CN108229748B - Matching method and device for carpooling service and electronic equipment - Google Patents
Matching method and device for carpooling service and electronic equipment Download PDFInfo
- Publication number
- CN108229748B CN108229748B CN201810039558.9A CN201810039558A CN108229748B CN 108229748 B CN108229748 B CN 108229748B CN 201810039558 A CN201810039558 A CN 201810039558A CN 108229748 B CN108229748 B CN 108229748B
- Authority
- CN
- China
- Prior art keywords
- interest
- service
- target
- target group
- requesters
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 41
- 239000013598 vector Substances 0.000 claims description 35
- 230000000694 effects Effects 0.000 claims description 20
- 230000006399 behavior Effects 0.000 claims description 18
- 238000004590 computer program Methods 0.000 claims description 8
- 230000001737 promoting effect Effects 0.000 abstract 1
- 230000000875 corresponding effect Effects 0.000 description 47
- 238000010586 diagram Methods 0.000 description 8
- 230000002596 correlated effect Effects 0.000 description 3
- 235000013305 food Nutrition 0.000 description 3
- 238000004891 communication Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000004044 response Effects 0.000 description 2
- 230000006978 adaptation Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 235000021185 dessert Nutrition 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 239000000835 fiber Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 239000011435 rock Substances 0.000 description 1
- 235000011888 snacks Nutrition 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
- G06Q10/047—Optimisation of routes or paths, e.g. travelling salesman problem
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/40—Business processes related to the transportation industry
Landscapes
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Engineering & Computer Science (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- Tourism & Hospitality (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- Game Theory and Decision Science (AREA)
- Quality & Reliability (AREA)
- Operations Research (AREA)
- Entrepreneurship & Innovation (AREA)
- Development Economics (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The application provides a matching method, a matching device and electronic equipment for a ride-sharing service, wherein a specific implementation mode of the method comprises the following steps: determining a target group based on the received multiple carpooling service requests, wherein the target group comprises service requesters corresponding to part of the carpooling service requests; obtaining similar parameters of interest between every two service requesters in the target group; and determining the matched service requesters in the target group according to the similar parameters. In the process of providing the ride-sharing service, the embodiment can match the service requesters with close interests, thereby improving the matching rationality of the service requesters, promoting the improvement of the service efficiency and improving the utilization rate of service resources.
Description
Technical Field
The present disclosure relates to the field of internet application technologies, and in particular, to a matching method and device for a ride-sharing service, and an electronic device.
Background
With the continuous development of internet technology, a new O2O (Online To Offline) business model appears, making the internet a platform for Offline transactions. Currently, the O2O service for vehicles is a more successful O2O service that has been developed. Taking the car booking service as an example, currently, there are some types of car booking services that can provide a ride-sharing service. When the ride sharing service is provided, two or more passengers who ride together need to be matched, so that if the passenger matching is not reasonable, a plurality of problems can be caused, thereby not only reducing the service efficiency, but also reducing the utilization rate of service resources.
Disclosure of Invention
In order to solve one of the above technical problems, the present application provides a matching method and apparatus for a ride-sharing service, and an electronic device.
According to a first aspect of embodiments of the present application, there is provided a matching method for a ride-sharing service, including:
determining a target group based on the received multiple carpooling service requests, wherein the target group comprises service requesters corresponding to part of the carpooling service requests;
obtaining similar parameters of interest between every two service requesters in the target group;
and determining the matched service requesters in the target group according to the similar parameters.
Optionally, the obtaining of the similar parameters of the interest between each two service requesters in the target group includes:
determining one or more target interest categories;
obtaining an interest feature vector of each service requester for each target interest category;
and acquiring similar parameters of the interests of the service requesters on the basis of the interest feature vectors.
Optionally, the determining one or more target interest categories includes:
acquiring the activity of each service requester for each preset alternative interest type;
And selecting the target interest category from the candidate interest categories based on the activity.
Optionally, the activity level is obtained based on user behavior data corresponding to each service requester.
Optionally, the obtaining of the interest feature vector of each service requester for each target interest category includes:
acquiring user behavior data corresponding to each service request party;
analyzing the user behavior data by adopting a preset topic model to obtain a target result, wherein the target result comprises a plurality of interest tags of each service requester for each target interest category and the weight of each interest tag;
generating the interest feature vector based on the target result.
Optionally, the obtaining of the similar parameters of the interests between every two service requesters based on the interest feature vector includes:
calculating Euclidean distance between every two service requesters for each target interest category based on the interest feature vector;
and obtaining interest similar parameters between every two service requesters based on the Euclidean distance.
Optionally, the determining a target group based on the received multiple ride-sharing service requests includes:
Acquiring a travel starting point and a travel end point carried by each ride sharing service request;
determining the target group based on the trip start point and the trip end point.
According to a second aspect of embodiments of the present application, there is provided a matching device for a ride-sharing service, including:
the system comprises a first determination module, a second determination module and a third determination module, wherein the first determination module is used for determining a target group based on a plurality of received ride-sharing service requests, and the target group comprises service requesters corresponding to part of the ride-sharing service requests;
the acquisition module is used for acquiring similar parameters of interest between every two service requesters in the target group;
and the second determining module is used for determining the matched service requesters in the target group according to the similar parameters.
According to a third aspect of embodiments herein, there is provided a computer-readable storage medium storing a computer program which, when executed by a processor, implements the matching method for a ride-sharing service of any one of the above first aspects.
According to a fourth aspect of embodiments of the present application, there is provided an electronic device, including a memory, a processor, and a computer program stored on the memory and executable on the processor, where the processor implements the matching method for a ride-sharing service of any one of the above first aspects when executing the program.
The technical scheme provided by the embodiment of the application can have the following beneficial effects:
according to the matching method and device for the carpooling service, the target group is determined based on the received multiple carpooling service requests, the target group comprises service requesters corresponding to partial carpooling service requests, similar parameters of interest between every two service requesters in the target group are obtained, and the matched service requesters in the target group are determined according to the similar parameters. Therefore, in the process of providing the ride-sharing service, the service requesters with close interests can be matched, so that the matching rationality of the service requesters is improved, the service efficiency is improved, and the utilization rate of service resources can also be improved.
It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the application.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and together with the description, serve to explain the principles of the application.
FIG. 1 is a schematic diagram of an exemplary system architecture to which embodiments of the present application may be applied;
FIG. 2 is a flow chart illustrating a matching method for a ride-sharing service according to an exemplary embodiment of the present application;
FIG. 3 is a flow chart illustrating another matching method for a ride-sharing service according to an example embodiment;
FIG. 4 is a flow chart illustrating another matching method for a ride-sharing service according to an example embodiment;
FIG. 5 is a block diagram of a matching device for a ride-sharing service shown herein in accordance with an exemplary embodiment;
FIG. 6 is a block diagram of another matching device for a ride-sharing service shown herein in accordance with an exemplary embodiment;
fig. 7 is a schematic structural diagram of an electronic device shown in the present application according to an exemplary embodiment.
Detailed Description
Reference will now be made in detail to the exemplary embodiments, examples of which are illustrated in the accompanying drawings. When the following description refers to the accompanying drawings, like numbers in different drawings represent the same or similar elements unless otherwise indicated. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present application. Rather, they are merely examples of apparatus and methods consistent with certain aspects of the present application, as detailed in the appended claims.
The terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the application. As used in this application and the appended claims, the singular forms "a", "an", and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. It should also be understood that the term "and/or" as used herein refers to and encompasses any and all possible combinations of one or more of the associated listed items.
It is to be understood that although the terms first, second, third, etc. may be used herein to describe various information, such information should not be limited to these terms. These terms are only used to distinguish one type of information from another. For example, first information may also be referred to as second information, and similarly, second information may also be referred to as first information, without departing from the scope of the present application. The word "if" as used herein may be interpreted as "at … …" or "when … …" or "in response to a determination", depending on the context.
Referring to fig. 1, an exemplary system architecture diagram to which the embodiments of the present application are applied:
as shown in fig. 1, the system architecture 100 may include a network 105 of terminal devices 101, 102, 103, 104 and a server 106. It should be understood that the number or types of terminal devices, networks, and servers in fig. 1 are merely illustrative. There may be any number or type of terminal devices, networks, and servers, as desired for an implementation.
The network 105 is a medium used to provide communication links between terminal devices and servers. Network 105 may include various connection types, such as wired, wireless communication links, or fiber optic cables, to name a few.
The terminal devices 101, 102, 103, 104 may interact with a server via the network 105 to receive or transmit requests or information or the like. The terminal devices 101, 102, 103, 104 may be various electronic devices including, but not limited to, smart phones, tablet computers, smart wearable devices, and personal digital assistants, among others.
The server 106 may be a server that provides various services. The server may store, analyze, and the like the received data, or may transmit a control command or a request to the terminal device or another server. The server may provide the service in response to a service request by the user. It will be appreciated that one server may provide one or more services, and that the same service may be provided by multiple servers.
The present application will be described in detail with reference to specific examples.
As shown in fig. 2, fig. 2 is a flowchart illustrating a matching method for a ride-sharing service according to an exemplary embodiment, which may be applied in a server. The method comprises the following steps:
In step 201, a target group is determined based on the received multiple ride-sharing service requests, and the target group comprises service requesters corresponding to part of the ride-sharing service requests.
In the embodiment, the service involved may be a car pool service of a vehicle, for example, a car pool service of a net appointment, and the like. The service requester corresponding to the ride-sharing service request may be a passenger requesting the ride-sharing service, and the ride-sharing service request may carry information such as a starting point of a trip, an ending point of a trip, and a passenger ID. When the server receives multiple ride-sharing service requests, the target group may be determined first. Wherein, the target group can comprise service requesters corresponding to the partial ride-sharing service request.
Specifically, in one implementation, the trip start point carried by each ride-sharing service request may be obtained first. And then, grouping the service requesters corresponding to the ride-sharing service request according to the position of the travel starting point to obtain a target group, so that the position relation between the travel starting points corresponding to the service requesters in the same target group meets a preset rule.
In another implementation, the travel starting point and the travel ending point carried by each ride-sharing service request can also be obtained. Then, a target group is determined based on the trip start point and the trip end point, so that the position relationship between the trip start points corresponding to the service requesters in the same target group meets a preset start point position rule, and the position relationship between the trip end points corresponding to the service requesters in the same target group meets a preset end point position rule.
It will be appreciated that the target group may be determined in any other reasonable manner, and the specific manner of determining the target group is not limited in this application.
In step 202, similar parameters of interest between each two service requesters in the target group are obtained.
In this embodiment, similar parameters of interest between two service requesters in the target group may be obtained. The similar parameter of the interest between the two service requesters may be any parameter capable of measuring the similarity degree of the interest between the two service requesters, and the similar parameter may be positively correlated with the similarity degree of the interest, that is, the greater the similar parameter is, the greater the similarity degree of the interest is (for example, the similar parameter may be similarity degree, etc.). The similarity parameter may also be inversely related to the degree of interest approximation, i.e. the greater the similarity parameter, the lesser the degree of interest approximation (e.g. the similarity parameter may be an euclidean distance, a mahkowski distance, or a minkowski distance, etc.).
Specifically, in one implementation, first, one or more target interest categories may be determined. Then, an interest feature vector of each service requester in the target group for each target interest category is obtained, and based on the interest feature vector of each service requester for each target interest category, a similarity parameter of interest between every two service requesters in the target group is obtained.
In another implementation, a user profile corresponding to each service requester in the target group may also be obtained, since the user profile may reflect the interest of the service requester to some extent. Therefore, the similarity of the user portrait between two service requesters can be calculated as a similarity parameter of interest.
It is to be understood that similar parameters of interest between two service requesters in the target group may also be obtained in any other reasonable manner, which is not limited in this respect.
In step 203, the matching service requestors in the target group are determined according to the similarity parameter.
In this embodiment, the matching service requesters in the target group may be determined according to similar parameters of interest between two service requesters in the target group. Specifically, for any pair of service requesters in the target group, if it is determined that the similarity degree of the interests of the pair of service requesters is greater than the preset similarity degree according to the similarity parameter of the interests, it may be determined that the pair of service requesters match.
In one implementation, if the similar parameter of the interest is positively correlated with the approximation degree of the interest, for any pair of service requesters in the target group, if the similar parameter of the interest of the pair of service requesters is greater than or equal to a preset threshold, it may be determined that the pair of service requesters is a matching service requester.
In another implementation, if the similar parameter of the interest is negatively correlated with the approximation degree of the interest, for any pair of service requesters in the target group, if the similar parameter of the interest of the pair of service requesters is less than or equal to a preset threshold, the pair of service requesters may be determined to be matched service requesters.
In the matching method for the ride-sharing service provided by the above embodiment of the application, a target group is determined based on a plurality of received ride-sharing service requests, the target group includes service requesters corresponding to part of the ride-sharing service requests, similar parameters of interest between every two service requesters in the target group are obtained, and the matched service requesters in the target group are determined according to the similar parameters. Therefore, in the process of providing the ride-sharing service, the service requesters with close interests can be matched, so that the matching rationality of the service requesters is improved, the service efficiency is improved, and the utilization rate of service resources can also be improved.
As shown in fig. 3, fig. 3 is a flowchart illustrating another matching method for a ride-sharing service according to an exemplary embodiment, which describes a process of obtaining similar parameters of interest between two service requesters in a target group, and the method can be applied to a server, and includes the following steps:
In step 301, a target group is determined based on the received multiple ride-sharing service requests, the target group including service requesters corresponding to the partial ride-sharing service requests.
In step 302, one or more target interest categories are determined.
In this embodiment, one or more interest categories may be preset, for example, the interest categories may include, but are not limited to, food, movie, show, travel, music, sports, entertainment, and the like. Then, in one implementation, all the preset interest categories may be determined as the target interest categories. In another implementation, a preset interest category may be used as an alternative interest category, and the target interest category may be selected from the alternative interest categories.
Specifically, the target interest category may be selected from the alternative interest categories by: first, user behavior data corresponding to each service requester in the target group may be obtained. User behavior data may include, but is not limited to, a user's search behavior data, browsing behavior data, transaction behavior data, collection data behavior data, and the like.
Then, the activity of each service requester for each preset alternative interest category may be obtained based on the user behavior data corresponding to each service requester. For any service requestor, the richer the data is in a certain target interest category, the higher the liveness for that target interest category.
Finally, one or more target interest categories may be selected from the candidate interest categories based on the liveness of each service requester for each preset candidate interest category. For example, the sum of the activity degrees of all the service requesters in the target group for each preset candidate interest category may be calculated, and the candidate interest category with the sum of the activity degrees greater than a preset threshold may be determined as the target interest category. Or, according to the sequence from the large sum of the liveness to the small sum of the liveness, a preset number of candidate interest types are taken as the target interest types.
In step 303, an interest feature vector for each target interest category of each service requester in the target group is obtained.
In this embodiment, first, user behavior data corresponding to each service requester in the target group may be acquired. Then, the user behavior data can be analyzed by adopting a preset theme model to obtain a target result. Alternatively, the preset topic model may adopt an LDA (Latent Dirichlet Allocation) topic model. The obtained target result may include a plurality of interest tags for each target interest category and a weight for each interest tag for each service requester in the target group. Wherein the interest tag for the target interest category may be an interest branch under the target interest category. For example, if the target interest category is food, interest tags for food can include, but are not limited to, hotpot, barbeque, Chuan Xiang dish, steak, snack, dessert, and the like. For another example, if the target interest category is music, interest tags for music may include, but are not limited to classical, rock, ballad, light music, jazz, campus, and the like. The interest tag weight may represent a preference degree of the service requester for the corresponding interest tag, and a greater weight indicates a greater preference degree of the service requester for the corresponding interest tag.
An interest feature vector may then be generated based on the target results, and for each service requestor, a corresponding interest feature vector may be generated for each target interest category. If there are N target interest categories, then N corresponding interest feature vectors may be generated. Specifically, for any target interest category, the interest tag under the target interest category may be used as a base of the interest feature vector, and the weight of the interest tag may be used as a coordinate of the interest feature vector, so as to generate the interest feature vector.
In step 304, similar parameters of interest between each two service requesters are obtained based on the interest feature vector.
In this embodiment, similar parameters of interest between every two service requesters may be obtained based on the interest feature vector. In an implementation manner, the euclidean distance between each two service requesters for each target interest category may be calculated based on the interest feature vector corresponding to each target interest category. Then, for any pair of service requesters, an average value or a weighted average value of euclidean distances corresponding to all target interest categories is obtained as a similar parameter of the interest corresponding to the pair of service requesters.
In another implementation manner, the similarity between each two service requesters for each target interest category may also be calculated based on the interest feature vector corresponding to each target interest category. Then, for any pair of service requesters, an average or weighted average of the similarity corresponding to all the target interest categories is obtained as a similarity parameter of the interest corresponding to the pair of service requesters.
It is to be understood that similar parameters of interest between two service requesters may also be obtained in any other reasonable manner, which is not limited in this respect.
In step 305, the matching service requestors in the target group are determined based on the similarity parameter.
It should be noted that, for the same steps as in the embodiment of fig. 2, details are not repeated in the embodiment of fig. 3, and related contents may refer to the embodiment of fig. 2.
It should be noted that while in the above-described embodiment of fig. 3, the operations of the methods of the present application were described in a particular order, this does not require or imply that these operations must be performed in this particular order, or that all of the illustrated operations must be performed, to achieve desirable results. Rather, the steps depicted in the flowcharts may change the order of execution. For example, step 301 may be performed to determine a target group based on the received plurality of ride-sharing service requests, and then step 302 may be performed to determine one or more target interest categories. Step 302 may be performed first, then step 301 may be performed, or step 301 and step 302 may be performed simultaneously. Additionally or alternatively, certain steps may be omitted, multiple steps combined into one step execution, and/or one step broken down into multiple step executions.
The matching method for the co-product service provided by the above embodiment of the application determines a target group based on a plurality of received co-product service requests, where the target group includes service requesters corresponding to part of the co-product service requests, determines one or more target interest categories, obtains an interest feature vector of each service requester in the target group for each target interest category, obtains similar parameters of interests between every two service requesters based on the interest feature vectors, and determines a matched service requester in the target group according to the similar parameters. Therefore, the matching rationality of the service requesters is further improved, and the service efficiency and the utilization rate of service resources are improved.
Fig. 4 is a flow chart illustrating another method for matching of a ride-sharing service according to an exemplary embodiment detailing the process of determining a target group, which may be applied in a server, as shown in fig. 4, and includes the steps of:
in step 401, a trip start point and a trip end point carried by each received ride-sharing service request are obtained.
In step 402, a target group is determined based on the trip start point and the trip end point, wherein the target group comprises service requesters corresponding to the partial ride-sharing service request.
In an implementation manner, a preset clustering algorithm may be adopted to cluster the travel starting point and the travel end point respectively to obtain a starting point cluster set and an end point cluster set. So that the distances between the travel starts in the start cluster set are sufficiently small. The travel ends in the end point cluster set are sufficiently small in distance from each other. And then, determining a target group according to the starting point cluster set and the end point cluster set, so that the travel starting points corresponding to all service requesters in the target group correspond to the same starting point cluster set, and the travel end points corresponding to all service requesters in the target group correspond to the same end point cluster set. By determining the target group in the manner, the starting points and the end points corresponding to all the service requesters in the target group can be as close as possible, so that the probability of unreasonable matching of the service requesters is reduced.
In another implementation, a plurality of sub-areas may be divided from an area providing a ride-sharing service in advance based on a road network, and then a target group is determined according to the sub-areas, the trip start point and the trip end point, so that the trip start points corresponding to all service requesters in the target group correspond to the same sub-area, and the trip end points corresponding to all service requesters in the target group also correspond to the same sub-area. By determining the target group in the manner described above, the starting points corresponding to all the service requesters in the target group can be located in the same sub-area as close as possible, and the end points can also be located in the same sub-area as close as possible. Therefore, the bypassing caused by the fact that the party service requester is located in different sub-areas in the process of receiving, driving and delivering in the process of the party service is avoided, and the matching rationality of the service requester is further improved.
It will be appreciated that the target group may be determined in any other reasonable manner, and the present application is not limited in this respect.
In step 403, similar parameters of interest between each two service requesters in the target group are obtained.
In step 404, the matching service requestors in the target group are determined based on the similarity parameter.
It should be noted that, for the same steps as in the embodiment of fig. 2 and fig. 3, description is not repeated in the embodiment of fig. 4, and related contents may refer to the embodiment of fig. 2 and fig. 3.
According to the matching method for the ride-sharing service provided by the embodiment of the application, the travel starting point and the travel end point corresponding to each received ride-sharing service request are obtained, the target group is determined based on the travel starting point and the travel end point, the target group comprises the service requesters corresponding to part of the ride-sharing service requests, the similar parameters of the interests of the service requesters in the target group are obtained, and the matched service requesters in the target group are determined according to the similar parameters. In the embodiment, the corresponding service requesters are preliminarily grouped based on the travel starting point and the travel ending point corresponding to each ride-sharing service request, so that the service requesters with relatively matched paths can be screened out preliminarily more accurately, and the matched service requesters in the target group are further determined based on the similar parameters of the interests of the service requesters. The matching rationality of the service requesters can be further improved, so that the service efficiency and the utilization rate of service resources are further improved.
Corresponding to the matching method embodiment for the ride-sharing service, the application also provides an embodiment of a matching device for the ride-sharing service.
As shown in fig. 5, fig. 5 is a block diagram of a matching device for a ride-sharing service according to an exemplary embodiment of the present application, where the device may include: a first determining module 501, an obtaining module 502 and a second determining module 503.
The first determining module 501 is configured to determine a target group based on the received multiple carpooling service requests, where the target group includes service requesters corresponding to the partial carpooling service requests.
An obtaining module 502, configured to obtain similar parameters of interest between every two service requesters in the target group.
A second determining module 503, configured to determine, according to the similarity parameter, a matching service requester in the target group.
As shown in fig. 6, fig. 6 is a block diagram of another matching device for a ride-sharing service according to an exemplary embodiment of the present application, where on the basis of the foregoing embodiment shown in fig. 5, the obtaining module 502 may include: a determination sub-module 601, a first acquisition sub-module 602 and a second acquisition sub-module 603.
Wherein the determining sub-module 601 is configured to determine one or more target interest categories.
The first obtaining sub-module 602 is configured to obtain an interest feature vector of each service requester for each target interest category.
The second obtaining sub-module 603 is configured to obtain similar parameters of interests between every two service requesters based on the interest feature vector.
In some optional embodiments, the determination submodule 601 is configured to: and acquiring the activity of each service request party aiming at each preset alternative interest type, and selecting a target interest type from the alternative interest types based on the activity.
In other alternative embodiments, the activity level is obtained based on user behavior data corresponding to each service requester.
In further alternative embodiments, the first obtaining sub-module 602 is configured to: and acquiring user behavior data corresponding to each service requester, and analyzing the user behavior data by adopting a preset theme model to obtain a target result. The target result comprises a plurality of interest labels of each service requester for each target interest category and the weight of each interest label, and the interest feature vector is generated based on the target result.
In further alternative embodiments, the second obtaining submodule 603 is configured to: and calculating Euclidean distance between every two service requesters aiming at each target interest type based on the interest feature vector, and acquiring interest similarity parameters between every two service requesters based on the Euclidean distance.
In further alternative embodiments, the first determining module 501 is configured to: and acquiring a travel starting point and a travel end point carried by each ride-sharing service request, and determining a target group based on the travel starting point and the travel end point.
It should be understood that the above-mentioned device may be preset in the server, and may also be loaded into the server by downloading or the like. The corresponding modules in the above-described apparatus may cooperate with modules in the server to implement a matching scheme for the ride-sharing service.
For the device embodiments, since they substantially correspond to the method embodiments, reference may be made to the partial description of the method embodiments for relevant points. The above-described embodiments of the apparatus are merely illustrative, and the units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the modules can be selected according to actual needs to achieve the purpose of the scheme of the application. One of ordinary skill in the art can understand and implement it without inventive effort.
An embodiment of the present application further provides a computer-readable storage medium, where the storage medium stores a computer program, and the computer program may be used to execute the matching method for the ride-sharing service provided in any one of the embodiments of fig. 2 to fig. 4.
Corresponding to the matching method for the ride-sharing service, the embodiment of the present application also proposes a schematic structural diagram of an electronic device according to an exemplary embodiment of the present application, shown in fig. 7. Referring to fig. 7, at the hardware level, the electronic device includes a processor, an internal bus, a network interface, a memory, and a non-volatile memory, but may also include hardware required for other services. The processor reads the corresponding computer program from the nonvolatile memory into the memory and runs the computer program to form the matching device for the ride-sharing service on the logic level. Of course, besides the software implementation, the present application does not exclude other implementations, such as logic devices or a combination of software and hardware, and the like, that is, the execution subject of the following processing flow is not limited to each logic unit, and may also be hardware or logic devices.
Other embodiments of the present application will be apparent to those skilled in the art from consideration of the specification and practice of the invention disclosed herein. This application is intended to cover any variations, uses, or adaptations of the invention following, in general, the principles of the application and including such departures from the present disclosure as come within known or customary practice within the art to which the invention pertains. It is intended that the specification and examples be considered as exemplary only, with a true scope and spirit of the application being indicated by the following claims.
It will be understood that the present application is not limited to the precise arrangements described above and shown in the drawings and that various modifications and changes may be made without departing from the scope thereof. The scope of the application is limited only by the appended claims.
Claims (6)
1. A matching method for a ride-sharing service, the method comprising:
acquiring a travel starting point and a travel end point carried by each ride sharing service request;
determining a target group according to a travel starting point and a travel end point carried by a carpool service request, wherein the determined position relationship between the travel starting points corresponding to the service requesters in the same target group meets a preset starting point position rule, and the position relationship between the travel end points corresponding to the service requesters in the same target group meets a preset end point position rule;
acquiring the activity of a service requester in the target group in a preset alternative interest category;
calculating the sum of the activity degrees of all the service requesters in the target group aiming at each preset alternative interest type, and determining the alternative interest type with the activity degree sum larger than a preset threshold value as a target interest type, or taking a preset number of alternative interest types as the target interest type according to the sequence from the large sum of the activity degrees to the small sum of the activity degrees;
Analyzing user behavior data by adopting a preset topic model to obtain a plurality of interest tags of each service requester for each target interest category and the weight of each interest tag, wherein the interest tag of the target interest category is an interest branch under the target interest category, and the weight of the interest tag represents the preference degree of the service requester for the corresponding interest tag; the preset topic model comprises a latent Dirichlet distribution (LDA) topic model;
for each service request party, regarding each target interest category, taking an interest tag under the target interest category as a base of an interest feature vector, taking the weight of the interest tag as a coordinate of the interest feature vector, and generating an interest feature vector corresponding to the target interest category;
obtaining similar parameters of interest between every two service requesters in the target group based on the interest feature vector;
and determining the matched service requesters in the target group according to the similar parameters.
2. The method of claim 1, wherein the activity level is obtained based on user behavior data corresponding to each of the service requesters.
3. The method of claim 1, wherein the obtaining similar parameters of interest between the service requesters based on the interest feature vector comprises:
Calculating Euclidean distance between every two service requesters for each target interest category based on the interest feature vector;
and obtaining interest similar parameters between every two service requesters based on the Euclidean distance.
4. A matching apparatus for a ride-sharing service, the apparatus comprising:
the first determining module is used for acquiring a travel starting point and a travel end point carried by each ride sharing service request;
determining a target group according to a travel starting point and a travel end point carried by the ride-sharing service request, wherein the determined position relationship between the travel starting points corresponding to the service requesters in the same target group meets a preset starting point position rule, and the position relationship between the travel end points corresponding to the service requesters in the same target group meets a preset end point position rule;
the acquisition module is used for acquiring the activity of the service requesters in the target group in a preset alternative interest type; calculating the sum of the activity degrees of all the service requesters in the target group aiming at each preset alternative interest type, and determining the alternative interest type with the activity degree sum larger than a preset threshold value as a target interest type, or taking a preset number of alternative interest types as the target interest type according to the sequence from the large sum of the activity degrees to the small sum of the activity degrees; analyzing user behavior data by adopting a preset topic model to obtain a plurality of interest tags of each service requester for each target interest category and the weight of each interest tag, wherein the interest tag of the target interest category is an interest branch under the target interest category, and the weight of the interest tag represents the preference degree of the service requester for the corresponding interest tag; the preset topic model comprises a latent Dirichlet distribution (LDA) topic model; for each service request party, regarding each target interest category, taking an interest tag under the target interest category as a base of an interest feature vector, taking the weight of the interest tag as a coordinate of the interest feature vector, and generating an interest feature vector corresponding to the target interest category; obtaining similar parameters of interest between every two service requesters in the target group based on the interest feature vector;
And the second determining module is used for determining the matched service requesters in the target group according to the similar parameters.
5. A computer-readable storage medium, characterized in that the storage medium stores a computer program which, when executed by a processor, implements the matching method for a ride-sharing service of any of the preceding claims 1-3.
6. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor implements the method of any of claims 1-3 when executing the program.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810039558.9A CN108229748B (en) | 2018-01-16 | 2018-01-16 | Matching method and device for carpooling service and electronic equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810039558.9A CN108229748B (en) | 2018-01-16 | 2018-01-16 | Matching method and device for carpooling service and electronic equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108229748A CN108229748A (en) | 2018-06-29 |
| CN108229748B true CN108229748B (en) | 2022-06-10 |
Family
ID=62640470
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810039558.9A Active CN108229748B (en) | 2018-01-16 | 2018-01-16 | Matching method and device for carpooling service and electronic equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108229748B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110581802A (en) * | 2019-08-27 | 2019-12-17 | 北京邮电大学 | fully-autonomous intelligent routing method and device based on deep belief network |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105468631A (en) * | 2014-09-04 | 2016-04-06 | 阿里巴巴集团控股有限公司 | Point-of-interest query method and apparatus |
| WO2017075330A1 (en) * | 2015-10-30 | 2017-05-04 | Faraday&Future Inc. | System for determining common interests of vehicle occupants |
| CN107577682A (en) * | 2016-07-05 | 2018-01-12 | 上海交通大学 | Users' Interests Mining and user based on social picture recommend method and system |
Family Cites Families (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2005250562A (en) * | 2004-03-01 | 2005-09-15 | Tama Tlo Kk | Discrimination analysis method, similar image search method, program for it, and device |
| CN102411596A (en) * | 2010-09-21 | 2012-04-11 | 阿里巴巴集团控股有限公司 | Information recommendation method and system |
| CN103325046A (en) * | 2012-03-19 | 2013-09-25 | 上海博路信息技术有限公司 | Real-time car-sharing system based on HTML5 |
| US20140129578A1 (en) * | 2012-11-08 | 2014-05-08 | Sap Ag | System and method for carpool matching |
| US9554244B2 (en) * | 2013-01-24 | 2017-01-24 | Sap Se | Distribution of location and movement information of meeting participants |
| CN103778206A (en) * | 2014-01-14 | 2014-05-07 | 河南科技大学 | Method for providing network service resources |
| CN103886072B (en) * | 2014-03-24 | 2016-08-24 | 河南理工大学 | Search result clustering system in the search engine of colliery |
| US10197410B2 (en) * | 2014-11-18 | 2019-02-05 | International Business Machines Corporation | Dynamic real-time carpool matching |
| CN104881459A (en) * | 2015-05-22 | 2015-09-02 | 电子科技大学 | Friend recommendation method of mobile social network |
| US20160364823A1 (en) * | 2015-06-11 | 2016-12-15 | Raymond Cao | Systems and methods for on-demand transportation |
| US10291574B2 (en) * | 2015-07-30 | 2019-05-14 | Uber Technologies, Inc. | Social media integration for transport arrangement service |
| CN105243562A (en) * | 2015-10-21 | 2016-01-13 | 北京小飞快充网络科技有限公司 | Method and system for enhancing content distribution effects of chauffeured cars |
| CN106447387A (en) * | 2016-08-31 | 2017-02-22 | 上海交通大学 | Air ticket personalized recommendation method based on shared account passenger prediction |
| CN107317688A (en) * | 2017-07-25 | 2017-11-03 | 薛江炜 | The device and method of communication group is created based on tag along sort |
| CN107527105B (en) * | 2017-08-11 | 2021-03-12 | 杨志伟 | Carpooling order combining method |
-
2018
- 2018-01-16 CN CN201810039558.9A patent/CN108229748B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105468631A (en) * | 2014-09-04 | 2016-04-06 | 阿里巴巴集团控股有限公司 | Point-of-interest query method and apparatus |
| WO2017075330A1 (en) * | 2015-10-30 | 2017-05-04 | Faraday&Future Inc. | System for determining common interests of vehicle occupants |
| CN107577682A (en) * | 2016-07-05 | 2018-01-12 | 上海交通大学 | Users' Interests Mining and user based on social picture recommend method and system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108229748A (en) | 2018-06-29 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| JP7052037B2 (en) | Fusion data processing method and information recommendation system | |
| CN110458663B (en) | Vehicle recommendation method, device, equipment and storage medium | |
| CN112000819B (en) | Multimedia resource recommendation method and device, electronic equipment and storage medium | |
| CN108875955B (en) | Gradient lifting decision tree implementation method based on parameter server and related equipment | |
| CN108228887B (en) | Method and apparatus for generating information | |
| CN108229864A (en) | Distribution method, device and the electronic equipment of order | |
| CN110083334A (en) | The online method and device of model | |
| US20140006166A1 (en) | System and method for determining offers based on predictions of user interest | |
| CN111461812A (en) | Object recommendation method and device, electronic equipment and readable storage medium | |
| US11379539B2 (en) | Efficient freshness crawl scheduling | |
| CN111899061B (en) | Order recommendation method, device, equipment and storage medium | |
| CN112182360A (en) | Personalized recommender with limited data availability | |
| CN111241388A (en) | Multi-policy recall method and device, electronic equipment and readable storage medium | |
| JP2024500464A (en) | Dynamic facet ranking | |
| CN110766513A (en) | Information sorting method and device, electronic equipment and readable storage medium | |
| WO2022127517A1 (en) | Hierarchical adaptive contextual bandits for resource-constrained recommendation | |
| CN108229748B (en) | Matching method and device for carpooling service and electronic equipment | |
| CN110515929B (en) | Book display method, computing device and storage medium | |
| CN109146109B (en) | Order distribution and model training method and device | |
| CN112163726A (en) | Service resource allocation method and device, electronic equipment and readable storage medium | |
| CN106716969A (en) | Technologies for pre-action execution | |
| US20220374683A1 (en) | Selecting points in continuous spaces using neural networks | |
| CN112200234B (en) | Method and device for preventing model stealing in model classification process | |
| CN113609378B (en) | Information recommendation method and device, electronic equipment and storage medium | |
| CN110059248B (en) | Recommendation method and device and server |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |