficient route determination parameter, and determining the rationality parameter of the sample route includes:
[0128] In the sample route in which the local detour determination parameter and the reverse determination parameter meet the first preset condition, comparing a road network identifier sequence of any two sample routes to determine a difference section corresponding to the two sample routes.
[0129] determining an inefficient route determination parameter of the two sample routes based on at least one of length information of the difference section corresponding to the two sample routes, a number of turns of the difference section corresponding to the two sample routes, and route heat information of a difference section with a shorter length.
[0130] Optionally, the sample route includes a reference route sample and a candidate route sample corresponding to the reference route sample, a similarity of the candidate route sample and the reference route sample meets a second preset condition, and determining the positive sample in the sample route based on the local detour determination parameter, the reverse determination parameter, and the inefficient route determination parameter includes:
[0131] determining the candidate route sample in which the local detour determination parameter, the reverse determination parameter, and the inefficient route determination parameter meet the first preset condition as a target route sample.
[0132] determining the positive sample based on a similarity of the target route sample and the reference route sample.
[0133] The route determination apparatus provided in the embodiments of the present disclosure can perform the route determination method provided in any of the embodiments of the present disclosure, and has the corresponding function modules and beneficial effects of performing the method.
[0134] It should be noted that each unit and module included in the above apparatus is only divided according to function logic, but is not limited to the above division, as long as the corresponding function can be implemented; in addition, the specific names of each functional unit are only for convenient mutual distinction, and do not serve to limit the protection scope of the embodiments of the present disclosure.
[0135] Figure 6 A structural schematic diagram of an electronic device provided in the embodiments of the present disclosure. The following refers to the accompanying drawings to further describe the embodiments of the present disclosure. Figure 6which shows a structural diagram of an electronic device (e.g., a terminal device or a server) 600 suitable for use in implementing embodiments of the present disclosure. The terminal device in embodiments of the present disclosure can include, but is not limited to, a mobile terminal such as a mobile phone, a notebook computer, a digital broadcast receiver, a PDA (Personal Digital Assistant), a PAD (Tablet Personal Computer), a PMP (Portable Multimedia Player), a car terminal (e.g., a car navigation terminal), and the like, as well as a stationary terminal such as a digital TV, a desktop computer, and the like. Figure 6 The electronic device shown is merely one example, and should not be taken as limiting the functionality or use of embodiments of the present disclosure. Figure 6 The electronic device shown is merely one example, and should not be taken as limiting the functionality or use of embodiments of the present disclosure.
[0136] As shown in FIG. 6, Figure 6 The electronic device 600 can include a processing device (e.g., a central processing unit, a graphics processing unit, etc.) 601 that can perform various appropriate actions and processes according to programs stored in a read-only memory (ROM) 602 or programs loaded from a storage device 608 into a random access memory (RAM) 603. Various programs and data required for the operation of the electronic device 600 are also stored in the RAM 603. The processing device 601, the ROM 602, and the RAM 603 are connected to each other through a bus 604. An input / output (I / O) interface 605 is also connected to the bus 604.
[0137] In general, the following devices can be connected to the I / O interface 605: input devices 606 including, for example, a touch screen, a touch pad, a keyboard, a mouse, a camera, a microphone, an accelerometer, a gyroscope, and the like; output devices 607 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, and the like; storage devices 608 including, for example, a magnetic tape, a hard disk, and the like; and communication devices 609. The communication devices 609 can allow the electronic device 600 to communicate wirelessly or via a wire with other devices to exchange data. Although Figure 6 The electronic device 600 is shown with various devices, but it should be understood that not all of the devices shown are required to be implemented or present. More or fewer devices can alternatively be implemented or present.
[0138] In particular, the processes described above with reference to the flowcharts can be implemented as a computer software program according to embodiments of the present disclosure. For example, embodiments of the present disclosure include a computer program product comprising a computer program carried on a non-transitory computer-readable medium, the computer program containing program code for performing the methods illustrated by the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via the communication devices 609, or installed from the storage devices 608, or installed from the ROM 602. When the computer program is executed by the processing device 601, the above-described functions defined in the methods of the present disclosure are performed.
[0139] The names of the messages or information exchanged between the plurality of devices in the embodiments of the present disclosure are only for illustrative purposes, and are not intended to limit the scope of the messages or information.
[0140] The electronic device provided by the embodiments of the present disclosure belongs to the same inventive concept as the route determination method provided by the above embodiments, and the technical details not described in detail in the present embodiment can be referred to the above embodiments, and the present embodiment has the same beneficial effects as the above embodiments.
[0141] The embodiments of the present disclosure provide a computer storage medium, which stores a computer program, and the program is executed by a processor to implement the route determination method provided by the above embodiments.
[0142] It should be noted that the computer readable medium of the present disclosure can be a computer readable signal medium or a computer readable storage medium or any combination of the two. The computer readable storage medium may, for example, but is not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or component, or any combination thereof. More specific examples of the computer readable storage medium can include, but are not limited to, an electrical connection having one or more wires, a portable computer diskette, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present disclosure, the computer readable storage medium can be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, device or component. In the present disclosure, the computer readable signal medium can include a data signal carried in a baseband or as a part of a carrier wave, which carries computer readable program code. Such a propagated data signal can take many forms, including but not limited to an electromagnetic signal, an optical signal or any suitable combination thereof. The computer readable signal medium can also be any computer readable medium other than the computer readable storage medium, which can send, propagate or transmit a program for use by or in conjunction with an instruction execution system, device or component. The program code contained in the computer readable medium can be transmitted by any suitable medium, including but not limited to a wire, a cable, an RF (radio frequency) or the like, or any suitable combination thereof.
[0143] In some embodiments, the client, server, or both can communicate using any known or later developed network protocols, such as the HyperText Transfer Protocol (HTTP), and can be interconnected with any form or medium of digital data communication (for example, a communication network) and any combination of one or more local area networks (LANs) and / or wide area networks (WANs). Examples of communication networks include peer-to-peer networks, client-server networks, and the Internet, among others, and any combination thereof.
[0144] The computer-readable medium described above can be included in the electronic device described above; alternatively, it can exist separately from the electronic device and be not incorporated into the electronic device.
[0145] The computer-readable medium described above carries one or more programs, which, when executed by the electronic device, cause the electronic device to:
[0146] receive origin information and destination information;
[0147] based on the origin information and the destination information, call a first model, wherein a training sample set of the first model is determined based on a rationality parameter of a sample route, positive samples of the training sample set include sample routes whose rationality parameters satisfy a first preset condition, and negative samples of the training sample set include sample routes whose rationality parameters do not satisfy the first preset condition;
[0148] based on a calling result of the first model, output target route information containing the origin information and the destination information, wherein a rationality parameter of a target route satisfies the first preset condition.
[0149] Computer program code for carrying out operations of the present disclosure can be written in any one or more of a number of programming languages or combinations of languages including an object-oriented programming language such as Java, Smalltalk, C++ or the like and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code can execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the latter scenario, the remote computer can be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or the connection can be made to an external computer (for example, through the Internet using an Internet Service Provider). In some embodiments, electronic circuitry including, for example, programmable logic circuitry, application specific circuitry, or field programmable gate array (FPGA) circuitry, includes the circuitry described above and / or can execute the computer program code described above.
[0150] The computer program product of the first aspect can include one or more non-transitory computer-readable media storing instructions that, when executed, cause one or more processors to perform the operations of the method of the first aspect. The computer program product of the first aspect can include a computer-readable medium storing instructions that, when executed, cause one or more processors to perform the operations of the method of the first aspect.
[0151] The units described in the embodiments of the present disclosure can be implemented by software, or by hardware, or by a combination of software and hardware. In some cases, the names of the units do not constitute a limitation on the units themselves.
[0152] The functions described in this document can be implemented in part or in whole using one or more hardware logic components. For example, and without limitation, illustrative types of hardware logic components that can be used include Field-programmable Gate Arrays (FPGAs), Program-specific Integrated Circuits (ASICs), Program-specific Standard Products (ASSPs), System-on-a-chip systems (SOCs), Complex Programmable Logic Devices (CPLDs), etc.
[0153] In the context of the present disclosure, a machine-readable medium can be a tangible medium that contains or stores a program for use by or in connection with an instruction execution system, apparatus, or device. The machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can include but is not limited to an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples of a machine-readable storage medium will include one or more lines of electrical connections, portable computer disks, hard disk drives, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or Flash memory), optical fiber, portable compact disc read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.
[0154] The above description merely illustrates the preferred embodiments of the disclosure and a principle for applying the technologies. It is understood by those skilled in the art that the disclosed scope of the disclosure is not limited to the technical solutions formed by the specific combinations of the technical features described above, and should also cover other technical solutions formed by the combinations of the technical features described above or their equivalent features without departing from the disclosed concept. For example, the technical solutions formed by the mutual replacement of the above-described features and the technical features with similar functions disclosed in the disclosure (but not limited to) can be formed.
[0155] Further, although operations are depicted in a particular, sequential order, this should not be understood as requiring or implying that the operations are performed in the order illustrated or sequentially. In certain circumstances, multitasking and parallel processing can be advantageous. Likewise, although specific implementation details are included for the purpose of providing a thorough disclosure, these should not be construed as limitations on the scope of the disclosure. Certain features that are described in the context of separate embodiments can also be implemented in combination in a single embodiment. Conversely, various features that are described in the context of a single embodiment can also be implemented in multiple embodiments separately or in any suitable sub-combination.
[0156] Although the subject matter has been described in language specific to structural features and / or methodological acts, it is to be understood that the subject defined in the appended claims is not necessarily limited to the specific features or acts described above. Rather, the specific features and acts described above are disclosed as example forms of implementing the claims.
Claims
1. A route determination method characterized by, Comprising: receiving start point information and end point information; based on the start point information and end point information, calling a first model, wherein the training sample set of the first model is determined based on the rationality parameter of the sample route, the positive sample of the training sample set includes the sample route whose rationality parameter meets the first preset condition, and the negative sample of the training sample set includes the sample route whose rationality parameter does not meet the first preset condition; according to the calling result of the first model, outputting target route information containing the start point information and the end point information, wherein the rationality parameter of the target route meets the first preset condition.
2. The method of claim 1, wherein, The calling of the first model based on the start point information and the end point information comprises: obtaining a plurality of candidate routes including the start point information and the end point information; calling the first model to determine a target route from the plurality of candidate routes, or to determine sorting information of the plurality of candidate routes, wherein the calling result of the first model includes the target route information or the sorting information of the plurality of candidate routes.
3. The method of claim 1, wherein, The rationality parameter includes at least one of a local detour judgment parameter, a reverse judgment parameter, and an inefficient route judgment parameter.
4. The method of claim 3, wherein, The first model is trained in the following manner: obtaining the sample route; determining the local detour judgment parameter, the reverse judgment parameter, and the inefficient route judgment parameter of the sample route; based on the local detour judgment parameter, the reverse judgment parameter, and the inefficient route judgment parameter, determining the positive sample in the sample route, marking the sample route other than the positive sample as a negative sample, and training the first model based on the positive sample and the negative sample.
5. The method of claim 1, wherein, The rationality parameter includes a local detour judgment parameter, and determining the rationality parameter of the sample route comprises: determining a detour segment in the sample route, wherein the detour segment is a route segment with local detour; based on the start point information and the end point information of the detour segment, determining a counterpart segment of the detour segment; based on the length of the detour segment and the length of the counterpart segment, determining the local detour judgment parameter of the sample route.
6. The method of claim 5, wherein, The determination of the detour segment in the sample route comprises: performing thinning processing on the sample route to obtain a plurality of track points in the sample route; based on the length and distance of the route segment between any two track points in the sample route, determining the detour proportion of the route segment between the two track points; determining a plurality of target route segments whose detour proportion meets a third preset condition, and performing deduplication processing based on the inclusion relationship of the plurality of target route segments to obtain the detour segment of the sample route.
7. The method of claim 1, wherein, The rationality parameter includes an inefficient route judgment parameter, and determining the rationality parameter of the sample route comprises: in the sample route whose local detour judgment parameter and reverse judgment parameter meet the first preset condition, comparing the road network identifier sequence of any two sample routes to determine the difference section corresponding to the two sample routes; Determine the low-efficiency route determination parameter of the two sample routes based on at least one of the length information of the difference road sections corresponding to the two sample routes, the number of turns of the difference road sections corresponding to the two sample routes, and the route heat information of the difference road section with shorter length.
8. The method of claim 4, wherein, The sample routes include a reference route sample and a candidate route sample corresponding to the reference route sample, the similarity of the candidate route sample and the reference route sample meets a second preset condition, and the determination of the positive sample in the sample routes based on the local detour determination parameter, the reverse determination parameter and the low-efficiency route determination parameter includes: The candidate route sample meeting the first preset condition of the local detour determination parameter, the reverse determination parameter and the low-efficiency route determination parameter is determined as a target route sample; Determine the positive sample based on the similarity of the target route sample and the reference route sample.
9. A route determining apparatus characterized by comprising: Comprise: An information receiving module for receiving start point information and end point information; A model calling module for calling a first model based on the start point information and end point information, wherein the training sample set of the first model is determined based on the rationality parameter of the sample route, the positive sample of the training sample set includes a sample route with a rationality parameter meeting a first preset condition, and the negative sample of the training sample set includes a sample route with a rationality parameter not meeting the first preset condition; A route determination module for outputting target route information containing the start point information and the end point information according to the calling result of the first model, wherein the rationality parameter of the target route meets the first preset condition.
10. An electronic device, comprising: The electronic device comprises: One or more processors; Storage device for storing one or more programs, When the one or more programs are executed by the one or more processors, the one or more processors implement the route determination method of any one of claims 1-8.
11. A storage medium containing computer-executable instructions, wherein: The computer executable instructions when executed by a computer processor are used to perform the route determination method of any one of claims 1-8.
12. A computer program product comprising a computer program, characterized in that, The computer program when executed by a processor implements the route determination method of any one of claims 1-8.