WO2020034851A1 - 推送信息的方法、装置及设备 - Google Patents

推送信息的方法、装置及设备 Download PDF

Info

Publication number
WO2020034851A1
WO2020034851A1 PCT/CN2019/098880 CN2019098880W WO2020034851A1 WO 2020034851 A1 WO2020034851 A1 WO 2020034851A1 CN 2019098880 W CN2019098880 W CN 2019098880W WO 2020034851 A1 WO2020034851 A1 WO 2020034851A1
Authority
WO
WIPO (PCT)
Prior art keywords
user
information
pick
time
driver
Prior art date
Application number
PCT/CN2019/098880
Other languages
English (en)
French (fr)
Inventor
陆读羚
Original Assignee
北京三快在线科技有限公司
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by 北京三快在线科技有限公司 filed Critical 北京三快在线科技有限公司
Publication of WO2020034851A1 publication Critical patent/WO2020034851A1/zh

Links

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
    • G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
    • G06Q10/063—Operations research, analysis or management
    • G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
    • G06Q10/06315—Needs-based resource requirements planning or analysis
    • 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
    • G06Q10/02—Reservations, e.g. for tickets, services or events
    • G06Q10/025—Coordination of plural reservations, e.g. plural trip segments, transportation combined with accommodation
    • 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"
    • 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

Definitions

  • the present application relates to the field of Internet technologies, and in particular, to a method, a device, and a device for pushing information.
  • the taxi platform will dispatch the vehicle for the user based on the information such as the pick-up point in the order, and estimate the waiting time for the user, that is, the driver's pickup. Driving time.
  • the embodiments of the present application provide a method, device, and device for pushing information, so as to solve the problem that the user waits for the driver to pick up the car for too long and easily cancels the order, which results in a decrease in the rate of the taxi platform and wastes the driver's time, which affects Issues for both user and driver experience.
  • a method for pushing information including:
  • the user's taxi order determine the information about the driver's pick-up time and the user's travel intention
  • the target information associated with the travel intention is pushed to the user.
  • a device for pushing information including:
  • the information and intent determination module is used to determine the driver's pick-up time related information and the user's travel intention based on the user's taxi order;
  • a target information push module is configured to push target information associated with the travel intention to the user when the information about the pick-up time meets a preset condition.
  • a device for pushing information which includes a memory, a processor, and a computer program stored on the memory and executable on the processor, wherein the processor executes the program To implement the above-mentioned method of pushing information.
  • a computer-readable storage medium stores a computer program, where the computer program is used to execute the foregoing method for pushing information.
  • FIG. 1 is a flowchart of a method for pushing information according to a first exemplary embodiment of the present application
  • FIG. 2 is a flowchart of a method for pushing information according to a second exemplary embodiment of the present application
  • FIG. 3 is a flowchart of a method for pushing information according to a third exemplary embodiment of the present application.
  • FIG. 4 is a flowchart of a method for pushing information according to a fourth exemplary embodiment of the present application.
  • Fig. 5 is a flow chart showing a method for pushing information according to a fifth exemplary embodiment of the present application.
  • FIG. 6 is a flowchart of a method for pushing information according to a sixth exemplary embodiment of the present application.
  • FIG. 7 is a flowchart illustrating how to determine a travel intention of the user according to an exemplary embodiment of the present application.
  • FIG. 8 is a flowchart illustrating how to determine a travel intention of the user according to another exemplary embodiment of the present application.
  • FIG. 9 is a flowchart of a method for pushing information according to a seventh exemplary embodiment of the present application.
  • FIG. 10 is a structural diagram of a device for pushing information according to an exemplary embodiment of the present application.
  • FIG. 11 is a structural diagram of a device for pushing information, according to another exemplary embodiment of the present application.
  • Fig. 12 is a structural diagram of a device for pushing information according to an exemplary embodiment of the present application.
  • first, second, third, etc. may be used in this application to describe various information, such information should not be limited to these terms. These terms are only used to distinguish the same type of information from each other.
  • first information may also be referred to as the second information, and similarly, the second information may also be referred to as the first information.
  • word "if” as used herein can be interpreted as “at” or “when” or "in response to a determination”.
  • FIG. 1 is a flowchart of a method for pushing information according to a first exemplary embodiment of the present application; this embodiment may be used for a server of a taxi platform (for example, a server cluster composed of one server and multiple servers, etc.) .
  • a server of a taxi platform for example, a server cluster composed of one server and multiple servers, etc.
  • the method includes steps S101-S102:
  • step S101 according to the user's taxi order, determine the driver's pick-up time related information and the user's travel intention.
  • the server when the server receives a taxi order sent by the user, the server can determine information about the driver's pick-up time and the user's travel intention.
  • a user can send a taxi order to the server through a smart terminal such as a mobile phone or tablet computer.
  • the server can determine information about the driver's pick-up time and the user's travel intention.
  • the server may determine to take the driver by means of grabbing orders or dispatching orders.
  • the above-mentioned information about the pick-up time can be set by the developer according to the actual business needs, such as the pick-up time and the pick-up timeout.
  • the pick-up time and the pick-up timeout For details, see the implementation shown in Figures 3 and 4 below. For example, we will not go into details here.
  • step S102 if the information about the pick-up time satisfies a preset condition, push the target information associated with the travel intention to the user.
  • a preset condition for pushing target information to a user may be set in advance. After determining the driver-related time-related information, it is determined whether the driver-time-related information satisfies the preset condition.
  • target information associated with the travel intention may be pushed to the user; otherwise, the information about the pick-up time may be ignored.
  • the above-mentioned time-related information meets a preset condition, and may include at least the following three cases:
  • the first case After determining the above-mentioned information about the pick-up time, the user may send the information about the pick-up time.
  • the pick-up time-related information meets a preset condition.
  • the server determines information about the pick-up time (such as the result of the pick-up time or whether the pick-up will time out)
  • it can send the information about the pick-up time to the user.
  • the user may send a request to cancel the order because the pick-up time is too long or the pick-up will time out.
  • the server can determine that the pick-up time related information meets the preset condition.
  • the second case the value of the information about the pick-up time meets a preset condition.
  • the preset condition for pushing target information to the user is "the value of the time-related information is greater than or equal to a preset threshold”
  • the value is related to The above thresholds are compared.
  • the third case The content of the above-mentioned time-related information meets a preset condition.
  • the preset condition for pushing the target information to the user is "the content of the pick-up time-related information includes preset information"
  • the content is related to the preset information
  • the matching is performed, and when it is determined that the content of the time-related information includes the above-mentioned preset information, it is determined that the time-related information meets a preset condition.
  • the travel intention of the user may be classified by the developer according to actual business needs, such as dating, parent-child, movie watching, travel, and re-driving, which is not limited in this embodiment.
  • the above target information may be used to prompt the user to keep the current order or continue to wait for the vehicle to obtain the target content corresponding to the target information.
  • the method for determining the travel intention may refer to the embodiments shown in FIG. 7 and FIG. 8 below, and will not be described in detail here.
  • the association relationship between various travel intentions of the user and the target information can be constructed in advance, and further, when the time-related information meets a preset condition, the association with the travel intention of the user can be determined according to the pre-established association relationship.
  • the content of the above target information may be: if this order is retained, a "popcorn coupon” can be obtained. Among them, the target content B in "B" can be changed according to the travel intention of the user.
  • this embodiment determines the driver's pick-up time related information and the user's travel intention based on the user's taxi order, and when the pick-up time related information meets a preset condition, the user is pushed with the The target information associated with the travel intention, because when the time-related information meets the preset conditions, it is determined that the user may cancel the current order. At this time, the target information is pushed to the user. If the user is interested in the pushed target information, he may choose to keep the current information.
  • a taxi order can increase the probability that a user will retain a taxi order, thereby increasing the success rate of the taxi platform, avoiding wasting driver time due to the user's cancellation of the order, and improving the user experience of both the user and the driver.
  • FIG. 2 is a flowchart of a method for pushing information shown in a second exemplary embodiment of the present application; this embodiment can be used for a server of a taxi platform (for example, a server cluster composed of one server and multiple servers, etc.) . As shown in FIG. 2, the method includes steps S201-S203:
  • step S201 a boarding point of the user, corresponding associated information, and a travel intention of the user are determined according to a taxi order of the user.
  • the server can determine the pickup point in the taxi order and the associated information corresponding to the taxi order; at the same time, it can also determine the user's travel intention (see Figure 6 below) The embodiment shown is not described in detail here).
  • the above-mentioned related information may include one or more of the following: road conditions, weather, driver positioning information, driver pickup trajectory, driver pickup speed, driver driving habits, and the like.
  • step S202 the driver's pick-up time related information is determined according to the pick-up point and the related information.
  • the driver's pick-up time related information may be determined according to the pick-up point and the related information. In one embodiment, the driver's pick-up time related information is determined according to the user's pick-up point, road conditions in the associated information, and driver positioning information.
  • the above-mentioned information about the pick-up time can be set by the developer according to the actual business needs, such as the pick-up time and the pick-up timeout.
  • the pick-up time and the pick-up timeout For details, see the implementation shown in Figures 3 and 4 below. For example, we will not go into details here.
  • step S203 if the information about the pick-up time satisfies a preset condition, the target information associated with the travel intention is pushed to the user.
  • step S203 For the related explanation and description of step S203, reference may be made to the foregoing embodiments, and details are not described herein.
  • this embodiment determines the user's boarding point, corresponding related information, and the user's travel intention, and determines the driver based on the boarding point and the related information.
  • the relevant information of the pick-up time can accurately determine the relevant information of the pick-up time, provide accurate basis for the subsequent push of the target information to the user based on the relevant information of the pick-up time, and achieve the purpose of increasing the rate of the taxi platform.
  • FIG. 3 is a flowchart of a method for pushing information according to a third exemplary embodiment of the present application; this embodiment may be used for a server of a taxi platform (for example, a server cluster composed of one server and multiple servers, etc.) . As shown in FIG. 3, the method includes steps S301-S303:
  • step S301 according to the taxi order of the user, the boarding point of the user, the corresponding associated information, and the user's travel intention are determined.
  • step S301 For the explanation and description of step S301, reference may be made to the foregoing embodiment, and details are not described herein.
  • step S302 the pick-up time of the driver is determined according to the pick-up point and the related information.
  • the server when the server receives a taxi order sent by the user, the server can determine the taxi point based on the taxi order, road conditions, weather, driver positioning information, driver trajectory, driver speed, and driver. Related information, such as driving habits, estimates the driver's pick-up time.
  • step S303 if the pick-up time is greater than or equal to a preset pick-up time threshold, target information associated with the travel intention is pushed to the user.
  • the preset pick-up time threshold may be set by a developer according to actual business requirements, such as 20 minutes, 30 minutes, and the like, which is not limited in this embodiment.
  • the estimated pick-up time can be compared with the preset pick-up time threshold, if the pick-up time is greater than or equal to the preset pick-up time
  • the driving time threshold may push target information associated with the travel intention to the user.
  • this embodiment determines the driver's pick-up time according to the user's taxi order, and pushes the user's travel intention with the user when the pick-up time is greater than or equal to a preset pick-up time threshold.
  • Associated target information because it is determined that the user may cancel the order when it is determined that the driver's pickup time is too long. In this case, the target information associated with the user's travel intention is sent.
  • the user has the purpose of obtaining the target content corresponding to the target information. It is possible to choose to retain the taxi order, which can increase the probability of the user retaining the taxi order, increase the rate of the taxi platform, avoid wasting driver time due to the user's cancellation of the order, and improve the user experience of both the user and the driver.
  • FIG. 4 is a flowchart illustrating a method for pushing information according to a fourth exemplary embodiment of the present application; this embodiment may be used for a server of a taxi platform (for example, a server cluster composed of one server and multiple servers, etc.) .
  • a server of a taxi platform for example, a server cluster composed of one server and multiple servers, etc.
  • the method includes steps S401-S403:
  • step S401 according to the taxi order of the user, a boarding point of the user, corresponding associated information, and a travel intention of the user are determined.
  • step S401 For the explanation and description of step S401, reference may be made to the foregoing embodiment, and details are not described herein.
  • step S402 the pick-up point and the related information are input into a pre-built decision tree model to obtain a prediction result used to characterize whether the driver will time out.
  • the server may also input the pick-up point and the related information into a pre-built decision tree model to obtain a prediction result used to characterize whether the driver will time out.
  • the decision tree model may include, but is not limited to, the historical driving distance of the driver, the average historical pick-up time of the driver, and the historical timeout rate of the driver. Using these features, by entering the user's pick-up point and corresponding associated information The decision tree model can predict whether the pick-up time required for a driver to reach the pick-up point will exceed a pick-up time threshold, thereby obtaining whether the pick-up time required for the driver to reach the pick-up point will be determined. A prediction result that exceeds the pick-up time threshold.
  • the decision tree model can also be pre-built and stored on the server side of the taxi platform.
  • decision tree model can be constructed by using a construction method of a decision tree model that is well known to those skilled in the art, which is not limited in this embodiment.
  • the server may also determine the initial pick-up time according to the pick-up point in the taxi order and the corresponding associated information. Further, during the driver pick-up process, the driver's current pick-up time can be predicted in real time according to the driving time-related information corresponding to the driver's traveled distance, and then the current pick-up time is compared with the initial pick-up time to Get a prediction of whether the pickup will time out.
  • step S403 if the prediction result indicates that the driver will time out when the driver picks up the vehicle, the target information associated with the travel intention is pushed to the user.
  • the prediction result indicates that the driver will time out when the driver picks up. If yes, the user is pushed to the user with the travel intention. Associated target information.
  • the server can further determine whether the proportion of the timeout period to the determined pickup time is greater than or equal to a preset ratio threshold, or, Determine whether the timeout period is greater than or equal to a preset timeout period threshold to ensure that the target information is pushed to the user when the timeout condition will adversely affect the user.
  • the timeout period is short (for example, it only times out for a few seconds), that is, the ratio of the timeout period to the pick-up time is less than the preset ratio threshold, or if the timeout period is less than the preset timeout period threshold, the timeout can be determined. The situation does not adversely affect the user, so there is no need to push the target information to the user.
  • the user may be pushed with the travel intention Associated target information.
  • FIG. 5 is a flowchart of a method for pushing information shown in a fifth exemplary embodiment of the present application; this embodiment can be used for a server of a taxi platform (for example, a server cluster composed of one server and multiple servers, etc.) . As shown in FIG. 5, the method includes steps S501-S508:
  • step S501 a boarding point of the user, corresponding associated information, and a travel intention of the user are determined.
  • step S502 the boarding point and the related information are input into a pre-built decision tree model to obtain a prediction result used to characterize whether the driver will time out.
  • step S503 it is determined whether the prediction result indicates that the driver will time out when picking up: if yes, steps S504-S507 and step S508 may be performed.
  • step S504 acquiring a plurality of associated information corresponding to the traveled distance during the driver's pick-up process.
  • the driver's terminal device reports the traveled distance and the corresponding multiple related information to the server, and the server can obtain multiple related information corresponding to the traveled distance.
  • step S505 a first contribution degree of each of the related information to the estimated travel time of the traveled distance and a second contribution degree to the actual travel time of the traveled distance are calculated.
  • the estimated travel time is determined according to the traveled distance and a plurality of related information of the taxi order when the taxi order is generated.
  • the server when determining the current travel distance of the driver, may calculate a first contribution of each of the related information to the estimated travel time of the traveled distance, and calculate each of the related information. A second contribution to the actual travel time of the traveled distance.
  • contribution degree calculation method known to those skilled in the art may be used to calculate the contribution degree of each of the related information to the estimated travel time or actual travel time of the traveled distance, which is not limited in this embodiment.
  • step S506 the first N pieces of associated information with the largest difference between the second contribution degree and the first contribution degree are determined as the cause of the timeout of the pick-up.
  • N is a preset positive integer, such as 1, 2, or 3, and so on.
  • the first N pieces of associated information with the largest difference between the second contribution degree and the first contribution degree are determined as the cause of the timeout of the pick-up.
  • each of the related information has a first contribution to the estimated travel time of the traveled distance, and a second contribution to the actual travel time of the traveled distance is as follows: One shown:
  • the one piece of associated information with the largest difference between the second contribution and the first contribution is "road condition", so the "road condition” can be determined as the cause of the timeout for the pickup.
  • step S507 the description information is generated according to the reason for the timeout of the pick-up meeting, and is pushed to the user.
  • the description information may be generated according to the reason why the pick-up meeting times out, and then the description information is pushed to the user.
  • step S508 target information associated with the travel intention is pushed to the user.
  • steps S507 and S508 are not limited.
  • developers can push the above target information and description information separately according to business needs, or they can use the description information as part of the target information. Push, this embodiment does not limit this.
  • steps S501-S503 and S508 reference may be made to the foregoing embodiments, and details are not described herein.
  • FIG. 6 is a flowchart of a method for pushing information according to a sixth exemplary embodiment of the present application; this embodiment may be used for a server of a taxi platform (for example, a server cluster composed of one server and multiple servers, etc.) .
  • a server of a taxi platform for example, a server cluster composed of one server and multiple servers, etc.
  • the method includes steps S601-S603:
  • step S601 the driver's pick-up time related information and the user's travel intention are determined according to the user's taxi order.
  • step S602 if the information related to the pick-up time satisfies a preset condition, the target information associated with the travel intention is pushed to the user.
  • steps S601-S602 For the explanation and description of steps S601-S602, reference may be made to the foregoing embodiments, and details are not described herein.
  • step S603 if an instruction to continue waiting for the vehicle sent by the user in response to the target information is received, target content corresponding to the target information is pushed to the user.
  • the above-mentioned instruction for continuing to wait for a taxi may be sent by the user by clicking the option of “continuing waiting for a taxi” or “holding a taxi order” set in the target information.
  • the user may be sent to the user target information including a "reserve taxi order” option, and then when the user clicks the "reserve taxi order” option, the The user pushes target content corresponding to the target information.
  • the user may be sent to the user with the message "Continue to wait for a taxi.”
  • Option “option, and then when the user clicks the” continue to wait for the car option "option, the user is pushed to the user with the target content corresponding to the target information.
  • the above target content can be set by the developer according to actual business needs, such as setting coupons, event information, attraction introductions, play strategies, and social topics, which are not limited in this embodiment.
  • the target content can be locked to make it unavailable or invalid to prevent users from illegally obtaining the target content , Causing losses to the platform.
  • FIG. 7 is a flowchart illustrating how to determine a user's travel intention according to an exemplary embodiment of the present application; based on the above embodiment, this embodiment uses an example of how to determine a user's travel intention as an example. As shown in FIG. 7, determining the travel intention of the user in step S101 may include the following steps S701-S703:
  • step S701 a boarding point, a destination, and corresponding associated information of the user are determined.
  • the server when the server receives a taxi order sent by a user, the server can determine the user's boarding point, destination, and corresponding associated information.
  • step S702 an estimated arrival time of the user is calculated according to the boarding point, the destination, and the associated information.
  • the accuracy of the above-mentioned estimated time can be set by a developer according to actual business needs, such as being set to be accurate to hours, minutes, seconds, etc., which is not limited in this embodiment.
  • a first neural network model for determining an estimated arrival time of a user may be constructed according to sample data in advance.
  • the sample data used to construct the first neural network includes historical driving data of the driver.
  • the server may input the pick-up point, the destination, and the current association information into a pre-built first neural network model to obtain the estimated arrival time of the user.
  • predicting the user's estimated arrival time based on the pre-built neural network model and the pick-up point, the destination and the current associated information can improve the accuracy of the estimated arrival time and further improve the accuracy of the travel intention prediction .
  • step S703 a user's travel intention is predicted based on the estimated arrival time and the destination.
  • the user's travel intention can be predicted based on the estimated arrival time and destination.
  • the user's travel intention can be predicted to be "watching a movie” based on the time and place information.
  • the estimated arrival time of the user is calculated according to the boarding point, the destination, and the related information, and the user's travel is predicted based on the estimated arrival time and the destination. Intentions can accurately predict the user's travel intentions, which can further improve the accuracy of subsequent determination of associated target information based on the travel intentions.
  • FIG. 8 is a flowchart showing how to determine a user's travel intention based on a user portrait, estimated arrival time, and POI (point of interest) according to an exemplary embodiment of the present application; this embodiment is based on the above embodiment,
  • the user portrait, estimated time of arrival, and POI to determine the user's travel intention are taken as examples for illustration.
  • the above step S603 predicts a user's travel intention based on the estimated arrival time and the destination, and may include the following steps S801-S804:
  • step S801 a user portrait of the user is acquired.
  • the server may obtain the user portrait of the user in advance, or obtain the user portrait of the user after calculating the estimated arrival time of the user.
  • the user portrait also known as the user role, is an effective tool for sketching target users, connecting user demands and design directions.
  • a user portrait is a labeled user model that is abstracted based on information such as user social attributes, living habits, and consumer behavior.
  • the core task of constructing user portraits is to affix "tags" to users, and tags are highly refined feature identifications obtained by analyzing user information.
  • the user portrait server can tag the user with "children" according to the purchase situation of the toy, and even determine the approximate age of the user's child, and paste "with 5-10 years old Child "tags, and the set and all the tags affixed to the user constitute the user portrait of the user, that is, the user portrait can be used to determine what kind of person the user is.
  • step S802 a preset area centered on the destination is determined.
  • a preset area centered on the destination may be further determined.
  • the size of the preset area can be divided by developers according to actual business requirements, such as 1km, 2km, etc., which is not limited in this embodiment.
  • step S803 at least one POI in the preset area is queried.
  • At least one POI in the preset area may be queried based on a third-party map library.
  • the above-mentioned POI may be a place displayed by a bubble icon on an electronic map, such as a scenic spot, a government agency, a company, a shopping mall, a restaurant, or the like.
  • step S804 the portrait of the user, the estimated arrival time, and the activity information or category of the at least one POI are input into a pre-built second neural network model to obtain the travel intention of the user.
  • the activity information of the at least one point of interest POI (eg, movie shows, shopping mall promotions), or the at least one point of interest may be determined.
  • Types of POI such as residence, work, business, entertainment, tourism, and learning).
  • a second neural network model for determining a user's travel intention may be constructed according to the sample data in advance.
  • the estimated arrival time, and the activity information or type of the at least one POI may be input into a pre-built second neural network model to obtain the User travel intentions.
  • FIG. 9 is a flowchart illustrating a method for pushing information according to a sixth exemplary embodiment of the present application; this embodiment can be used for a server of a taxi platform (for example, a server cluster composed of one server and multiple servers, etc.) .
  • a server of a taxi platform for example, a server cluster composed of one server and multiple servers, etc.
  • the method includes steps S901-S903:
  • step S901 the driver's pick-up time related information and the user's travel intention are determined according to the user's taxi order.
  • step S902 if the information about the pick-up time satisfies a preset condition, the target information associated with the travel intention is pushed to the user.
  • step S903 it is determined whether the target information meets the needs of the user: if yes, the push information process is ended; otherwise, the user's travel intention is re-determined based on the multi-round interactive question and answer method, and then based on the re-determined travel Intent to push the associated target information to the user again. In an embodiment, if the response of the user is not received within a preset period of time after the target information is pushed to the user, it may be determined that the target information does not meet the needs of the user.
  • the server can re-determine the user's travel intention based on the multiple rounds of interactive question and answer.
  • the re-determined travel intention of the user may also be used to optimize the second neural network constructed above to improve the accuracy of the second neural network in predicting the travel intention of the user.
  • the user may send the above feedback information to the server by clicking the "satisfied / unsatisfied” option on the user interface of the taxi client.
  • the specific content of the multiple rounds of interactive Q & A can be set by the developer according to the actual business needs, such as "Is the purpose of this trip to travel?", "The purpose of this trip Is it working? “Etc. This embodiment is not limited to this.
  • this embodiment re-determines the travel intention of the user based on multiple rounds of interactive question and answer, and queries the target associated with the re-determined travel intention
  • the information and push to the user can further improve the accuracy of predicting the travel intention of the user, and further improve the accuracy of determining the associated target information based on the travel intention.
  • this application also provides embodiments of corresponding devices.
  • FIG. 10 is a structural diagram of a device for pushing information according to an exemplary embodiment of the present application; as shown in FIG. 10, the device may include: an information and intention determination module 110 and a target information pushing module 120, where:
  • the information and intent determination module 110 is configured to determine information about the driver's pick-up time and the user's travel intention according to the user's taxi order;
  • the target information pushing module 120 is configured to push target information associated with the travel intention to the user when the information about the pick-up time meets a preset condition.
  • the information and intention determination module 110 is further configured to determine the driver's pick-up time related information according to the user's taxi order and the driver's response to the taxi order.
  • this embodiment determines the driver's pick-up time related information and the user's travel intention, and when the pick-up time related information meets a preset condition, the user is pushed to the user with
  • the target information related to the travel intention is described, because when the time-related information meets the preset conditions, it is determined that the user may cancel the current order. At this time, the target information is pushed to the user. If the user is interested in the pushed target information, he may choose to keep it.
  • the current taxi order can increase the probability that a user will retain a taxi order, thereby increasing the success rate of the taxi platform, avoiding wasting driver time due to the user's cancellation of the order, and improving the user experience of both the user and the driver.
  • FIG. 11 is a structural diagram of a device for pushing information according to still another exemplary embodiment of the present application; wherein, the information and intent determining module 210 and the target information pushing module 220 and the information and intent in the foregoing embodiment shown in FIG. 10
  • the functions of the determining module 110 and the target information pushing module 120 are the same, and details are not described herein.
  • the information related to the pick-up time meets a preset condition, and may include:
  • the value of the information related to the pick-up time satisfies a preset numerical condition
  • the content of the time-related information meets a preset content condition
  • the information and intention determination module 210 may include: a related information determination unit 211;
  • the related information determining unit 211 may be configured to:
  • the related information determining unit 211 may be further configured to:
  • the values of the time-related information meet the preset numerical conditions, which may include:
  • the pick-up time is greater than or equal to a preset pick-up time threshold.
  • the related information determining unit 211 may be further configured to:
  • the content of the time-related information meets the preset content conditions, which may include:
  • the prediction result signifies that the driver will time out when picking up.
  • a ratio of the timeout period to the pick-up time is greater than or equal to a preset ratio threshold, or the timeout period is greater than or equal to a preset timeout period threshold.
  • the apparatus may further include: a description information generating module 230;
  • the description information generating module 230 may further include:
  • An association information obtaining unit 231, configured to obtain a plurality of association information corresponding to the distance traveled during the driver's pick-up;
  • a contribution degree calculation unit 232 configured to calculate a first contribution degree of each of the associated information to the estimated travel time of the traveled distance, and a second contribution degree to the actual travel time of the traveled distance;
  • the timeout cause determining unit 233 is configured to determine the first N pieces of associated information with the largest difference between the second contribution degree and the first contribution degree as the reason for the timeout of the pick-up meeting, where N is a preset positive integer;
  • a description information generating unit 234 is configured to generate description information according to a reason for the timeout of the pickup meeting, and push the description information to the user.
  • the apparatus may further include:
  • a target content pushing module 240 is configured to push the target content corresponding to the target information to the user when receiving a user's instruction to continue waiting for a vehicle sent in response to the target information.
  • the information and intention determination module 210 may further include: a travel intention determination unit 212;
  • the travel intention determination unit 212 may be configured to:
  • the travel intention determining unit 212 may be further configured to:
  • the user portrait, the estimated arrival time, and the activity information or category of the at least one POI are input into a pre-built neural network model to obtain the travel intention of the user.
  • the information and intent determination module 210 may be further configured to re-determine the travel of the user if a response from the user is not received within a preset period of time after the target information is pushed to the user. intention;
  • the target information pushing module 212 may be further configured to push the target information to the user according to the pick-up time related information and the newly determined travel intention.
  • the embodiments of the apparatus for pushing information of the present disclosure may be applied to a network device.
  • the device embodiments may be implemented by software, or by hardware or a combination of software and hardware. Take software implementation as an example.
  • As a logical device it is formed by reading the corresponding computer program instructions in the non-volatile memory into the memory through the processor of the device in which it resides.
  • the computer program is used to execute the above.
  • the method for pushing information provided by the embodiments shown in FIG. 1 to FIG. 9.
  • FIG. 12 a hardware structure diagram of a device for pushing information according to the present disclosure.
  • the device can also include other hardware, such as a forwarding chip responsible for processing messages.
  • the device may also be a distributed device, which may include multiple interface cards, so that the message processing can be extended at the hardware level.
  • the present application also provides a computer-readable storage medium.
  • the storage medium stores a computer program, and the computer program is configured to execute the method for pushing information provided by the embodiments shown in FIG. 1 to FIG. 9.
  • the relevant part may refer to the description of the method embodiment.
  • the device embodiments described above are only schematic, wherein the units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, may be located One place, or it can be distributed across multiple network elements. Some or all of these modules can be selected according to actual needs to achieve the purpose of the solution of this application. Those of ordinary skill in the art can understand and implement without creative efforts.

Landscapes

  • Business, Economics & Management (AREA)
  • Engineering & Computer Science (AREA)
  • Human Resources & Organizations (AREA)
  • Strategic Management (AREA)
  • Economics (AREA)
  • Tourism & Hospitality (AREA)
  • Theoretical Computer Science (AREA)
  • Marketing (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Physics & Mathematics (AREA)
  • General Business, Economics & Management (AREA)
  • General Physics & Mathematics (AREA)
  • Development Economics (AREA)
  • Operations Research (AREA)
  • Quality & Reliability (AREA)
  • Game Theory and Decision Science (AREA)
  • Educational Administration (AREA)
  • Health & Medical Sciences (AREA)
  • General Health & Medical Sciences (AREA)
  • Primary Health Care (AREA)
  • Traffic Control Systems (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)
  • Navigation (AREA)

Abstract

本申请提供一种推送信息的方法、装置及设备，其中，所述方法包括：根据用户的打车订单，确定司机的接驾时间相关信息以及用户的出行意图；若所述接驾时间相关信息满足预设条件，则向所述用户推送与所述出行意图关联的目标信息。本申请由于当接驾时间相关信息满足预设条件时，判断用户可能取消当前订单，此时向用户推送目标信息，若用户对推送的目标信息感兴趣，则可能选择保留当前的打车订单。

Description

推送信息的方法、装置及设备 技术领域
本申请涉及互联网技术领域，尤其涉及一种推送信息的方法、装置及设备。
背景技术
随着互联网行业的迅猛发展，使用打车软件的用户也越来越多。通常情况下，打车平台在接到用户通过手机等智能终端发送的打车订单后，会根据该订单中的上车点等信息为用户调度车辆，并为用户预估等车时间，即司机的接驾时间。
然而在预估的接驾时间较长，或预估司机接驾超时等情况下，用户容易取消订单，不仅会降低打车平台的成单率，还会浪费司机的时间，影响用户和司机双方的体验。
发明内容
有鉴于此，本申请实施例提供一种推送信息的方法、装置及设备，以解决用户等待司机接驾时间过长容易取消订单，导致打车平台的成单率降低，以及浪费司机的时间，影响用户和司机双方的体验的问题。
根据本申请实施例的第一方面，提出了一种推送信息的方法，包括：
根据用户的打车订单，确定司机的接驾时间相关信息以及用户的出行意图；
若所述接驾时间相关信息满足预设条件，则向所述用户推送与所述出行意图关联的目标信息。
根据本申请实施例的第二方面，提出了一种推送信息的装置，包括：
信息及意图确定模块，用于根据用户的打车订单，确定司机的接驾时间相关信息以及用户的出行意图；
目标信息推送模块，用于当所述接驾时间相关信息满足预设条件时，向所述用户推送与所述出行意图关联的目标信息。
根据本申请实施例的第三方面，提出了一种推送信息的设备，包括存储器、处理器及存储在存储器上并可在处理器上运行的计算机程序，其中，所述处理器执行所述程序时实现上述推送信息的方法。
根据本申请实施例的第四方面，提出了一种计算机可读存储介质，所述存储介质存储有 计算机程序，所述计算机程序用于执行上述推送信息的方法。
附图说明
图1是本申请第一示例性实施例示出的一种推送信息的方法的流程图；
图2是本申请第二示例性实施例示出的一种推送信息的方法的流程图；
图3是本申请第三示例性实施例示出的一种推送信息的方法的流程图；
图4是本申请第四示例性实施例示出的一种推送信息的方法的流程图；
图5是本申请第五示例性实施例示出的一种推送信息的方法的流程图；
图6是本申请第六示例性实施例示出的一种推送信息的方法的流程图；
图7是本申请一示例性实施例示出的如何确定所述用户的出行意图的流程图；
图8是本申请又一示例性实施例示出的如何确定所述用户的出行意图的流程图；
图9是本申请第七示例性实施例示出的一种推送信息的方法的流程图；
图10是本申请一示例性实施例示出的一种推送信息的装置的结构图；
图11是本申请又一示例性实施例示出的一种推送信息的装置的结构图；
图12是本申请一示例性实施例示出的一种推送信息的设备的结构图。
具体实施方式
这里将详细地对示例性实施例进行说明，其示例表示在附图中。下面的描述涉及附图时，除非另有表示，不同附图中的相同数字表示相同或相似的要素。以下示例性实施例中所描述的实施方式并不代表与本申请相一致的所有实施方式。相反，它们仅是与如所附权利要求书中所详述的、本申请的一些方面相一致的装置和方法的例子。
在本申请使用的术语是仅仅出于描述特定实施例的目的，而非旨在限制本申请。在本申请和所附权利要求书中所使用的单数形式的“一种”、“所述”和“该”也旨在包括多数形式，除非上下文清楚地表示其他含义。还应当理解，本文中使用的术语“和/或”是指并包含一个或多个相关联的列出项目的任何或所有可能组合。
应当理解，尽管在本申请可能采用术语第一、第二、第三等来描述各种信息，但这些信息不应限于这些术语。这些术语仅用来将同一类型的信息彼此区分开。例如，在不脱离本申请范围的情况下，第一信息也可以被称为第二信息，类似地，第二信息也可以被称为第一信息。取决于语境，如在此所使用的词语“如果”可以被解释成为“在……时”或“当……时” 或“响应于确定”。
图1是本申请第一示例性实施例示出的一种推送信息的方法的流程图；该实施例可以用于打车平台的服务端(例如，一台服务器和多台服务器组成的服务器集群等)。
如图1所示，该方法包括步骤S101-S102：
在步骤S101中：根据用户的打车订单，确定司机的接驾时间相关信息以及用户的出行意图。
在一实施例中，当服务端接收到用户发送的打车订单时，可以确定司机的接驾时间相关信息以及用户的出行意图。
举例来说，用户可以通过手机、平板电脑等智能终端向服务端发送打车订单，进而当服务端接收到用户发送的打车订单后，可以确定司机的接驾时间相关信息以及用户的出行意图。
在一实施例中，当用户发起打车订单时，服务端可通过抢单或者派单等方式确定接驾司机。
在一实施例中，确定接驾时间相关信息的方式还可以参见下述图2所示实施例，在此先不进行详述。
在一实施例中，上述接驾时间相关信息可以由开发人员根据实际业务需要进行设置，如设置为接驾时间、接驾超时情况等，具体还可以参见下述图3、图4所示实施例，在此先不进行详述。
在步骤S102中：若所述接驾时间相关信息满足预设条件，则向所述用户推送与所述出行意图关联的目标信息。
在一实施例中，可以预先设置向用户推送目标信息的预设条件，当确定上述司机的接驾时间相关信息后，判断该接驾时间相关信息是否满足该预设条件。
在一实施例中，若所述接驾时间相关信息满足预设条件，则可以向所述用户推送与所述出行意图关联的目标信息；否则，可以忽略该接驾时间相关信息。
在一实施例中，上述接驾时间相关信息满足预设条件，至少可以包括以下三种情况：
第一种情况：当确定上述接驾时间相关信息后，可以向用户发送该接驾时间相关信息。当接收到所述用户响应于所述接驾时间相关信息发送的取消订单的请求时，可以确定接驾时间相关信息满足预设条件。
举例来说，当服务端确定接驾时间相关信息(如，接驾时间或接驾是否会超时的预测结果等)后，可以将该接驾时间相关信息发送给用户。当用户接收到该接驾时间相关信息后， 可能因为接驾时间太长或接驾会超时等原因而发送取消订单的请求，在此情况下，服务端可以确定接驾时间相关信息满足预设条件。
第二种情况：上述接驾时间相关信息的数值满足预先设定的条件。
举例来说，若预先设置的向用户推送目标信息的条件是“接驾时间相关信息的数值大于或等于预设的阈值”，则可以当确定接驾时间相关信息的数值后，将该数值与上述阈值进行比较，当确定接驾时间相关信息的数值大于或等于上述阈值时，确定接驾时间相关信息满足预设条件。
值得说明的是，下述图3所示实施例即属于该第二种情况。
第三种情况：上述接驾时间相关信息的内容满足预先设定的条件。
举例来说，若预先设置的向用户推送目标信息的条件是“接驾时间相关信息的内容包含预设信息”，则当确定接驾时间相关信息的内容后，将该内容与上述预设信息进行匹配，进而当确定接驾时间相关信息的内容包含上述预设信息时，确定接驾时间相关信息满足预设条件。
值得说明的是，下述图4所示实施例即属于该第三种情况。
在一实施例中，用户的出行意图可以由开发人员根据实际业务需要进行类别划分，如划分为约会、亲子、看电影、旅游以及重新打车等，本实施例对此不进行限定。
在一实施例中，上述目标信息可以用于提示用户保留当前订单或继续等车，以获取目标信息对应的目标内容。
在一实施例中，出行意图的确定方法可以参见下述图7、图8所示实施例，在此先不进行详述。
在一实施例中，可以预先构建用户的各种出行意图与目标信息的关联关系，进而可以在接驾时间相关信息满足预设条件时，根据预先构建的关联关系确定与用户的出行意图关联的目标信息，并向用户进行推送。
举例来说，若服务端确定用户此次的出行意图为看电影，则上述目标信息的内容可以为：如果保留本订单，可以得到“爆米花优惠券”。其中，“B”中的目标内容B可以根据用户的出行意图进行改变。
值得说明的是，上述目标信息的内容仅用于示例性说明，在实际实施例中，开发人员还可以根据实际业务需要设置为其它形式，本实施例对此不进行限定。
由上述描述可知，本实施例通过根据用户的打车订单，确定司机的接驾时间相关信息以及用户的出行意图，并当接驾时间相关信息满足预设条件时，向所述用户推送与所述出行意 图关联的目标信息，由于当接驾时间相关信息满足预设条件时，判断用户可能取消当前订单，此时向用户推送目标信息，若用户对推送的目标信息感兴趣，则可能选择保留当前的打车订单，可以提升用户保留打车订单的概率，进而提高打车平台的成单率，避免因用户取消订单而浪费司机时间，提升用户和司机双方的用户体验。
图2是本申请第二示例性实施例示出的一种推送信息的方法的流程图；该实施例可以用于打车平台的服务端(例如，一台服务器和多台服务器组成的服务器集群等)。如图2所示，该方法包括步骤S201-S203：
在步骤S201中，根据用户的打车订单，确定所述用户的上车点、对应的关联信息以及用户的出行意图。
在一实施例中，服务端接收到用户的打车订单后，可以确定该打车订单中的上车点以及该打车订单对应的关联信息；同时，还可以确定用户的出行意图(参见下述图6所示实施例，在此先不进行详述)。
在一实施例中，上述关联信息可以包括以下一项或多项：路况、天气、司机定位信息、司机接驾轨迹、司机接驾速度以及司机驾驶习惯等。
在步骤S202中，根据所述上车点和所述关联信息确定所述司机的接驾时间相关信息。
在一实施例中，当确定用户的上车点以及对应的关联信息后，可以根据该上车点和关联信息确定所述司机的接驾时间相关信息。在一实施例中，根据用户的上车点、关联信息中的路况以及司机定位信息确定司机的接驾时间相关信息。
在一实施例中，上述接驾时间相关信息可以由开发人员根据实际业务需要进行设置，如设置为接驾时间、接驾超时情况等，具体还可以参见下述图3、图4所示实施例，在此先不进行详述。
在步骤S203中，若所述接驾时间相关信息满足预设条件，则向所述用户推送与所述出行意图关联的目标信息。
其中，步骤S203的相关解释和说明可以参见上述实施例，在此不进行赘述。
由上述描述可知，本实施例通过根据用户的打车订单，确定所述用户的上车点、对应的关联信息以及用户的出行意图，并根据所述上车点和所述关联信息确定所述司机的接驾时间相关信息，可以实现准确地确定接驾时间相关信息，为后续基于该接驾时间相关信息向用户推送目标信息提供准确依据，实现提高打车平台的成单率的目的。
图3是本申请第三示例性实施例示出的一种推送信息的方法的流程图；该实施例可以用于打车平台的服务端(例如，一台服务器和多台服务器组成的服务器集群等)。如图3所示， 该方法包括步骤S301-S303：
在步骤S301中，根据用户的打车订单，确定所述用户的上车点、对应的关联信息以及用户的出行意图。
其中，步骤S301的解释和说明可以参见上述实施例，在此不进行赘述。
在步骤S302中，根据所述上车点和所述关联信息确定所述司机的接驾时间。
在一实施例中，当服务端接收到用户发送的打车订单后，可以根据所述打车订单中的上车点，以及路况、天气、司机定位信息、司机接驾轨迹、司机接驾速度以及司机驾驶习惯等关联信息预估司机的接驾时间。
值得说明的是，除上述根据上车点和关联信息确定司机的接驾时间之外，开发人员还可以根据实际业务需要选取本领域技术人员熟知的其他方法预测司机的接驾时间，且预测的接驾时间同样适用于后续步骤，本实施例对此不进行限定。
在步骤S303中，若所述接驾时间大于或等于预设的接驾时间阈值，则向所述用户推送与所述出行意图关联的目标信息。
在一实施例中，上述预设的接驾时间阈值可以由开发人员根据实际业务需要进行设置，如设置为20分钟、30分钟等，本实施例对此不进行限定。
在一实施例中，当预估司机的接驾时间后，可以将该预估的接驾时间与上述预设的接驾时间阈值进行对比，若所述接驾时间大于或等于预设的接驾时间阈值，则可以向所述用户推送与所述出行意图关联的目标信息。由上述描述可知，本实施例通过根据用户的打车订单确定司机的接驾时间，并在接驾时间大于或等于预设的接驾时间阈值时，向所述用户推送与所述用户的出行意图关联的目标信息，由于在确定司机的接驾时间过长时，判断用户可能取消订单，在此情况下发送与用户的出行意图关联的目标信息，用户出于获取目标信息对应的目标内容的目的，可能选择保留打车订单，因而可以提升用户保留打车订单的概率，提高打车平台的成单率，避免因用户取消订单而浪费司机时间，提升用户和司机双方的用户体验。
图4是本申请第四示例性实施例示出的一种推送信息的方法的流程图；该实施例可以用于打车平台的服务端(例如，一台服务器和多台服务器组成的服务器集群等)。
如图4所示，该方法包括步骤S401-S403：
在步骤S401中，根据用户的打车订单，确定所述用户的上车点、对应的关联信息以及用户的出行意图。
其中，步骤S401的解释和说明可以参见上述实施例，在此不进行赘述。
在步骤S402中，将所述上车点和所述关联信息输入到预先构建的决策树模型中，得到 用于表征所述司机接驾是否会超时的预测结果。
在一实施例中，服务端还可以将所述上车点和所述关联信息输入到预先构建的决策树模型中，得到用于表征所述司机接驾是否会超时的预测结果。
在一实施例中，决策树模型可以包括但不限于司机的历史行驶距离、司机历史平均接驾时间、司机历史超时率等特征，利用这些特征，通过输入用户的上车点以及对应的关联信息，该决策树模型能够预测司机到达所述上车点所需的接驾时间是否会超过接驾时间阈值，从而得到用于表征所述司机到达所述上车点所需的接驾时间是否会超过所述接驾时间阈值的预测结果。此外该决策树模型还可以被预先构建并存储在打车平台的服务端。
值得说明的是，可以利用本领域技术人员熟知的决策树模型的构建方法来构建上述决策树模型，本实施例对此不进行限定。
在另一实施例中，服务端还可以根据打车订单中的上车点，以及对应的关联信息确定初始接驾时间。进一步地，在上述司机接驾过程中，可以根据司机已行驶路程对应的行驶时间关联信息实时预测的司机的当前接驾时间，进而将该当前接驾时间与上述初始接驾时间进行比较，以得到接驾是否会超时的预测结果。
值得说明的是，除了上述根据决策树模型或者根据当前接驾时间与初始接驾时间的比较结果确定接驾是否会超时的预测结果之外，开发人员还可以根据实际业务需要选取本领域技术人员熟知的其他方法预测司机接驾是否会超时，本实施例对此不进行限定。
在步骤S403中，若所述预测结果表征所述司机接驾会超时，则向所述用户推送与所述出行意图关联的目标信息。
在一实施例中，当得到用于表征所述司机接驾是否会超时的预测结果后，可以判断该预测结果是否表征司机接驾会超时，若是，则向所述用户推送与所述出行意图关联的目标信息。
在另一实施例中，若服务端得到的预测结果表征所述司机接驾会超时，还可以进一步确定超时的时长占上述确定的接驾时间的比例是否大于或等于预设比例阈值，或，确定超时的时长是否大于或等于预设超时时长阈值，以确保在超时情况会对用户造成不良影响时，再向用户推送上述目标信息。换言之，若超时时间较短(如，仅超时几秒钟)，即该超时的时长占接驾时间的比例小于预设比例阈值，或，超时的时长小于预设超时时长阈值，则可以判定超时情况不会对用户造成不良影响，因而不必向用户推送目标信息。
进一步地，当确定超时的时长占所述接驾时间的比例大于或等于预设比例阈值，或，超时的时长大于或等于预设超时时长阈值时，可以向所述用户推送与所述出行意图关联的目标信息。
由上述描述可知，本实施例通过将所述用户发送的打车订单中的上车点以及所述关联信息输入到预先构建的决策树模型中，得到用于表征所述司机接驾是否会超时的预测结果，并当所述预测结果满足上述预设条件时，向所述用户推送与所述用户的出行意图关联的目标信息，由于在确定司机接驾会超时并且超时时长较长时，判断用户可能取消订单，在此情况下发送与用户的出行意图关联的目标信息，用户出于获取目标信息对应的目标内容的目的，可能选择保留打车订单，因而可以提升用户保留打车订单的概率，提高打车平台的成单率，避免因用户取消订单而浪费司机时间，提升用户和司机双方的用户体验。
图5是本申请第五示例性实施例示出的一种推送信息的方法的流程图；该实施例可以用于打车平台的服务端(例如，一台服务器和多台服务器组成的服务器集群等)。如图5所示，该方法包括步骤S501-S508：
在步骤S501中，确定所述用户的上车点、对应的关联信息以及用户的出行意图。
在步骤S502中，将所述上车点和所述关联信息输入到预先构建的决策树模型中，得到用于表征所述司机接驾是否会超时的预测结果。
在步骤S503中，确定预测结果是否表征所述司机接驾会超时：若是，则可以执行步骤S504-S507以及步骤S508。
在步骤S504中：获取所述司机接驾过程中的、已行驶路程对应的多个关联信息。
在一实施例中，司机在接驾过程中，司机的终端设备会将已行驶路程以及对应的多个关联信息上报给服务端，进而服务端可以获取该已行驶路程对应的多个关联信息。
在步骤S505中，计算每个所述关联信息对所述已行驶路程的预计行驶时间的第一贡献度，以及对所述已行驶路程的实际行驶时间的第二贡献度。
其中，所述预计行驶时间根据所述已行驶路程以及生成所述打车订单时的所述打车订单的多个关联信息进行确定。
在一实施例中，服务端在确定司机当前的已行驶路程时，可以计算每个所述关联信息对该已行驶路程的预计行驶时间的第一贡献度，以及，计算每个所述关联信息对所述已行驶路程的实际行驶时间的第二贡献度。
值得说明的是，可以使用本领域技术人员熟知的贡献度的计算方法计算每个所述关联信息对已行驶路程的预计行驶时间或实际行驶时间的贡献度，本实施例对此不进行限定。
在步骤S506中，将所述第二贡献度与所述第一贡献度之间差值最大的前N个关联信息确定为接驾会超时的原因。
其中，N为预设的正整数，如1、2或3等。
在一实施例中，当计算每个所述关联信息对所述已行驶路程的预计行驶时间的第一贡献度，以及，对所述已行驶路程的实际行驶时间的第二贡献度后，可以将所述第二贡献度与所述第一贡献度之间差值最大的前N个关联信息确定为接驾会超时的原因。
举例来说，若N为1，且每个所述关联信息对所述已行驶路程的预计行驶时间的第一贡献度，以及对所述已行驶路程的实际行驶时间的第二贡献度如下表一所示：
表一
Figure PCTCN2019098880-appb-000001
由上表一可知，第二贡献度与第一贡献度之间差值最大的1个关联信息为“路况”，因而可以将“路况”确定为接驾会超时的原因。
值得说明的是，上述贡献度的数值仅用于示例性说明，本实施例对此不进行限定。
在步骤S507中，根据所述接驾会超时的原因生成所述说明信息，并向所述用户进行推送。
在一实施例中，当确定上述接驾会超时的原因后，可以根据该接驾会超时的原因生成所述说明信息，进而将该说明信息推送给上述用户。
在步骤S508中，向所述用户推送与所述出行意图关联的目标信息。
值得说明的是，步骤S507和S508的执行顺序不做限定，在实际实施中，开发人员可以根据业务需要对上述目标信息和说明信息进行分别推送，或者，可以将说明信息作为目标信息的一部分进行推送，本实施例对此不进行限定。
其中，步骤S501-S503、S508的解释和说明可以参见上述实施例，在此不进行赘述。
由上述描述可知，本实施例通过获取所述司机接驾过程中的、已行驶路程对应的多个关联信息，并计算每个所述关联信息对所述已行驶路程的预计行驶时间的第一贡献度，以及对所述已行驶路程的实际行驶时间的第二贡献度，进而将所述第二贡献度与所述第一贡献度之间差值最大的前N个关联信息确定为接驾会超时的原因，可以准确的确定司机接驾会超时的原因，进而向用户推送包含该接驾会超时的原因的说明信息，以使用户知悉接驾超时原因，提升用户保留打车订单的概率，提高打车平台的成单率，避免因用户取消订单而浪费司机时间，提升用户和司机双方的用户体验。
图6是本申请第六示例性实施例示出的一种推送信息的方法的流程图；该实施例可以用 于打车平台的服务端(例如，一台服务器和多台服务器组成的服务器集群等)。
如图6所示，该方法包括步骤S601-S603：
在步骤S601中，根据用户的打车订单，确定司机的接驾时间相关信息以及用户的出行意图。
在步骤S602中，若所述接驾时间相关信息满足预设条件，则向所述用户推送与所述出行意图关联的目标信息。
其中，步骤S601-S602的解释和说明可以参见上述实施例，在此不进行赘述。
在步骤S603中，若接收到所述用户响应于所述目标信息发送的继续等车指示，则向所述用户推送与所述目标信息对应的目标内容。
在一实施例中，上述继续等车指示可以由用户通过点击目标信息中设置的“继续等车选项”或“保留打车订单”选项来发送。
举例来说，当接收到所述用户发送的取消打车订单的请求后，可以向用户发送包含“保留打车订单”选项的目标信息，进而当用户点击该“保留打车订单”选项后，向所述用户推送与所述目标信息对应的目标内容。
同理，当未接收到所述用户发送的取消打车订单的请求，但已确定接驾时间较长，或，司机接驾会超时且超时时间较长，则可以向用户发送包含“继续等车选项”选项的目标信息，进而当用户点击该“继续等车选项”选项后，向所述用户推送与所述目标信息对应的目标内容。
在一实施例中，上述目标内容可以由开发人员根据实际业务需要进行设置，如设置为优惠券、活动信息、景点介绍、游玩攻略以及社交话题等，本实施例对此不进行限定。
值得说明的是，若某些用户在接收到与上述目标信息对应的目标内容后再进行了取消订单的操作，则可以锁定该目标内容，使其不可用或失效，以防止用户非法获取目标内容，给平台造成损失。
由上述描述可知，本实施例通过当接收到所述用户响应于所述目标信息而发送的继续等车指示时，向用户推送与所述目标信息对应的目标内容，可以对选择保留订单或选择继续等车的用户进行奖励，提升用户的体验。
图7是本申请一示例性实施例示出的如何确定用户的出行意图的流程图；本实施例在上述实施例的基础上，以如何确定用户的出行意图为例进行示例性说明。如图7所示，步骤S101中确定用户的出行意图，可以包括以下步骤S701-S703：
在步骤S701中，确定所述用户的上车点、目的地以及对应的关联信息。
在一实施例中，当服务端接收到用户发送的打车订单时，可以确定所述用户的上车点、目的地以及对应的关联信息。
在步骤S702中，根据所述上车点、所述目的地以及所述关联信息计算所述用户的预计到达时间。
在一实施例中，上述预计达到时间的精确度可以由开发人员根据实际业务需要进行设置，如设置为精确到小时、分钟、秒钟等，本实施例对此不进行限定。
在一实施例中，可以预先根据样本数据构建用于确定用户的预计到达时间的第一神经网络模型。用于构建第一神经网络的样本数据包括司机的历史行驶数据。
在一实施例中，服务端可以将所述上车点、所述目的地以及当前的关联信息输入到预先构建的第一神经网络模型中，得到所述用户的预计到达时间。
值得说明的是，基于预先构建的神经网络模型以及上车点、所述目的地以及当前的关联信息预测用户的预计到达时间，可以提高预计到达时间的准确率，进一步提升出行意图预测的准确性。
在步骤S703中，根据所述预计到达时间和所述目的地预测用户的出行意图。
在一实施例中，当确定用户的预计达到时间和目的地后，可以根据该预计到达时间和目的地预测用户的出行意图。
举例来说，若用户的预计达到时间为PM 8:00(即，非工作时间)，而目的地为“电影院”，则可以根据该时间和地点信息预测用户的出行意图为“看电影”。
在一实施例中，根据所述预计到达时间和所述目的地预测用户的出行意图的方式还可以参见下述图8所示实施例，在此先不进行详述。
由上述描述可知，本实施例通过根据所述上车点、所述目的地以及所述关联信息计算所述用户的预计到达时间，并根据所述预计到达时间和所述目的地预测用户的出行意图，可以实现准确地预测用户的出行意图，进而可以提高后续基于出行意图确定关联的目标信息的准确性。
图8是本申请一示例性实施例示出的如何根据用户画像、预计到达时间以及POI(point of interest)确定用户的出行意图的流程图；本实施例在上述实施例的基础上，以如何根据用户画像、预计到达时间以及POI确定用户的出行意图为例进行示例性说明。如图8所示，上述步骤S603中根据所述预计到达时间和所述目的地预测用户的出行意图，可以包括以下步骤S801-S804：
在步骤S801中，获取所述用户的用户画像。
在一实施例中，服务端可以预先获取用户的用户画像，或者，在计算所述用户的预计到达时间后，获取用户的用户画像。
其中，用户画像又称用户角色，是一种勾画目标用户、联系用户诉求与设计方向的有效工具。
简而言之，用户画像是根据用户社会属性、生活习惯和消费行为等信息而抽象出来的一个标签化的用户模型。构建用户画像的核心工作即是给用户贴“标签”，而标签是通过对用户信息分析而来的高度精炼的特征标识。
举例来说，如果用户经常购买一些玩具，那么用户画像服务端可以根据玩具购买情况给用户打上标签“有孩子”，甚至还可以判断出用户孩子的大概年龄，贴上“有5-10岁的孩子”的标签，而集和所有给该用户贴的标签，就构成了该用户的用户画像，即可以通过用户画像判断用户是什么样的人。
值得说明的是，上述用户画像的获取方式还可以参见本领域技术人员熟知方式，本实施例对此不进行限定。
在步骤S802中，确定以所述目的地为中心的预设区域。
在一实施例中，当确定打车订单中的目的地后，可以进一步确定该目的地为中心的预设区域。
在一实施例中，上述预设区域的大小可以由开发人员根据实际业务需求进行划分，如划分为方圆1km、2km等，本实施例对此不进行限定。
在步骤S803中，查询所述预设区域内的至少一个兴趣点POI。
在一实施例中，当确定以所述目的地为中心的预设区域，可以基于第三方地图库，查询预设区域内的至少一个兴趣点POI。
在一实施例中，上述POI可以为电子地图上以气泡图标显示的地点，如景点、政府机构、公司、商场、饭馆等。
在步骤S804中，将所述用户画像、所述预计到达时间以及所述至少一个POI的活动信息或种类输入到预先构建的第二神经网络模型中，得到所述用户的出行意图。
在一实施例中，当确定预设区域内的至少一个兴趣点POI后，可以确定上述至少一个兴趣点POI的活动信息(如，电影场次、商场促销活动)，或，确定上述至少一个兴趣点POI的种类(如，居住类、工作类、商业类、娱乐类、旅游类以及学习类等)。
在一实施例中，可以预先根据样本数据构建用于确定用户的出行意图的第二神经网络模型。
在一实施例中，当确定所述用户画像、所述预计到达时间以及所述至少一个POI的活动信息或种类后，可以将这些信息输入到预先构建的第二神经网络模型中，得到所述用户的出行意图。
由上述描述可知，本实施例通过获取所述用户的用户画像，并确定以所述目的地为中心的预设区域，然后查询所述预设区域内的至少一个兴趣点POI，并将所述用户画像、所述预计到达时间以及所述至少一个POI的活动信息或种类输入到预先构建的第二神经网络模型中，得到所述用户的出行意图，可以实现准确地预测用户的出行意图，进而可以提高后续基于出行意图确定关联的目标信息的准确性。
图9是本申请第六示例性实施例示出的一种推送信息的方法的流程图；该实施例可以用于打车平台的服务端(例如，一台服务器和多台服务器组成的服务器集群等)。
如图9所示，该方法包括步骤S901-S903：
在步骤S901中，根据用户的打车订单，确定司机的接驾时间相关信息以及用户的出行意图。
在步骤S902中，若所述接驾时间相关信息满足预设条件，则向用户推送与所述出行意图关联的目标信息。
其中，步骤S901-S902的相关解释和说明可以参见上述实施例，在此不进行赘述。
在步骤S903中，确定所述目标信息是否符合所述用户的需求：若是，则结束推送信息流程；否则，基于多轮交互问答方式，重新确定所述用户的出行意图，进而基于重新确定的出行意图再次向用户推送关联的目标信息。在一实施例中，若在向所述用户推送所述目标信息之后的预设时间段内未接收到所述用户的响应，可以确定该目标信息不符合用户的需求。
在一实施例中，若服务端接收到推送的目标信息不符合用户需求的反馈信息，则可以基于多轮交互问答方式，重新确定用户的出行意图。
在一实施例中，上述重新确定的用户的出行意图还可以用于优化上述构建的第二神经网络，以提升第二神经网络预测用户的出行意图的准确性。
在一实施例中，用户可以通过点击打车客户端的用户界面上设置“满意/不满意”选项的方式向服务端发送上述反馈信息。
在一实施例中，上述多轮交互问答的具体内容可以由开发人员根据实际业务需要进行设置，如设置为“请问您本次出行的目的是旅游吗？”，“请问您本次出行的目的是工作吗？”等，本实施例对此不进行限定。
由上述描述可知，本实施例通过当所述目标信息不符合所述用户的需求时，基于多轮交 互问答方式，重新确定所述用户的出行意图，并查询与重新确定的出行意图关联的目标信息，并向所述用户进行推送，可以进一步提高预测用户的出行意图的准确性，进而可以提高基于出行意图确定关联的目标信息的准确性。
与前述方法实施例相对应，本申请还提供了相应的装置的实施例。
图10是本申请一示例性实施例示出的一种推送信息的装置的结构图；如图10所示，该装置可以包括：信息及意图确定模块110以及目标信息推送模块120，其中：
信息及意图确定模块110，用于根据用户的打车订单，确定司机的接驾时间相关信息以及用户的出行意图；
目标信息推送模块120，用于当所述接驾时间相关信息满足预设条件时，向所述用户推送与所述出行意图关联的目标信息。
在一实施例中，信息及意图确定模块110还用于根据用户的打车订单和司机对该打车订单的响应，确定该司机的接驾时间相关信息。
由上述描述可知，本实施例根据用户的打车订单，确定司机的接驾时间相关信息以及用户的出行意图，并当所述接驾时间相关信息满足预设条件时，向所述用户推送与所述出行意图关联的目标信息，由于当接驾时间相关信息满足预设条件时，判断用户可能取消当前订单，此时向用户推送目标信息，若用户对推送的目标信息感兴趣，则可能选择保留当前的打车订单，可以提升用户保留打车订单的概率，进而提高打车平台的成单率，避免因用户取消订单而浪费司机时间，提升用户和司机双方的用户体验。
图11是本申请又一示例性实施例示出的一种推送信息的装置的结构图；其中，信息及意图确定模块210和目标信息推送模块220与前述图10所示实施例中的信息及意图确定模块110和目标信息推送模块120的功能相同，在此不进行赘述。
在一实施例中，接驾时间相关信息满足预设条件，可以包括：
所述接驾时间相关信息的数值满足预设的数值条件；或，
所述接驾时间相关信息的内容满足预设的内容条件；或，
向所述用户发送所述接驾时间相关信息后，接收到所述用户响应于所述接驾时间相关信息发送的取消订单的请求。
在一实施例中，信息及意图确定模块210，可以包括：相关信息确定单元211；
相关信息确定单元211可以用于：
根据用户的打车订单，确定所述用户的上车点以及对应的关联信息；
根据所述上车点和所述关联信息确定所述司机的接驾时间相关信息。
在一实施例中，相关信息确定单元211还可以用于：
根据所述上车点和所述关联信息确定所述司机的接驾时间；
在此基础上，接驾时间相关信息的数值满足预设的数值条件，可以包括：
所述接驾时间大于或等于预设的接驾时间阈值。
在另一实施例中，相关信息确定单元211还可以用于：
将所述上车点和所述关联信息输入到预先构建的决策树模型中，得到用于表征所述司机接驾是否会超时的预测结果；
在此基础上，接驾时间相关信息的内容满足预设的内容条件，可以包括：
所述预测结果表征所述司机接驾会超时；以及，
超时的时长占所述接驾时间的比例大于或等于预设比例阈值，或，超时的时长大于或等于预设超时时长阈值。
在一实施例中，所述装置还可以包括：说明信息生成模块230；
说明信息生成模块230，还可以包括：
关联信息获取单元231，用于获取所述司机接驾过程中的、已行驶路程对应的多个关联信息；
贡献度计算单元232，用于计算每个所述关联信息对所述已行驶路程的预计行驶时间的第一贡献度，以及对所述已行驶路程的实际行驶时间的第二贡献度；
超时原因确定单元233，用于将所述第二贡献度与所述第一贡献度之间差值最大的前N个关联信息确定为接驾会超时的原因，N为预设的正整数；
说明信息生成单元234，用于根据所述接驾会超时的原因生成说明信息，并向所述用户进行推送。
在一实施例中，所述装置还可以包括：
目标内容推送模块240，用于当接收到所述用户响应于所述目标信息发送的继续等车指示时，向所述用户推送所述目标信息对应的目标内容。
在一实施例中，信息及意图确定模块210还可以包括：出行意图确定单元212；
出行意图确定单元212，可以用于：
确定所述用户的上车点、目的地以及对应的关联信息；
根据所述上车点、所述目的地以及所述关联信息计算所述用户的预计到达时间；
根据所述预计到达时间和所述目的地预测用户的出行意图。
在一实施例中，出行意图确定单元212，还可以用于：
获取所述用户的用户画像；
确定以所述目的地为中心的预设区域；
查询所述预设区域内的至少一个兴趣点；
将所述用户画像、所述预计到达时间以及所述至少一个POI的活动信息或种类输入到预先构建的神经网络模型中，得到所述用户的出行意图。
在一实施例中，信息及意图确定模块210还可以用于若在向所述用户推送所述目标信息之后的预设时间段内未接收到所述用户的响应，重新确定所述用户的出行意图；
在此基础上，目标信息推送模块212还可以用于根据所述接驾时间相关信息与重新确定的出行意图向所述用户推送目标信息。
值得说明的是，上述所有可选技术方案，可以采用任意结合形成本公开的可选实施例，在此不再一一赘述。
本公开的推送信息的装置的实施例可以应用在网络设备上。装置实施例可以通过软件实现，也可以通过硬件或者软硬件结合的方式实现。以软件实现为例，作为一个逻辑意义上的装置，是通过其所在设备的处理器将非易失性存储器中对应的计算机程序指令读取到内存中运行形成的，其中计算机程序用于执行上述图1～图9所示实施例提供的推送信息的方法。从硬件层面而言，如图12所示，为本公开的推送信息的设备的硬件结构图，除了图12所示的处理器、网络接口、内存以及非易失性存储器之外，所述设备通常还可以包括其他硬件，如负责处理报文的转发芯片等等；从硬件结构上来讲该设备还可能是分布式的设备，可能包括多个接口卡，以便在硬件层面进行报文处理的扩展。另一方面，本申请还提供了一种计算机可读存储介质，存储介质存储有计算机程序，计算机程序用于执行上述图1～图9所示实施例提供的推送信息的方法。
对于装置实施例而言，由于其基本对应于方法实施例，所以相关之处参见方法实施例的部分说明即可。以上所描述的装置实施例仅仅是示意性的，其中所述作为分离部件说明的单元可以是或者也可以不是物理上分开的，作为单元显示的部件可以是或者也可以不是物理单元，即可以位于一个地方，或者也可以分布到多个网络单元上。可以根据实际的需要选择其中的部分或者全部模块来实现本申请方案的目的。本领域普通技术人员在不付出创造性劳动的情况下，即可以理解并实施。
本领域技术人员在考虑说明书及实践这里公开的发明后，将容易想到本申请的其它实施方案。本申请旨在涵盖本申请的任何变型、用途或者适应性变化，这些变型、用途或者适应性变化遵循本申请的一般性原理并包括本申请未公开的本技术领域中的公知常识或惯用技术手段。说明书和实施例仅被视为示例性的，本申请的真正范围和精神由下面的权利要求指出。
还需要说明的是，术语“包括”、“包含”或者其任何其他变体意在涵盖非排他性的包含，从而使得包括一系列要素的过程、方法、商品或者设备不仅包括那些要素，而且还包括没有明确列出的其他要素，或者是还包括为这种过程、方法、商品或者设备所固有的要素。在没有更多限制的情况下，由语句“包括一个……”限定的要素，并不排除在包括所述要素的过程、方法、商品或者设备中还存在另外的相同要素。
以上所述仅为本申请的较佳实施例而已，并不用以限制本申请，凡在本申请的精神和原则之内，所做的任何修改、等同替换、改进等，均应包含在本申请保护的范围之内。

Claims (14)

  1. 一种推送信息的方法，包括：
    根据用户的打车订单，确定司机的接驾时间相关信息以及用户的出行意图；
    若所述接驾时间相关信息满足预设条件，则向所述用户推送与所述出行意图关联的目标信息。
  2. 根据权利要求1所述的方法，其特征在于，所述接驾时间相关信息满足预设条件，包括：
    所述接驾时间相关信息的数值满足预设的数值条件；或，
    所述接驾时间相关信息的内容满足预设的内容条件；或，
    向所述用户发送所述接驾时间相关信息后，接收到所述用户响应于所述接驾时间相关信息而发送的取消所述打车订单的请求。
  3. 根据权利要求2所述的方法，其特征在于，根据所述用户的打车订单，确定所述司机的接驾时间相关信息，包括：
    根据用户的打车订单，确定所述用户的上车点以及对应的关联信息；
    根据所述上车点和所述关联信息确定所述司机的接驾时间相关信息。
  4. 根据权利要求3所述的方法，其特征在于，根据所述上车点和所述关联信息确定所述司机的接驾时间相关信息，包括：
    根据所述上车点和所述关联信息确定所述司机的接驾时间；
    所述接驾时间相关信息的数值满足预设的数值条件，包括：
    所述接驾时间大于或等于预设的接驾时间阈值。
  5. 根据权利要求3所述的方法，其特征在于，根据所述上车点和所述关联信息确定所述司机的接驾时间相关信息，包括：
    将所述上车点和所述关联信息输入到预先构建的决策树模型中，得到用于表征所述司机接驾是否会超时的预测结果；
    所述接驾时间相关信息的内容满足预设的内容条件，包括：
    所述预测结果表征所述司机接驾会超时。
  6. 根据权利要求5所述的方法，其特征在于，所述方法还包括：
    获取所述司机接驾过程中的、已行驶路程对应的多个关联信息；
    计算每个所述关联信息对所述已行驶路程的预计行驶时间的第一贡献度，以及对所述已行驶路程的实际行驶时间的第二贡献度；
    将所述第二贡献度与所述第一贡献度之间差值最大的前N个关联信息确定为接驾会超时的原因，N为预设的正整数；
    根据所述接驾会超时的原因生成说明信息，并向所述用户进行推送。
  7. 根据权利要求1所述的方法，其特征在于，所述方法还包括：
    若接收到所述用户响应于所述目标信息发送的继续等车指示，则向所述用户推送所述目标信息对应的目标内容。
  8. 根据权利要求1所述的方法，其特征在于，确定用户的出行意图，包括：
    确定所述用户的上车点、目的地以及对应的关联信息；
    根据所述上车点、所述目的地以及所述关联信息计算所述用户的预计到达时间；
    根据所述预计到达时间和所述目的地预测用户的出行意图。
  9. 根据权利要求8所述的方法，其特征在于，根据所述预计到达时间和所述目的地预测用户的出行意图，包括：
    获取所述用户的用户画像；
    确定以所述目的地为中心的预设区域；
    查询所述预设区域内的至少一个兴趣点；
    将所述用户画像、所述预计到达时间以及所述至少一个兴趣点的活动信息或种类输入到预先构建的神经网络模型中，得到所述用户的出行意图。
  10. 根据权利要求1-9任一项所述的方法，其特征在于，所述方法还包括：
    若在向所述用户推送所述目标信息之后的预设时间段内未接收到所述用户的响应，则重新确定所述用户的出行意图；
    根据所述接驾时间相关信息与重新确定的出行意图向所述用户推送目标信息。
  11. 根据权利要求1所述的方法，其特征在于，根据所述用户的打车订单，确定用户的接驾时间相关信息包括：
    根据所述用户的打车订单和所述司机对所述打车订单的响应，确定所述司机的接驾时间相关信息。
  12. 一种推送信息的装置，其特征在于，包括：
    信息及意图确定模块，用于根据用户的打车订单，确定司机的接驾时间相关信息以及用户的出行意图；
    目标信息推送模块，用于当所述接驾时间相关信息满足预设条件时，向所述用户推送与所述出行意图关联的目标信息。
  13. 一种推送信息的设备，其特征在于，包括存储器、处理器及存储在存储器上并可在处理器上运行的计算机程序，其中，所述处理器执行所述程序时实现上述权利要求1-11任一所述的推送信息的方法。
  14. 一种计算机可读存储介质，其特征在于，所述存储介质存储有计算机程序，所述计算机程序用于执行上述权利要求1-11任一所述的推送信息的方法。
PCT/CN2019/098880 2018-08-14 2019-08-01 推送信息的方法、装置及设备 WO2020034851A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201810924946.5 2018-08-14
CN201810924946.5A CN109146280B (zh) 2018-08-14 2018-08-14 一种推送信息的方法、装置及系统

Publications (1)

Publication Number Publication Date
WO2020034851A1 true WO2020034851A1 (zh) 2020-02-20

Family

ID=64793120

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2019/098880 WO2020034851A1 (zh) 2018-08-14 2019-08-01 推送信息的方法、装置及设备

Country Status (2)

Country Link
CN (1) CN109146280B (zh)
WO (1) WO2020034851A1 (zh)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113590973A (zh) * 2021-08-23 2021-11-02 中国银行股份有限公司 一种数据推送方法、装置及电子设备

Families Citing this family (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109146280B (zh) * 2018-08-14 2021-07-30 北京三快在线科技有限公司 一种推送信息的方法、装置及系统
CN109885765B (zh) * 2019-01-31 2022-02-15 曾国进 一种适用于固定线路交通工具的乘客信息分析推送系统
CN109978197A (zh) * 2019-03-29 2019-07-05 北京三快在线科技有限公司 一种处理订单的方法、装置、设备及存储介质
CN110990714B (zh) * 2019-11-01 2023-05-23 中国联合网络通信集团有限公司 一种用户行为意图预测方法和装置
CN114041129A (zh) * 2019-11-04 2022-02-11 北京嘀嘀无限科技发展有限公司 确定上车点名称的系统和方法
CN111177296B (zh) * 2019-12-30 2022-12-06 科大讯飞股份有限公司 信息推荐方法、装置、电子设备及计算机存储介质
CN112116151A (zh) * 2020-09-17 2020-12-22 北京嘀嘀无限科技发展有限公司 一种接驾时间预估方法和系统
CN113408877A (zh) * 2021-06-07 2021-09-17 北京百度网讯科技有限公司 网约车信息处理方法、装置、设备和计算机存储介质
CN114422580B (zh) * 2021-12-03 2024-02-02 浙江吉利控股集团有限公司 一种信息处理方法、装置、电子设备及存储介质

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US8626637B1 (en) * 2006-09-28 2014-01-07 Gfi Group, Inc. Apparatus, method and system for providing an electronic marketplace to join a trade for credit default swaps and other financial interests, and to deal-by-volume for the interests
CN106776771A (zh) * 2016-11-10 2017-05-31 百度在线网络技术（北京）有限公司 信息推送方法和装置
CN108009651A (zh) * 2017-08-16 2018-05-08 北京嘀嘀无限科技发展有限公司 订单处理方法、装置、终端设备和计算机可读存储介质
CN109146280A (zh) * 2018-08-14 2019-01-04 北京三快在线科技有限公司 一种推送信息的方法、装置及系统

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US8626637B1 (en) * 2006-09-28 2014-01-07 Gfi Group, Inc. Apparatus, method and system for providing an electronic marketplace to join a trade for credit default swaps and other financial interests, and to deal-by-volume for the interests
CN106776771A (zh) * 2016-11-10 2017-05-31 百度在线网络技术（北京）有限公司 信息推送方法和装置
CN108009651A (zh) * 2017-08-16 2018-05-08 北京嘀嘀无限科技发展有限公司 订单处理方法、装置、终端设备和计算机可读存储介质
CN109146280A (zh) * 2018-08-14 2019-01-04 北京三快在线科技有限公司 一种推送信息的方法、装置及系统

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113590973A (zh) * 2021-08-23 2021-11-02 中国银行股份有限公司 一种数据推送方法、装置及电子设备

Also Published As

Publication number Publication date
CN109146280B (zh) 2021-07-30
CN109146280A (zh) 2019-01-04

Similar Documents

Publication Publication Date Title
WO2020034851A1 (zh) 推送信息的方法、装置及设备
TWI683272B (zh) 資訊獲取方法、提供方法、裝置及系統、儲存介質
KR102050527B1 (ko) 컴퓨팅 디바이스의 사용자 컨텍스트에 기초한 운송의 자동 예약
US11570276B2 (en) Forecasting requests based on context data for a network-based service
US20190362252A1 (en) Learning user preferences in a conversational system
US9953389B2 (en) System for preemptively navigating drivers to passengers based on passenger device activity
US9003030B2 (en) Detecting relative crowd density via client devices
WO2017181613A1 (zh) 搜索响应方法、装置及系统
CN107657007B (zh) 信息推送方法、装置、终端、可读存储介质及系统
WO2020011030A1 (zh) 拼车方法、拼车路线的推荐方法、装置、介质及电子设备
JP7120790B2 (ja) メッセージと対応するタスクを生成、処理、管理するコンピュータプログラム、及び電子機器
US10623890B1 (en) Event-based location based services
US20190279096A1 (en) Making resource-constrained sequential recommendations
KR102443534B1 (ko) 메시징 서비스 환경에서의 사용자 상황 감지 및 사용자 상황에 기반한 메시징 서비스와의 인터랙션
CN110753078B (zh) 提示方法、装置、电子设备及存储介质
CN113906432A (zh) 使用知识模型对聊天机器人中的自然理解系统的上下文反馈
CN113160607A (zh) 停车位导航方法、装置、电子设备、存储介质及产品
WO2015157487A1 (en) System utilizing location-based data and methods of its use
CN111949859B (zh) 用户画像更新方法、装置、计算机设备及存储介质
US20220292414A1 (en) Dynamic invitation transmission and presentation mode determination for a network-based service
CN112288115B (zh) 生成预约服务信息的方法、装置、设备以及存储介质
CN111242711A (zh) 信息提示方法、装置、电子设备和存储介质
CN112862544A (zh) 对象信息的获取方法、装置以及存储介质
US11144884B2 (en) Contextualized item reminder assitance
US20190279117A1 (en) System and method for providing wait times for taxi queueing areas

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 19850114

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 19850114

Country of ref document: EP

Kind code of ref document: A1