CN110427574B - Route similarity determination method, device, equipment and medium - Google Patents
Route similarity determination method, device, equipment and medium Download PDFInfo
- Publication number
- CN110427574B CN110427574B CN201910712478.XA CN201910712478A CN110427574B CN 110427574 B CN110427574 B CN 110427574B CN 201910712478 A CN201910712478 A CN 201910712478A CN 110427574 B CN110427574 B CN 110427574B
- Authority
- CN
- China
- Prior art keywords
- route
- target
- determining
- click
- pair
- 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
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9536—Search customisation based on social or collaborative filtering
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9537—Spatial or temporal dependent retrieval, e.g. spatiotemporal queries
-
- 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
- G06Q10/08—Logistics, e.g. warehousing, loading or distribution; Inventory or stock management
- G06Q10/083—Shipping
Abstract
The embodiment of the invention discloses a method, a device, equipment and a medium for determining route similarity, and relates to the technical field of route planning. The method comprises the following steps: determining a target route pair from historical click routes of a target time period, and determining at least one target user from click users of the historical click routes; determining a first characteristic vector of the target route to a first route and a second characteristic vector of a second route according to the route clicking number of the at least one target user; and calculating the similarity between the first feature vector and the second feature vector, and taking the similarity as the similarity between the first route and the second route. The embodiment of the invention provides a method, a device, equipment and a medium for determining route similarity, which are used for determining the similarity between a route clicked by a user and a route not clicked by the user, and further mining potential interesting routes of the user from the route not clicked based on the similarity.
Description
Technical Field
The embodiment of the invention relates to the technical field of route planning, in particular to a method, a device, equipment and a medium for determining route similarity.
Background
Freight platforms match millions of sources of goods on tens of thousands of routes for millions of drivers daily. However, because of the large differences in driver origin and destination, there are a large number of drivers with fewer sources of goods that can be matched on routes of interest, and drivers are unaware of other routes of potential interest. Therefore, it is desirable to determine such routes for drivers to help drivers find more goods that can be matched.
The existing implementation scheme is to recommend the route of the city around the starting and ending point of the route according to the geographic position.
The above scheme has the following disadvantages:
1. the number of routes of potential interest is limited, since there are a limited number of cities around a city.
2. Based on the geographical position, the supply and demand conditions of the city can not be reflected, if some urban goods are few, or drivers in the city are concerned rarely, the drivers can not be treated differently, and the goods of the drivers can not be matched according to the real supply and demand conditions.
3. The concept of a short range route, a medium range route and a long range route for similar routes is only relevant to cities around the starting and ending point and is therefore not sufficient to meet the demand of long range drivers for goods in cities that are further away.
Disclosure of Invention
The embodiment of the invention provides a route similarity determination method, a route similarity determination device, route similarity determination equipment and a route similarity determination medium, which are used for determining the similarity between a clicked route and an unchecked route of a user and further determining a potential interesting route of the user from the unchecked route based on the similarity, wherein the number of the potential interesting routes is not limited by the number of cities around a starting point and a finishing point, more goods can be matched on the potential interesting route, and the potential interesting route comprises routes of cities far away from the starting point and the finishing point.
In a first aspect, an embodiment of the present invention provides a method for determining route similarity, where the method includes:
determining a target route pair from historical click routes of a target time period, and determining at least one target user from click users of the historical click routes;
determining a first feature vector of a first route in the target route pair according to the number of clicks of the first route in the target time period by the at least one target user;
determining a second feature vector of a second route in the target route pair according to the number of clicks of the at least one target user on the second route in the target time period;
and calculating the similarity between the first feature vector and the second feature vector, and taking the similarity as the similarity between the first route and the second route.
In a second aspect, an embodiment of the present invention further provides a route similarity determining apparatus, where the apparatus includes:
the route pair determining module is used for determining a target route pair from historical click routes in a target time period and determining at least one target user from click users of the historical click routes;
the first vector determination module is used for determining a first feature vector of a first route in the target route pair according to the number of clicks of the at least one target user on the first route in the target route pair within a target time period;
a second vector determination module, configured to determine a second feature vector of a second route in the target route pair according to the number of clicks of the second route in the target time period by the at least one target user;
and the similarity calculation module is used for calculating the similarity between the first feature vector and the second feature vector and taking the similarity as the similarity between the first route and the second route.
In a third aspect, an embodiment of the present invention further provides an electronic device, where the electronic device includes:
one or more processors;
a storage device to store one or more programs,
when executed by the one or more processors, the one or more programs cause the one or more processors to implement a route similarity determination method as described in any one of the embodiments of the present invention.
In a fourth aspect, the embodiment of the present invention further provides a computer-readable storage medium, on which a computer program is stored, where the computer program, when executed by a processor, implements the route similarity determination method according to any one of the embodiments of the present invention.
The embodiment of the invention determines at least one target user from the clicking users of the historical clicking route; determining a first feature vector of a first route in the target route pair according to the number of clicks of the first route in the target time period by the at least one target user; determining a second feature vector of a second route in the target route pair according to the number of clicks of the at least one target user on the second route in the target time period; and calculating the similarity between the first feature vector and the second feature vector, and taking the similarity as the similarity between the first route and the second route, so as to realize the determination of the similarity between the routes, and further mining the potential interested routes of the user according to the determined similarity.
Because the embodiment of the invention does not depend on the peripheral cities of the starting and ending points of the route, the embodiment of the invention is not influenced by the number of the peripheral cities and can comprise the route of the city far away from the starting and ending points.
Because the number of clicks of the target user on the route reflects the supply and demand amount of the route path city, the potential interested route determined based on the similarity of the embodiment of the invention can be matched with more goods.
In addition, the characteristic vector of the route is determined according to the number of clicks of the target user on the route, and the similarity between the two routes is determined according to the similarity between the characteristic vectors of the two routes, so that the number of clicks of the route is associated with the similarity determination of the route. Since the utilization value of the click data of the user with the large number of times of clicking the route is not higher than that of the click data of the user with the small number of times of clicking the route, the influence of the click data of the user with the large number of times of clicking the route on the route similarity determination can be reduced through the correlation between the number of clicks of the route and the route similarity determination, and the similarity determination accuracy is further improved.
Drawings
Fig. 1 is a flowchart of a route similarity determining method according to an embodiment of the present invention;
fig. 2 is a flowchart of a route similarity determination method according to a second embodiment of the present invention;
fig. 3 is a flowchart of a route similarity determination method according to a third embodiment of the present invention;
fig. 4 is a schematic structural diagram of a route similarity determination apparatus according to a fourth embodiment of the present invention;
fig. 5 is a schematic structural diagram of an apparatus according to a fifth embodiment of the present invention.
Detailed Description
The present invention will be described in further detail with reference to the accompanying drawings and examples. It is to be understood that the specific embodiments described herein are merely illustrative of the invention and are not to be construed as limiting the invention. It should be further noted that, for the convenience of description, only some structures related to the present invention are shown in the drawings, not all of them.
Example one
Fig. 1 is a flowchart of a route similarity determining method according to an embodiment of the present invention. The embodiment is applicable to the case of determining the similarity of two lines. Typically, the present embodiment may be applied to the case of performing similarity determination on the route in which the target user is interested and other routes, and then mining the potential route in which the target user is interested from other routes. The method may be performed by a route similarity determination apparatus, which may be implemented in software and/or hardware. Referring to fig. 1, the method for determining route similarity according to the present embodiment includes:
s110, determining a target route pair from historical click routes in a target time period, and determining at least one target user from click users of the historical click routes.
The target time period is a time period of the historical time, and can be specifically set according to actual needs.
Alternatively, the target period may be a month in the historical time or a day in the historical time.
The historical click route refers to a route clicked by the user within a target period.
The target route pair refers to two routes to be subjected to similarity determination.
The target user is the user who provides the calculation data for the subsequent similarity calculation.
Specifically, the step of determining a target route pair from historical click routes in a target time period comprises the following steps:
and determining two different historical click routes from the different historical click routes in the target time period to serve as a target route pair.
Typically, the determining a target route pair from historical click routes of a target period includes:
acquiring a historical click route of a target time period, click time of the historical click route and a click user;
grouping the historical click routes of the same click user according to the click time of the historical click routes and a set time interval to generate at least one candidate route group, and respectively setting different candidate user identifications for the at least one candidate route group;
and determining a first route and a second route in the target route pair from historical click routes of any one of the candidate route groups.
Specifically, determining a first route and a second route in the target route pair from historical clicked routes of any one of the candidate route groups includes:
and selecting two different historical click routes from the historical click routes of any one of the candidate route groups as a first route and a second route in the target route pair.
Typically, the determining a first route and a second route in the target route pair from the historical clicked routes of any one of the candidate route groups includes:
deleting duplicate routes in each of the route groups;
combining the historical click routes in each past-weighted route group pairwise to generate a candidate route pair;
determining a first route of the target route pair;
and searching the second route which has an association relation with the first route from the candidate route pair according to the first route in the target route pair.
Optionally, determining at least one target user from the clicked users of the historical clicked route includes:
all clicking users of the historical clicking route are used as target users; alternatively, the first and second electrodes may be,
taking part of clicking users in the historical clicking route as target users; alternatively, the first and second electrodes may be,
and taking the user clicking the first route and the user clicking the second route in the historical clicking routes as target users.
S120, determining a first feature vector of a first route in the target route pair according to the number of clicks of the at least one target user on the first route in the target time period.
Wherein the first feature vector is a vector describing features of the first route.
Specifically, determining a first feature vector of a first route in the target route pair according to the number of clicks of the first route in the target route pair by the at least one target user in a target time period includes:
and taking the number of clicks of the first route in the target route pair by the at least one target user in a target period as a first feature vector of the first route.
S130, determining a second feature vector of a second route in the target route pair according to the number of clicks of the at least one target user on the second route in the target time period.
Wherein the second feature vector is a vector describing features of the second route.
Specifically, determining a second feature vector of a second route in the target route pair according to the number of clicks of the at least one target user on the second route in the target time period includes:
and taking the number of clicks of the at least one target user on a second route in the target route pair in a target period of time as a second feature vector of the second route.
S140, calculating the similarity between the first feature vector and the second feature vector, and taking the similarity as the similarity between the first route and the second route.
Specifically, the similarity between the first feature vector and the second feature vector may be calculated according to an existing calculation method for similarity between arbitrary vectors, which is not limited in this embodiment.
The execution steps of S120 and S130 are not limited in the embodiment of the present invention, and optionally, S130 may be executed before S120.
According to the technical scheme of the embodiment of the invention, at least one target user is determined from the clicking users of the historical clicking route; determining a first feature vector of a first route in the target route pair according to the number of clicks of the first route in the target time period by the at least one target user; determining a second feature vector of a second route in the target route pair according to the number of clicks of the at least one target user on the second route in the target time period; and calculating the similarity between the first feature vector and the second feature vector, and taking the similarity as the similarity between the first route and the second route, so as to determine the similarity between the routes, and further mining the potential interested routes of the user according to the determined similarity.
Because the embodiment of the invention does not depend on the surrounding cities of the starting and ending points of the route, the embodiment of the invention is not influenced by the number of the surrounding cities and can comprise the route of the city far away from the starting and ending points.
Because the number of clicks of the target user on the route reflects the supply and demand amount of the route path city, the potential interested route determined based on the similarity of the embodiment of the invention can be matched with more goods.
In addition, the feature vector of the route is determined according to the number of clicks of the route by the target user, and the similarity between the two routes is determined according to the similarity between the feature vectors of the two routes, so that the number of clicks of the route is associated with the similarity determination of the route. Since the utilization value of the click data of the user with the large number of times of clicking the route is not higher than that of the click data of the user with the small number of times of clicking the route, the influence of the click data of the user with the large number of times of clicking the route on the route similarity determination can be reduced through the correlation between the number of clicks of the route and the route similarity determination, and the similarity determination accuracy is further improved.
Example two
Fig. 2 is a flowchart of a route similarity determining method according to a second embodiment of the present invention. The present embodiment is an alternative proposed on the basis of the above-described embodiments. Referring to fig. 2, the method for determining route similarity according to the present embodiment includes:
s210, determining a target route pair from historical click routes in a target time period, and determining at least one target user from click users of the historical click routes.
S220, sequencing the at least one target user.
The arrangement sequence of the target users is not limited in this embodiment, and may be specifically determined according to actual needs.
Specifically, the at least one target user may be sorted according to a set sorting order.
S230, determining the first feature vector according to the arrangement sequence of each target user and the number of the target users clicking the first route.
Specifically, the determining the first feature vector according to the ranking order of each target user and the number of the target users clicking the first route includes:
determining the click weight of each target user on the first route according to the number of the target users clicking the first route;
according to the arrangement sequence of each target user, sorting the click weights of the target users to generate a feature matrix;
and taking the feature matrix as the first feature vector.
Optionally, determining the click weight of each target user on the first route according to the number of the target users clicking the first route includes:
taking the number of the target users clicking the first route as the clicking weight of the target users on the first route; or
Determining whether the target user is interested in the first route according to the number of the target user clicking the first route;
and determining the click weight of the target user on the first route according to the determined interest condition of the target user on the first route.
For example, if the target user is interested in the first route, the click weight of the target user on the first route is determined to be 1, otherwise, the click weight of the target user on the first route is determined to be 0.
S240, determining the second feature vector according to the arrangement sequence of each target user and the number of the target users clicking the second route.
The specific calculation process of S240 is the same as S230, and this embodiment will not be described again.
And S250, calculating the similarity between the first feature vector and the second feature vector, and taking the similarity as the similarity between the first route and the second route.
According to the technical scheme of the embodiment of the invention, the at least one target user is sequenced; and determining the characteristic vector of the route according to the arrangement sequence of each target user and the number of the target users clicking the route, thereby realizing the determination of the characteristic vector of the route.
The number of clicks of the target user on the route can accurately reflect the click characteristics of the route, so that the accuracy rate of describing the route can be improved according to the characteristic vector determined by the number of clicks.
In order to reduce the influence of the clicking data of the users with a large number of times of clicking the route on the determination of the similarity of the route, the clicking weight of the target user on the first route is inversely related to the number of the target users clicking the first route.
EXAMPLE III
Fig. 3 is a flowchart of a route similarity determining method according to a third embodiment of the present invention. The present embodiment is an alternative proposed based on the above embodiments, taking a target time period as one month, and all drivers click on the delivery route (market level) data of the goods through the shipping platform application within one month as the data source. Referring to fig. 3, the method for determining route similarity according to the present embodiment includes:
historical click route data within one month are obtained as original data.
And according to the clicking time of the historical clicking route, grouping historical clicking route sequences of the same clicking user in the original data according to a set time interval to generate at least one candidate route group, and performing deduplication on the routes in each candidate route group.
And combining every two routes in each candidate route group subjected to the past repetition to generate a candidate route pair.
Calculating the click weight of each user for each route, specifically the click weight of the user =1/g (n), where n is the number of clicks of the route by the user, and g may take a simple increasing function.
And combining the click weight of each user clicking each route to generate the feature vector of the route.
The geometric distance of the feature vector of each route, i.e. the norm of the feature vector, is calculated.
And determining a first route in the target route pair, and determining a second route in the target route pair according to the first route and the candidate route pair.
And calculating the vector product of the feature vector of the first route and the feature vector of the second route, and recording the vector product as Sim1.
And calculating the product of the geometric distance of the feature vector of the first route and the geometric distance of the feature vector of the second route, and recording as Sim2.
Calculating the similarity between the first route and the second route in the target route pair according to the following formula:
Sim＝Sim1/Sim2
where Sim represents the similarity between the first route and the second route in the target route pair.
The method is used for determining the similarity between every two routes in the historical click routes in the target time period.
Specifically, the calculation principle of the above method is as follows:
referring to Table 1, assume that all users interested in two routes form a matrix, with 1 representing interest and 0 not.
TABLE 1
Then, the feature vector of the first route is (0, 1, 0), and the feature vector of the second route is (1, 0,1, 0).
The similarity of the two routes is represented by using the characteristic vector included angle of the routes, and the specific calculation formula is as follows:
further, since the user with a large number of clicks generally cannot reflect the correlation between routes, and instead, several routes clicked by the user with a small number of clicks actually reflect the correlation of routes, the function f (x) instead of 0 and 1 in the matrix can be generally set to 1/g (n), so that the user with a larger number of clicks can obtain a smaller coefficient, where n is the number of clicks of the user on the route, and g can be a simple incremental function. Thus, referring to table 2, the matrix may be changed as follows:
TABLE 2
Then, the feature vector of the first route is (0, 1/30,0,1/100, 0), and the feature vector of the second route is (1/150, 1/30,0,1/100, 0).
The similarity of the two lines shown in table 2 can be determined according to the following formula:
according to the technical scheme, the route is taken as the vector in the high-dimensional vector space, the driver interest is taken as the coordinate axis in the high-dimensional vector space, the length of the vector on the coordinate axis is related to the activity degree of the driver, and the route preferred by most drivers together is determined.
Example four
Fig. 4 is a schematic structural diagram of a route similarity determination apparatus according to a fourth embodiment of the present invention. Referring to fig. 4, the route similarity determination apparatus provided in the present embodiment includes: a route pair determination module 10, a first vector determination module 20, a second vector determination module 30, and a similarity calculation module 40.
The route pair determining module 10 is configured to determine a target route pair from historical click routes in a target time period, and determine at least one target user from click users of the historical click routes;
a first vector determination module 20, configured to determine a first feature vector of a first route in the target route pair according to the number of clicks of the first route in the target time period by the at least one target user;
a second vector determination module 30, configured to determine a second feature vector of a second route in the target route pair according to the number of clicks of the second route in the target time period by the at least one target user;
and the similarity calculation module 40 is configured to calculate a similarity between the first feature vector and the second feature vector, and use the similarity as a similarity between the first route and the second route.
The embodiment of the invention determines at least one target user from the clicking users of the historical clicking routes; determining a first feature vector of a first route in the target route pair according to the number of clicks of the first route in the target time period by the at least one target user; determining a second feature vector of a second route in the target route pair according to the number of clicks of the at least one target user on the second route in the target time period; and calculating the similarity between the first feature vector and the second feature vector, and taking the similarity as the similarity between the first route and the second route, so as to realize the determination of the similarity between the routes, and further mining the potential interested routes of the user according to the determined similarity.
Because the embodiment of the invention does not depend on the peripheral cities of the starting and ending points of the route, the embodiment of the invention is not influenced by the number of the peripheral cities and can comprise the route of the city far away from the starting and ending points.
Because the number of clicks of the target user on the route reflects the supply and demand amount of the route path city, the potential interested route determined based on the similarity of the embodiment of the invention can be matched with more goods.
In addition, the characteristic vector of the route is determined according to the number of clicks of the target user on the route, and the similarity between the two routes is determined according to the similarity between the characteristic vectors of the two routes, so that the number of clicks of the route is associated with the similarity determination of the route. Because the utilization value of the click data of the user with the large number of times of clicking the route is not higher than that of the click data of the user with the small number of times of clicking the route, the influence of the click data of the user with the large number of times of clicking the route on the route similarity determination can be reduced through the correlation between the number of clicks of the route and the route similarity determination, and the similarity determination accuracy is further improved. Further, the first vector determination module includes: a user sorting unit and a first vector determination unit.
The user sorting unit is used for sorting the at least one target user;
and the first vector determining unit is used for determining the first characteristic vector according to the arrangement sequence of each target user and the number of the target users clicking the first route.
Further, the target user's click weight for the first route is inversely related to the number of clicks of the first route by the target user.
Further, the line pair determining module includes: a route acquisition unit, a route grouping unit, and a target route pair determination unit.
The route acquisition unit is used for acquiring a historical click route of a target time period, click time of the historical click route and a click user;
the route grouping unit is used for grouping the historical click routes of the same click user according to the click time of the historical click routes and a set time interval to generate at least one candidate route group and respectively setting different candidate user identifiers for the at least one candidate route group;
and the target route pair determining unit is used for determining a first route and a second route in the target route pair from historical click routes of any one of the candidate route groups.
The route similarity determining device provided by the embodiment of the invention can execute the route similarity determining method provided by any embodiment of the invention, and has corresponding functional modules and beneficial effects of the executing method.
EXAMPLE five
Fig. 5 is a schematic structural diagram of an apparatus provided in embodiment 5 of the present invention, as shown in fig. 5, the apparatus includes a processor 70, a memory 71, an input device 72, and an output device 73; the number of processors 70 in the device may be one or more, and one processor 70 is taken as an example in fig. 5; the processor 70, the memory 71, the input device 72 and the output device 73 of the apparatus may be connected by a bus or other means, as exemplified by a bus connection in fig. 5.
The memory 71 serves as a computer-readable storage medium, and may be used to store software programs, computer-executable programs, and modules, such as program instructions/modules corresponding to the route similarity determination method in the embodiment of the present invention (for example, the route pair determination module 10, the first vector determination module 20, the second vector determination module 30, and the similarity calculation module 40 in the route similarity determination device). The processor 70 executes various functional applications of the device and data processing by running software programs, instructions, and modules stored in the memory 71, that is, implements the route similarity determination method described above.
The memory 71 may mainly include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program required for at least one function; the storage data area may store data created according to the use of the terminal, and the like. Further, the memory 71 may include high speed random access memory, and may also include non-volatile memory, such as at least one magnetic disk storage device, flash memory device, or other non-volatile solid state storage device. In some examples, the memory 71 may further include memory located remotely from the processor 70, which may be connected to the device over a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.
The input device 72 may be used to receive entered numeric or character information and to generate key signal inputs relating to user settings and function controls of the apparatus. The output device 73 may include a display device such as a display screen.
Example six
A sixth embodiment of the present invention further provides a storage medium containing computer-executable instructions, which when executed by a computer processor, are configured to perform a method for route similarity determination, the method including:
determining a target route pair from historical click routes of a target time period, and determining at least one target user from click users of the historical click routes;
determining a first feature vector of a first route in the target route pair according to the number of clicks of the first route in the target time period by the at least one target user;
determining a second feature vector of a second route in the target route pair according to the number of clicks of the at least one target user on the second route in the target time period;
and calculating the similarity between the first feature vector and the second feature vector, and taking the similarity as the similarity between the first route and the second route.
Of course, the storage medium provided by the embodiment of the present invention contains computer-executable instructions, and the computer-executable instructions are not limited to the method operations described above, and may also perform related operations in the route similarity determination method provided by any embodiment of the present invention.
From the above description of the embodiments, it is obvious for those skilled in the art that the present invention can be implemented by software and necessary general hardware, and certainly, can also be implemented by hardware, but the former is a better embodiment in many cases. Based on such understanding, the technical solutions of the present invention may be embodied in the form of a software product, which can be stored in a computer-readable storage medium, such as a floppy disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a FLASH Memory (FLASH), a hard disk or an optical disk of a computer, and includes several instructions for enabling a computer device (which may be a personal computer, a server, or a network device) to execute the methods according to the embodiments of the present invention.
It should be noted that, in the embodiment of the route similarity determining apparatus, the included units and modules are only divided according to functional logic, but are not limited to the above division as long as the corresponding functions can be implemented; in addition, specific names of the functional units are only for convenience of distinguishing from each other, and are not used for limiting the protection scope of the present invention.
It is to be noted that the foregoing description is only exemplary of the invention and that the principles of the technology may be employed. It will be understood by those skilled in the art that the present invention is not limited to the particular embodiments described herein, but is capable of various obvious changes, rearrangements and substitutions as will now become apparent to those skilled in the art without departing from the scope of the invention. Therefore, although the present invention has been described in greater detail by the above embodiments, the present invention is not limited to the above embodiments, and may include other equivalent embodiments without departing from the spirit of the present invention, and the scope of the present invention is determined by the scope of the appended claims.
Claims (9)
1. A route similarity determination method, comprising:
determining a target route pair from historical click routes of a target time period, and determining at least one target user from click users of the historical click routes;
determining a first feature vector of a first route in the target route pair according to the number of clicks of the first route in the target time period by the at least one target user;
determining a second feature vector of a second route in the target route pair according to the number of clicks of the at least one target user on the second route in the target time period;
calculating the similarity between the first feature vector and the second feature vector, and taking the similarity as the similarity between the first route and the second route;
the method for determining the target route pair from the historical click routes in the target time period comprises the following steps:
obtaining a historical click route of a target time period, click time of the historical click route and a click user;
grouping the historical click routes of the same click user according to the click time of the historical click routes and a set time interval to generate at least one candidate route group, and respectively setting different candidate user identifications for the at least one candidate route group;
determining a first route and a second route in the target route pair from historical click routes of any one of the candidate route groups;
determining a first route and a second route in the target route pair from historical clicked routes of any one of the candidate route groups, including:
deleting duplicate routes in each of the route groups;
combining every two historical click routes in each past repeated route group to generate a candidate route pair;
determining a first route of the target route pair;
and searching the second route which is associated with the first route from the candidate route pair according to the first route in the target route pair.
2. The method of claim 1, wherein determining the first feature vector of the first route based on the number of clicks the at least one target user made on the first route of the target route pair over the target period of time comprises:
ranking the at least one target user;
and determining the first feature vector according to the arrangement sequence of each target user and the number of the target users clicking the first route.
3. The method of claim 2, wherein determining the first feature vector based on the ranking of each of the target users and the number of clicks on the first route by the target user comprises:
determining the click weight of each target user on the first route according to the number of the target users clicking the first route;
according to the arrangement sequence of each target user, sorting the click weights of the target users to generate a feature matrix;
and taking the feature matrix as the first feature vector.
4. The method of claim 3, wherein the target user's click weight on the first route is inversely related to the number of clicks on the first route by the target user.
5. A route similarity determination apparatus, comprising:
the route pair determining module is used for determining a target route pair from historical click routes in a target time period and determining at least one target user from click users of the historical click routes;
the first vector determination module is used for determining a first feature vector of a first route in the target route pair according to the number of clicks of the at least one target user on the first route in the target route pair within a target time period;
the second vector determining module is used for determining a second feature vector of a second route in the target route pair according to the number of clicks of the at least one target user on the second route in the target route pair within a target time period;
the similarity calculation module is used for calculating the similarity between the first feature vector and the second feature vector and taking the similarity as the similarity between the first route and the second route;
the line pair determining module includes: a route acquisition unit, a route grouping unit and a target route pair determination unit;
the route acquisition unit is used for acquiring a historical click route of a target time period, click time of the historical click route and a click user;
the route grouping unit is used for grouping the historical click routes of the same click user according to the click time of the historical click routes and a set time interval to generate at least one candidate route group, and different candidate user identifications are respectively set for the at least one candidate route group;
the target route pair determining unit is used for determining a first route and a second route in the target route pair from historical click routes of any one of the candidate route groups;
determining a first route and a second route in the target route pair from historical clicked routes of any one of the candidate route groups, including:
deleting duplicate routes in each of the route groups;
combining every two historical click routes in each past repeated route group to generate a candidate route pair;
determining a first route of the target route pair;
and searching the second route which has an association relation with the first route from the candidate route pair according to the first route in the target route pair.
6. The apparatus of claim 5, wherein the first vector determination module comprises:
the user sorting unit is used for sorting the at least one target user;
and the first vector determining unit is used for determining the first characteristic vector according to the arrangement sequence of each target user and the number of the target users clicking the first route.
7. The apparatus according to claim 6, wherein the first vector determination unit is specifically configured to:
determining the click weight of each target user on the first route according to the number of the target users clicking the first route; according to the arrangement sequence of each target user, sorting the click weights of the target users to generate a feature matrix; and taking the feature matrix as the first feature vector.
8. An electronic device, characterized in that the device comprises:
one or more processors;
a storage device for storing one or more programs,
when executed by the one or more processors, cause the one or more processors to implement the route similarity determination method of any one of claims 1-4.
9. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out a route similarity determination method according to any one of claims 1 to 4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910712478.XA CN110427574B (en) | 2019-08-02 | 2019-08-02 | Route similarity determination method, device, equipment and medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910712478.XA CN110427574B (en) | 2019-08-02 | 2019-08-02 | Route similarity determination method, device, equipment and medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110427574A CN110427574A (en) | 2019-11-08 |
| CN110427574B true CN110427574B (en) | 2022-10-14 |
Family
ID=68412358
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910712478.XA Active CN110427574B (en) | 2019-08-02 | 2019-08-02 | Route similarity determination method, device, equipment and medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110427574B (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111126909B (en) * | 2019-12-20 | 2023-08-08 | 贵阳货车帮科技有限公司 | Data processing method, device, equipment and storage medium for goods source route |
| CN113762667A (en) * | 2020-08-13 | 2021-12-07 | 北京京东振世信息技术有限公司 | Vehicle scheduling method and device |
| CN114218288B (en) * | 2021-11-09 | 2022-09-23 | 北京中交兴路车联网科技有限公司 | Driving route recommendation method and device, storage medium and terminal |
Family Cites Families (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106503022B (en) * | 2015-09-08 | 2020-12-01 | 北京邮电大学 | Method and device for pushing recommendation information |
| CN108806241B (en) * | 2017-04-27 | 2021-08-17 | 阿里巴巴（中国）有限公司 | Method and device for determining common driving route |
| CN109241403B (en) * | 2018-08-03 | 2022-11-22 | 腾讯科技（北京）有限公司 | Project recommendation method and device, machine equipment and computer-readable storage medium |
| CN109299327A (en) * | 2018-11-16 | 2019-02-01 | 广州市百果园信息技术有限公司 | Video recommendation method, device, equipment and storage medium |
| CN109668570A (en) * | 2018-12-21 | 2019-04-23 | 斑马网络技术有限公司 | Travel route recommended method, device, system and storage medium |
| CN109658033B (en) * | 2018-12-26 | 2021-03-16 | 江苏满运物流信息有限公司 | Method, system, device and storage medium for calculating similarity of goods source route |
-
2019
- 2019-08-02 CN CN201910712478.XA patent/CN110427574B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN110427574A (en) | 2019-11-08 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110427574B (en) | Route similarity determination method, device, equipment and medium | |
| US20130054647A1 (en) | Information processing apparatus, information processing method, and program | |
| CN111639253B (en) | Data weight judging method, device, equipment and storage medium | |
| CN105205188A (en) | Method and device for recommending purchase material suppliers | |
| CN110888866B (en) | Data expansion method and device, data processing equipment and storage medium | |
| CN104765793A (en) | Software recommending method and server | |
| CN109241360B (en) | Matching method and device of combined character strings and electronic equipment | |
| CN104123321A (en) | Method and device for determining recommended pictures | |
| CN108984723A (en) | Creation index, data query method, apparatus and computer equipment | |
| EP3407568A1 (en) | Service processing method and device | |
| CN111831686A (en) | Optimization method, device and system of sequencing model, electronic equipment and storage medium | |
| CN115758271A (en) | Data processing method, data processing device, computer equipment and storage medium | |
| CN112528096B (en) | Enterprise analysis method, storage medium and electronic equipment | |
| CN110443493B (en) | Route similarity determination method, device, equipment and medium | |
| CN104503980B (en) | Determining comprehensive search information and determining candidate search sequences to be pushed according to comprehensive search information | |
| CN110188274B (en) | Search error correction method and device | |
| CN110929207A (en) | Data processing method, device and computer readable storage medium | |
| CN110837606A (en) | Spatio-temporal data fusion query method, device, server and storage medium | |
| CN104750822A (en) | Method and device for providing search suggestion | |
| CN113065071B (en) | Product information recommendation method and computer equipment | |
| CN116452014B (en) | Enterprise cluster determination method and device applied to city planning and electronic equipment | |
| CN113868532B (en) | Location recommendation method and device, electronic equipment and storage medium | |
| CN110856253B (en) | Positioning method, positioning device, server and storage medium | |
| CN111274272B (en) | Object searching method and device and computer system | |
| CN109101634B (en) | Data recording processing method, device, electronic equipment and storage medium |
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 |