Message pushing method and computer readable storage medium

Abstract

The invention provides a message pushing method and a computer readable storage medium. The server determines the degree information of the first user receiving the to-be-pushed goods source according to at least one of the historical portrait feature of the first user, the first user activeness feature and the matching degree feature of the first user and the to-be-pushed goods source, determines the goods source pushing frequency according to the predicted degree information of the first user receiving the to-be-pushed goods source, and pushes the goods source to the first user according to the goods source pushing frequency. And pushing the to-be-pushed goods source to a terminal device corresponding to the first user under the condition of conforming to the goods source pushing frequency. And after the terminal equipment corresponding to the first user receives the pushed goods source, the pushed goods source is displayed. According to the information of the historical portrait features of the driver, the driver activeness and the matching degree of the driver to the to-be-pushed goods source, the acceptance degree of the driver to the to-be-pushed goods source is determined, so that the goods source pushing frequency is adaptively regulated and controlled, the determined goods source pushing frequency better conforms to the condition of the driver, the driver can quickly find a satisfactory goods source, and the user experience is improved. And the user experience and the conversion efficiency of message pushing are balanced.

Description

Technical Field

[0001] The present disclosure relates to the field of intelligent transportation technology, and in particular to a message push method and a computer-readable storage medium. Background Art

[0002] In the scenario of intelligent transportation, the transportation demand form proposed by the cargo owner needs to be matched with the driver, and the cargo owner and the driver reach an order online for subsequent transportation. The above process can be implemented through a freight application (Application, app), in which the transportation demand form proposed by the cargo owner can be called the source of goods.

[0003] In order to help drivers quickly match suitable cargo sources, freight applications usually push messages. According to the driver's offline status, messages can be pushed to the driver at a preset frequency.

[0004] However, smart transportation scenarios are complex, which can easily disturb inactive users, while push notifications to active users are not timely enough, resulting in low efficiency in drivers taking orders and poor user experience. Summary of the invention

[0005] The present disclosure provides a message push method and a computer-readable storage medium to solve the current problem in intelligent transportation scenarios that messages pushed are not timely enough and drivers are not efficient in accepting orders.

[0006] In a first aspect, the present disclosure provides a message push method, the method comprising:

[0007] Get the delivery source to be pushed;

[0008] Determining information on the degree of acceptance of the to-be-promoted delivery source by the first user based on at least one of a historical portrait feature of the first user, an activity feature of the first user, and a matching feature between the first user and the to-be-promoted delivery source;

[0009] Determining a frequency of pushing the source of goods according to information about the expected degree of acceptance of the source of goods to be pushed by the first user;

[0010] In the case where the supply pushing frequency is met, the supply to be pushed is pushed to the terminal device corresponding to the first user.

[0011] In some embodiments, the historical portrait feature of the first user includes at least one of the following information: the historical arrival volume of the first user, the historical click volume of the first user, the historical click rate of the first user, and the historical click rate per unit time of the first user;

[0012] The historical arrival volume of the first user refers to the quantity of external sources of goods pushed to the first user in the most recent first preset time period;

[0013] The historical click volume of the first user refers to the number of pushed external product sources clicked by the first user in the most recent first preset time period;

[0014] The historical click rate of the first user refers to the ratio of the historical click volume of the first user to the historical reach volume of the first user;

[0015] The historical click-through rate per unit time of the first user refers to the ratio of the number of external sources of goods pushed by the first user to the number of external sources of goods pushed to the first user in each unit time of the most recent first preset time period.

[0016] In some embodiments, the first user activity feature includes at least one of the following information: the current arrival volume of the first user, the current click volume of the first user, the full-scene click volume of the first user, and the duration of the first user's most recent active behavior; the active behavior includes clicking on a source of goods, searching for a source of goods, or opening a freight application;

[0017] The current arrival volume of the first user refers to the quantity of the supply pushed to the first user in the most recent second preset time period; the second preset time period is less than the first preset time period;

[0018] The current click volume of the first user refers to the number of pushed sources of goods clicked by the first user in the most recent second preset time period;

[0019] The full-scenario click volume of the first user refers to the number of sources of goods clicked by the first user in all scenarios within the most recent second preset time period.

[0020] In some embodiments, the matching characteristics between the first user and the delivery source to be pushed include at least one of the following: driver-cargo matching score, empty driving ratio, and driver-cargo matching information corresponding to each freight information; the freight information includes at least one of the following information: vehicle length, vehicle type, load, cargo type, departure place, and destination;

[0021] The driver-cargo matching score is used to indicate the matching degree between the to-be-delivered source and the first user;

[0022] The idle driving ratio refers to the ratio of the idle driving distance of the first user to the transportation distance of the source to be pushed;

[0023] The driver-cargo matching information of each freight information is used to indicate the degree to which each freight information in the to-be-promoted source of goods matches the first user's preference for the corresponding source of goods information.

[0024] In some embodiments, obtaining the source to be pushed includes:

[0025] Determine the frequency of picking up goods from a supply pool according to the login status of the freight application corresponding to the first user; the login status includes an online status and an offline status; the supply pool includes supplies that meet the freight push scenario currently in which the first user is in;

[0026] Obtaining a first source of goods from the source pool at the pickup frequency and according to a preset pickup method;

[0027] When the driver-cargo matching score of the first source of cargo is greater than or equal to the matching score threshold, and the time from the current moment to the last push is greater than or equal to the time threshold, the first source of cargo is determined to be the source of cargo to be pushed; the driver-cargo matching score is used to indicate the score of the degree of matching between the source of cargo to be pushed and the first user.

[0028] In some embodiments, the matching score threshold is determined according to a current login state of the freight application corresponding to the first user and a running state of the freight application corresponding to the first user.

[0029] In some embodiments, the supply pool includes a quick pass pool, a shared pool, and a support pool; obtaining the first supply from the supply pool according to the pickup frequency and a preset pickup method includes:

[0030] At the frequency of picking up goods, the following processing is performed each time the first source of goods is obtained:

[0031] If there is a source of goods in the quick pass pool, the earliest source of goods in the quick pass pool is obtained as the first source of goods; if there is no source of goods in the quick pass pool and the support conditions are not met at present, the source of goods with the highest driver-goods matching score is obtained from the shared pool as the first source of goods; if there is no source of goods in the quick pass pool and the support conditions are currently met, the source of goods with the highest driver-goods matching score is obtained from the support pool as the first source of goods.

[0032] In some embodiments, the method further comprises:

[0033] After receiving the push information that does not meet the value condition and the timeliness condition, the push information is placed in the quick pass pool, the sharing pool or the support pool according to the preset pool entry method;

[0034] After receiving the push information that meets the value condition or the time limit condition, the push information that meets the value condition or the time limit condition is pushed to the terminal device.

[0035] In a second aspect, the present disclosure provides a message push method, the method comprising:

[0036] The terminal device receives a delivery source to be pushed pushed by a server, wherein the delivery source to be pushed is determined by the server based on at least one of the first user's historical profile feature, the first user's activity feature, and the first user's matching feature with the delivery source to be pushed, to determine the delivery source push frequency based on the first user's expected acceptance of the delivery source to be pushed; and is pushed in accordance with the delivery source push frequency; the first user is a logged-in user of a freight application in the terminal device;

[0037] The terminal device displays the source to be pushed.

[0038] In a third aspect, the present disclosure provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the method described in the first aspect.

[0039] The message push method and computer-readable storage medium provided by the embodiments of the present disclosure may have multiple users in the freight application program. Therefore, the server may need to maintain multiple users and push the source of goods message to multiple users. The source of goods message is pushed to each user separately: the server determines the degree of acceptance of the source of goods to be pushed by the first user based on at least one of the historical portrait feature of the first user, the activity feature of the first user, and the matching feature between the first user and the source of goods to be pushed, and fully considers the situation of the source of goods to be pushed and the first user, so that the degree of acceptance of the source of goods to be pushed by the first user is more accurate. The server determines the source of goods push frequency based on the expected degree of acceptance of the first user to be pushed. The determined source of goods push frequency is more in line with the acceptance of the first user. In the case of meeting the source of goods push frequency, the source of goods to be pushed is pushed to the terminal device corresponding to the first user. After the terminal device corresponding to the first user receives the pushed source of goods, it displays the pushed source of goods. Therefore, based on the driver's historical portrait characteristics, the driver's activity level and the driver's matching degree with the pushed delivery source, the driver's acceptance degree of the pushed delivery source is determined, so as to adaptively adjust the delivery source push frequency. The determined delivery source push frequency is more in line with the driver's situation, and freight messages are adaptively pushed at this delivery source push frequency, so that the pushed delivery source does not disturb the driver and meets the driver's needs for timely receiving messages. The driver can quickly find a satisfactory delivery source, which improves the driver's order acceptance efficiency, thereby improving the efficiency of the shipper and the driver in reaching an order, and better balancing the user experience and the reach and conversion efficiency of message push. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] Figure 1 An architecture diagram of a message push system provided in an embodiment of the present disclosure;

[0041] Figure 2An interactive schematic diagram of a message push method provided in an embodiment of the present disclosure. DETAILED DESCRIPTION

[0042] Exemplary embodiments will be described in detail herein, examples of which are shown in the accompanying drawings. When the following description refers to the drawings, the same numbers in different drawings represent the same or similar elements unless otherwise indicated. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present disclosure. Instead, they are merely examples of devices and methods consistent with some aspects of the present disclosure as detailed in the appended claims.

[0043] In the present disclosure, "at least one" refers to one or more, and "plurality" refers to two or more. "And / or" describes the association relationship of associated objects, indicating that three relationships may exist. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone, where A and B can be singular or plural. The character " / " generally indicates that the objects associated before and after are in an "or" relationship. "At least one of the following" or similar expressions refers to any combination of these items, including any combination of single items or plural items. For example, at least one of a alone, b alone, or c alone can represent: a alone, b alone, c alone, a and b in combination, a and c in combination, b and c in combination, or a, b, and c in combination, where a, b, and c can be single or multiple. In addition, the terms "first" and "second" are used for descriptive purposes only and cannot be understood as indicating or implying relative importance.

[0044] The terms "connected" and "connected" should be understood in a broad sense. For example, the "connected" or "connected" of a circuit structure may refer to not only a physical connection, but also an electrical connection or a signal connection. For example, it may be a direct connection, i.e. a physical connection, or it may be an indirect connection through at least one intermediate element, as long as the circuit is connected. It may also be the internal connection of two elements. In addition to signal connection through a circuit, signal connection may also refer to signal connection through a media medium, such as radio waves. For those of ordinary skill in the art, the specific meanings of the above terms in this disclosure may be understood according to specific circumstances.

[0045] In the intelligent transportation scenario, the cargo owner can fill in the freight request information on the freight application of the terminal device. The freight request information may include the loading place information, the unloading place information, the required vehicle type and other information. The freight application of the terminal device used by the cargo owner can be called the cargo owner's end. The cargo owner's end sends the freight request information as a source of goods to the corresponding server. The driver can also perform operations such as searching on the freight application of the terminal device. The freight application of the terminal device used by the driver can be called the driver's end. The server sends the current source of goods to the driver's end for display. After seeing the displayed source of goods, the driver can accept the order, and the cargo owner and the driver can sign the order for subsequent transportation.

[0046] This application provides a message push method that can be applied to a message push system. Figure 1 , Figure 1 The present invention provides an architecture diagram of a message push system according to an embodiment of the present invention, wherein the message push system includes a server 102 and a terminal device 101. The server 102 and the terminal device 101 are connected via a network. The server 102 may be a single server or a server cluster consisting of two or more servers. The terminal device 101 may include but is not limited to a terminal device, a terminal, a user equipment (UE), a mobile station, a mobile terminal, etc. The terminal device 101 may specifically be a mobile phone, a tablet computer, a computer with wireless transceiver function, a wearable device, a robot, a smart home device, etc.

[0047] A freight application can be installed in the terminal device 101, and the user can log in to the freight application, so that the server 102 corresponds the first user to the terminal device 101. The server 102 can push corresponding push information to the terminal device 101. Unlike the e-commerce application, in the intelligent transportation scenario, the message pushed by the freight application is usually the source of goods. The driver has the need to find the source of goods or listen to orders during transportation. Therefore, the driver pays more attention to the messages pushed by the freight application. Usually, if the first user is using the freight application, and the freight application is at the forefront of the terminal device 101, the pushed source of goods can be displayed through the display control of the freight application of the freight application; if the first user logs in to the freight application, but the freight application runs in the background of the terminal device 101, the source of goods can be pushed in the form of a notification in the notification bar.

[0048] In the process of message push, in order to increase the number of active users and the amount of fulfillment, the server 102 will push more messages to activate users. Obviously, if the sending volume is too high, it will have a negative impact: for example, users feel disturbed and will cancel subscriptions, turn off notification permissions, or even uninstall freight applications. In addition, if the terminal device detects that the freight application pushes too many messages, it may regard the freight application as a potential spammer and begin to block the reach of messages. In addition, compared with other advertising messages, drivers pay more attention to messages pushed by freight applications, and the messages pushed by freight applications also have a certain timeliness. Therefore, a certain frequency of message push is also required. In summary, the messages pushed by freight applications need to meet the driver's needs to receive messages in a timely manner without disturbing the driver.

[0049] The present disclosure provides a message push method, wherein the server determines the degree of acceptance of the first user to the delivery source to be pushed according to at least one of the historical portrait characteristics of the first user, the first user activity characteristics and the matching characteristics of the first user and the delivery source to be pushed, determines the frequency of pushing the source of goods according to the expected degree of acceptance of the first user to the delivery source to be pushed, and pushes the delivery source to be pushed to the terminal device corresponding to the first user in accordance with the frequency of pushing the source of goods. After receiving the pushed source of goods, the terminal device corresponding to the first user displays the pushed source of goods. Thus, according to the historical portrait characteristics of the driver, the driver activity and the information of the driver's matching degree with the delivery source to be pushed, the driver's acceptance degree of the delivery source to be pushed is determined, so as to adaptively adjust the frequency of pushing the source of goods, and the determined frequency of pushing the source of goods is more in line with the driver's situation, and the freight message is adaptively pushed with the frequency of pushing the source of goods, so that the pushed source of goods meets the driver's need to receive the message in time without disturbing the driver, and the driver can quickly find a satisfactory source of goods, thereby improving the efficiency of the driver's order acceptance, thereby improving the efficiency of the cargo owner and the driver in reaching an order, and better balancing the user experience and the efficiency of the contact conversion of the message push.

[0050] See also Figure 2 , Figure 2 This is an interactive diagram of a message push method provided by an embodiment of the present disclosure. The method provided by this embodiment can be applied to a message push system, which can be the above-mentioned Figure 1 The message push system in the embodiment shown. Figure 2 As shown, the method provided in this embodiment may include the following steps 201 to 205.

[0051] Step 201: The server obtains the source of the items to be pushed.

[0052] The supply to be pushed refers to the supply that meets the message push scenario that the current first user is in and needs to be pushed to the terminal device corresponding to the first user.

[0053] There are many ways for the server to obtain the source of goods to be pushed. The source of goods to be pushed can be obtained after the source of goods to be pushed is generated. It is also possible that multiple sources of goods are generated at the same time, and the server can obtain one of the sources of goods as the source of goods to be pushed according to a preset rule. The present disclosure does not limit the way in which the server obtains the source of goods to be pushed.

[0054] Step 202: The server determines information on the degree of acceptance of the first user to be pushed to the delivery source based on at least one of the first user's historical portrait feature, the first user's activity feature, and the matching feature between the first user and the delivery source to be pushed.

[0055] The historical profile feature of the first user is used to indicate the first user's acceptance of the pushed supply information in the past. Exemplarily, the historical profile feature of the first user may include the first user's previous processing behavior information on the pushed supply information.

[0056] The first user activity feature is used to indicate the first user's current acceptance of the supply of the freight application. Exemplarily, the first user activity feature may include the first user's processing behavior information on the supply of the current freight application.

[0057] The matching feature between the first user and the delivery source to be pushed is used to indicate the matching degree between the preference of the first user and the delivery source to be pushed.

[0058] Furthermore, the information on the degree to which the first user accepts the delivery source to be pushed may be an inferred probability value of the first user accepting the delivery source to be pushed.

[0059] Furthermore, the server may input at least one of the historical portrait feature of the first user, the activity feature of the first user, and the matching feature between the first user and the delivery source to be pushed into the push acceptance model to obtain information on the degree of acceptance of the delivery source to be pushed by the first user.

[0060] Among them, the push acceptance model can be a model established based on machine learning. There can be many forms of the push acceptance model. In one possible implementation, the acceptance model can be a binary classification model based on machine learning, and the classification label is whether the first user clicks or trades the source of goods to be pushed at the current moment, wherein click refers to the click operation on the source display control, and trade refers to the completion of the order. The input of the push acceptance model is at least one of the historical portrait features of the first user, the first user's activity features, and the matching features between the first user and the source of goods to be pushed. In the push acceptance model, the above-mentioned input features are processed by offline data extraction, conversion, loading, etc. and real-time data processing (flink) stream processing and uploaded to the online, and a gradient boosting decision tree model (gbdt) is called. The push acceptance model outputs the probability value of the first user accepting the source of goods to be pushed.

[0061] In another possible implementation, it may be a multi-objective modeling model. The modeling objectives in the multi-objective modeling model may include: the first user clicks on the delivery source to be pushed, the first user trades the delivery source to be pushed, the delivery source to be pushed is traded from other scenarios (e.g., search scenarios) of the freight application, and the first user clicks on the freight to be pushed and returns to the freight application. Since the expected effect of the pushed delivery source information is to promote active users to place orders and to promote inactive users to return to the freight application, the fusion of the above four labels can better describe the utility brought by the delivery source to be pushed, making the results of the push acceptance model more accurate, and thus making the pushed source of goods more in line with customer needs.

[0062] Step 203: The server determines the frequency of pushing the source of goods according to the information on the degree to which the first user is expected to accept the source of goods to be pushed.

[0063] The supply push frequency refers to the frequency of pushing supply messages to the first user.

[0064] A mapping function may be established between the first user's acceptance degree information of the source of goods to be pushed and the source of goods push frequency. The server inputs the first user's acceptance degree information of the source of goods to be pushed into the mapping function to obtain the corresponding source of goods push frequency.

[0065] Step 204: The server pushes the supply to be pushed to the terminal device corresponding to the first user in accordance with the supply push frequency.

[0066] The server may push the source to be pushed when the source push frequency is reached. The server may also not push the source to be pushed when it is determined that the push time indicated by the push frequency has not yet arrived.

[0067] Step 205: The terminal device displays the source of goods to be pushed.

[0068] The terminal device can display the delivery sources to be pushed in the form of a notification in the notification bar, or can display the delivery sources to be pushed through the display controls of the freight application.

[0069] In this embodiment, the freight application may have multiple users, so the server may need to maintain multiple users and push the source of goods message to multiple users. Push the source of goods message to each user separately: the server determines the degree of acceptance of the first user to be pushed to the source of goods based on at least one of the historical portrait feature of the first user, the activity feature of the first user, and the matching feature between the first user and the source of goods to be pushed, and fully considers the situation of the source of goods to be pushed and the first user, so that the obtained degree of acceptance of the first user to be pushed to the source of goods is more accurate. The server determines the source of goods push frequency based on the estimated degree of acceptance of the first user to be pushed to the source of goods. The determined source of goods push frequency is more in line with the acceptance of the first user. In the case of meeting the source of goods push frequency, the source of goods to be pushed is pushed to the terminal device corresponding to the first user. After receiving the pushed source of goods, the terminal device corresponding to the first user displays the pushed source of goods. Therefore, based on the driver's historical portrait characteristics, the driver's activity level and the driver's matching degree with the pushed delivery source, the driver's acceptance degree of the pushed delivery source is determined, so as to adaptively adjust the delivery source push frequency. The determined delivery source push frequency is more in line with the driver's situation, and freight messages are adaptively pushed at this delivery source push frequency, so that the pushed delivery source does not disturb the driver and meets the driver's needs for timely receiving messages. The driver can quickly find a satisfactory delivery source, which improves the driver's order acceptance efficiency, thereby improving the efficiency of the shipper and the driver in reaching an order, and better balancing the user experience and the reach and conversion efficiency of message push.

[0070] In some embodiments, the historical portrait features of the first user include at least one of the following information: the historical arrival volume of the first user, the historical click volume of the first user, the historical click rate of the first user, and the historical click rate per unit time of the first user.

[0071] The historical arrival volume of the first user refers to the quantity of external sources of goods pushed to the first user in the most recent first preset time period.

[0072] The most recent first preset time period refers to a preset time period before the current moment. Exemplarily, the most recent first preset time period may be nearly N days, where N is a positive integer.

[0073] Among them, the off-terminal source of goods refers to the source of goods pushed outside the freight application, for example, it can be the source of goods pushed in the form of a notification in the notification bar of the terminal device.

[0074] The historical click volume of the first user refers to the number of external sources of goods clicked by the first user in the most recent first preset time period.

[0075] The historical click rate of the first user refers to the ratio of the historical click volume of the first user to the historical reach volume of the first user.

[0076] The historical click-through rate per unit time of the first user refers to the ratio of the number of pushed external end sources of goods viewed by the first user to the number of external end sources of goods pushed to the first user in each unit time of the most recent first preset time period.

[0077] The unit time is a preset duration, and the unit time is less than the first preset time period. For example, each unit time may be one hour.

[0078] In some embodiments, the first user activity feature includes at least one of the following information: the first user's current arrival volume, the first user's current click volume, the first user's full-scene click volume, and the length of time since the first user's most recent active behavior.

[0079] Active actions include clicking on a source, searching for a source, or opening a shipping app.

[0080] The current arrival quantity of the first user refers to the quantity of the supply pushed to the first user in the most recent second preset time period.

[0081] The second preset time period is shorter than the first preset time period.

[0082] The current click volume of the first user refers to the number of pushed sources clicked by the first user in the most recent second preset time period;

[0083] The full-scenario click volume of the first user refers to the number of sources of goods clicked by the first user in all scenarios within the most recent second preset time period.

[0084] The scenarios may include search scenarios, push scenarios, etc. The search scenario refers to the scenario of searching for cargo sources in the cargo application. The push scenario refers to the scenario of receiving push cargo sources.

[0085] In some embodiments, the matching characteristics between the first user and the delivery source to be pushed include at least one of the following: driver-cargo matching score, empty driving ratio, and driver-cargo matching information corresponding to each freight information.

[0086] The driver-cargo matching score is used to indicate the matching degree between the source to be pushed and the first user.

[0087] Exemplarily, the driver-goods matching score can be obtained through a transaction rate model, which can be established based on a machine learning model and is used to process the input user information and supply information to obtain the degree to which the supply meets the user's expectations. The higher the driver-goods matching score, the more the supply meets the user's expectations. It can also be understood that the probability of the user completing a transaction with the supply is obtained. The higher the driver-goods matching score, the greater the probability of the user completing a transaction with the supply.

[0088] The idle driving ratio refers to the ratio of the idle driving distance of the first user to the transportation distance of the source to be delivered.

[0089] The empty driving ratio refers to the distance the driver drives from the empty vehicle to the loading location to pick up the goods, that is, the empty driving distance, which is the ratio of the transportation distance. Since the empty driving process requires time, fuel and other costs, the empty driving ratio can be used to represent the empty driving cost. The higher the empty driving ratio, the higher the driver's cost of picking up the goods.

[0090] The driver-cargo matching degree information of each freight information is used to indicate the degree to which each freight information in the source of goods to be pushed meets the first user's preference for the corresponding source of goods information.

[0091] The freight information includes at least one of the following information: vehicle length, vehicle type, load, cargo type, departure place and destination.

[0092] The cargo source information generated by the cargo owner when placing an order generally includes the above-mentioned freight information. The search conditions for the driver to search for cargo sources generally also include the above-mentioned freight information. For the above-mentioned information not included, it can also be determined through the driver's historical search or the cargo source of the transaction.

[0093] When determining the driver-cargo matching information of each freight information, each type of freight information may be processed separately. For example, the driver-cargo matching information of the driver may be obtained by comparing the driver in the to-be-delivered source with the driver who has been searched and / or traded with by the first user in the past. The driver-cargo matching information of the driver refers to the degree to which the driver in the to-be-delivered source meets the first user's preference for the driver.

[0094] In some embodiments, step 201 may include the following steps 2011 to 2013.

[0095] Step 2011: The server determines the frequency of picking up goods from the supply pool according to the login status of the freight application corresponding to the first user.

[0096] The login status includes online status and offline status.

[0097] The cargo pool includes cargoes that meet the current freight push scenario of the first user.

[0098] Among them, since the goods are first picked up by obtaining the frequency of picking up the source of goods from the source pool, the source of goods needs to be pushed to the terminal device corresponding to the first user later when the determined source of goods push frequency is met. Therefore, the preset frequency of picking up the source of goods from the source pool is usually less than or equal to the preset source of goods push frequency.

[0099] In this embodiment, the login status and the pickup frequency have a corresponding relationship, and the corresponding pickup frequency can be determined according to the login status of the freight application corresponding to the current first user. The pickup frequency corresponding to the offline state is lower than the pickup frequency corresponding to the online state. For example, if the first user is online, it means that the user is in an active state of finding goods, and the first source of goods is obtained from the source pool at a pickup frequency of 10s to ensure that the first source of goods is delivered in a timely and continuous manner. If the first user is offline, it means that the first user has entered an inactive state. At this time, the pickup frequency can be reduced, and the first source of goods can be obtained at a pickup frequency of 100s to avoid disturbing the first user.

[0100] Step 2012: The server obtains the first source of goods from the source pool according to the pickup frequency and the preset pickup method.

[0101] In this embodiment, there may be more than one source of goods in the supply pool, so it is necessary to obtain the first source of goods from the supply pool according to the preset pickup method. The preset pickup method can also be called the out-of-pool priority condition. The preset pickup method is a preset method of obtaining a source of goods from multiple sources of goods in the supply pool. The preset pickup method can be to obtain the source of goods according to the timeliness priority, that is, the source of goods with the highest timeliness is obtained each time as the first source of goods; it can also be obtained according to the driver-cargo matching score, that is, the source of goods with the highest driver-cargo matching score is obtained each time as the first source of goods. The above-mentioned preset pickup methods are only examples and do not constitute a limitation of the present disclosure. The present disclosure does not limit the preset pickup methods.

[0102] Step 2013: When the driver-cargo matching score of the first source of goods is greater than or equal to the matching score threshold, and the time from the current moment to the last push is greater than or equal to the time threshold, the server determines that the first source of goods is the source to be pushed.

[0103] In the cargo source broadcasting scenario, due to its product characteristics, it is necessary to wait for the banner of a cargo source to be displayed before displaying the next cargo source. Compared with the list page format that can display multiple cargo sources at a time, the exposure efficiency is low. In addition, drivers have limited time and energy, and the proportion of cargo sources with lower income in a day is often higher than that of cargo sources with higher income. Excessive exposure of cargo sources with lower income will distract drivers' attention and affect drivers' feedback on more valuable cargo sources. Based on the above reasons, the first cargo source can be controlled with low scores to block low-score cargo sources from leaving the pool. After obtaining the first cargo source from the cargo source pool, the driver-cargo matching score of the first cargo source can be compared with the matching score threshold, and the time from the current time to the last push can be compared with the time threshold. If the driver-cargo matching score is lower than the matching score threshold and the interval from the current time to the last push time is lower than the time threshold, the current cargo source scheduling is blocked and the first cargo source is put back into the cargo source pool. If the driver-cargo matching score of the first source of goods is greater than or equal to the matching score threshold, and the time from the current moment to the last push is greater than or equal to the time threshold, the first source of goods is determined to be the source of goods to be pushed.

[0104] The driver-cargo matching score is used to indicate the score of the matching degree between the source to be pushed and the first user. The driver-cargo matching score in this embodiment is the same as the driver-cargo matching score mentioned in the above embodiment.

[0105] Furthermore, the matching score threshold is determined based on the login state of the freight application corresponding to the current first user and the running state of the freight application corresponding to the first user. The running state of the freight application refers to the freight application running on the front end of the terminal device or the freight application running in the background of the terminal device. Exemplarily, the matching score threshold can be determined based on whether the current first user is in an online state within the terminal, an online state outside the terminal, or an offline state. The above three states are respectively set with corresponding matching score thresholds. From online to offline within the terminal, it describes the driver's state from active to inactive. The more active the driver, the lower the matching score threshold and duration threshold. Since the driver can accept more sources of goods when he is active, and has more energy to identify the quality of the sources of goods, a lower matching score threshold and duration threshold can be set, so that the driver can view more sources of goods.

[0106] Furthermore, based on long connection heartbeat, Rest interface reporting and other methods, it is possible to identify whether the first user is offline, on or off the terminal, etc.

[0107] In this embodiment, the server determines the frequency of picking up goods from the source pool according to the login status of the freight application corresponding to the first user, obtains the first source of goods from the source pool according to the frequency of picking up goods and the preset picking method, and determines the first source of goods as the source of goods to be pushed when the driver-cargo matching score of the source of goods to be pushed is greater than or equal to the matching score threshold, and the time from the current moment to the last push is greater than or equal to the time threshold. Thus, the frequency of picking up goods is determined according to the user login status, and the first source of goods is obtained from the source pool according to the frequency of picking up goods. When the driver-cargo matching score and the push interval time of the source of goods meet the conditions, the first source of goods is determined as the source of goods to be pushed, and the degree of acceptance of the source of goods to be pushed by the first user is determined according to at least one of the historical portrait feature of the first user, the activity feature of the first user, and the matching feature of the first user and the source of goods to be pushed. The frequency of pushing the source of goods is determined according to the expected degree of acceptance of the source of goods to be pushed by the first user, and the source of goods to be pushed is pushed to the terminal device corresponding to the first user when the source of goods push frequency is met. Since there is a certain amount of calculation in the process of determining the degree of information on the first user's acceptance of the source of goods to be pushed based on at least one of the first user's historical portrait feature, the first user's activity feature, and the first user's matching feature with the source of goods to be pushed, which consumes the processing resources of the server, the source of goods to be pushed can be first obtained through the frequency of picking up goods, and then the source of goods to be pushed can be processed to obtain the corresponding frequency of goods push, thereby determining to push the source of goods to be pushed to the terminal device corresponding to the first user. This has a fast processing speed and saves processing resources.

[0108] In some embodiments, the supply pool includes a quick pass pool, a sharing pool, and a support pool.

[0109] Among them, the quick pass pool stores goods for push scenarios with high timeliness. Goods for push scenarios with high timeliness usually have a short life cycle and are more sensitive to the time it takes to reach them. For example, goods for limited-time grab orders usually only have the right to grab orders for a short period of time.

[0110] Among them, the shared pool stores goods without special business background. Furthermore, after the goods are stored in the shared pool, they can be scored through the above-mentioned transaction rate model to obtain the driver-goods matching score of the goods.

[0111] Among them, the sources of goods corresponding to the support channels of the storage business in the support pool are the sources of goods that need to be obtained first when the driver-cargo matching score is not high.

[0112] In step 2012, the server performs the following processing from step 20121 to step 20122 each time it obtains the first source of goods based on the pickup frequency.

[0113] Step 20121: The server determines whether there is a source of goods in the quick pass pool.

[0114] If so, continue to step 20122; if not, continue to step 20123.

[0115] Step 20122: The server obtains the earliest source of goods in the quick pass pool as the first source of goods.

[0116] Step 20123: The server determines whether the current support conditions are met.

[0117] If so, continue to step 20124; if not, continue to step 20125.

[0118] Step 20124: The server obtains the source of goods with the highest driver-cargo matching score from the support pool as the first source of goods.

[0119] Usually, the driver-cargo matching score of the goods in the support pool is lower than the goods with the highest driver-cargo matching score in the shared pool. However, due to the needs of the scenario policy, when the support conditions are met, the goods in the support pool can be obtained as the first source of goods. That is, the goods in the support pool are inserted to the head of the queue at a certain frequency and are the first to leave the source pool. Furthermore, the M-insert-1 method can be adopted, where M is a positive integer greater than 1, that is, when obtaining the source of goods, one of the M sources of goods is guaranteed to be obtained from the support pool.

[0120] For example, the support condition may be to provide 3-in-1 support for LTL cargo sources. In this case, a counter may be set, and every 3 times cargo sources are obtained from the shared pool, it will trigger a trigger to obtain LTL cargo sources from the support pool. Furthermore, the cargo sources obtained from the support pool may be determined by the driver-cargo matching score, and cargo sources with high driver-cargo matching scores may be given priority.

[0121] Step 20125: The server obtains the source of goods with the highest driver-cargo matching score from the shared pool as the first source of goods.

[0122] In this embodiment, the server can obtain the first source of goods from the source pool by polling. Each polling will obtain the source of goods from the source pool according to the preset pickup method: first search whether there is a source of goods in the quick pass pool. If there is, obtain the earliest source of goods in the quick pass pool and take it out of the pool as the first source of goods; if there is no source of goods in the quick pass pool, search the shared pool and take the source of goods with the highest score out of the shared pool. In the process of searching the shared pool, the server inquires whether there are currently support conditions. The support conditions are set according to business rules. If it is found that there are currently support conditions, for example, 3-in-1 support is provided for LTL sources of goods, a counter will be set. Every 3 times the source of goods is dispatched from the shared pool, it will trigger the dispatch of LTL sources of goods from the support pool. Which source of goods in the support pool is specifically dispatched to support the business can be determined by the driver-cargo matching score of the transaction rate model, and high-scoring sources of goods will be dispatched first.

[0123] In this embodiment, based on the characteristics of the supply push scenario, multiple supply pools are configured: in scenarios with high timeliness requirements, the supply pool adopts a first-in-first-out strategy, and in scenarios with low timeliness requirements, a high-score priority strategy is adopted. The generated supplies are stored in different supply pools, and the first supply is obtained according to the pickup priority set for different supply pools, so that multiple supplies generated simultaneously in multiple scenarios can be pushed in an orderly manner.

[0124] In some scenarios, for push information generated in real time, it is necessary to push the push messages according to categories.

[0125] The following is a detailed description with reference to specific embodiments.

[0126] In some embodiments, the method provided in this embodiment further includes the following step 206.

[0127] Step 206: After receiving the push information that does not meet the value condition and the timeliness condition, the server puts the push information into the quick pass pool, the sharing pool or the support pool according to the preset pool entry method.

[0128] Among them, the value condition refers to the relatively high value relative to the first user.

[0129] The timeliness condition refers to a relatively high processing time requirement relative to the first user.

[0130] In this embodiment, for the push information generated in real time, if the push message does not meet the value condition and the timeliness condition, the server puts the push message into the resource pool and waits for pushing.

[0131] In some embodiments, the method provided in this embodiment further includes the following step 207 .

[0132] Step 207: After receiving the push information that meets the value condition or the time limit condition, the server pushes the push information that meets the value condition or the time limit condition to the terminal device.

[0133] In this embodiment, for real-time push information, if the push message meets the value condition or timeliness condition, the server directly pushes the push message to the terminal device. That is, notification messages with high value or high timeliness can be directly pushed to the terminal device. For example, driver A discusses the freight with cargo owner B about cargo source H, and cargo owner B replies to driver A's message, which is directly pushed to the terminal device corresponding to driver A. This ensures that important messages reach users directly.

[0134] Based on the message push method described in any of the above embodiments, the embodiment of the present disclosure further provides a computer-readable storage medium, for example, the non-temporary computer-readable storage medium may be a read-only memory (ROM), a random access memory (RAM), a CD-ROM, a magnetic tape, a floppy disk, and an optical data storage device, etc. The storage medium stores computer instructions for executing the message push method described in any of the above embodiments, which will not be described in detail here.

[0135] A person skilled in the art will understand that all or part of the steps to implement the above embodiments may be accomplished by hardware, or by a program to instruct the relevant hardware, and the program may be stored in a computer-readable storage medium, and the above-mentioned storage medium may be a read-only memory, a disk or an optical disk, etc.

[0136] Those skilled in the art will readily appreciate other embodiments of the present disclosure after considering the specification and practicing the disclosure disclosed herein. This application is intended to cover any variations, uses, or adaptations of the present disclosure that follow the general principles of the present disclosure and include common knowledge or customary techniques in the art that are not disclosed in the present disclosure. The description and examples are intended to be exemplary only, and the true scope and spirit of the present disclosure are indicated by the following claims.

Claims

1. A message push method, characterized in that: The method comprises: Get the delivery source to be pushed; Determining information on the degree of acceptance of the delivery source to be recommended by the first user based on at least one of a historical portrait feature of the first user, an activity feature of the first user, and a matching feature between the first user and the delivery source to be recommended; Determining a frequency of pushing the source of goods according to information about the expected degree of acceptance of the source of goods to be pushed by the first user; In the case where the supply pushing frequency is met, the supply to be pushed is pushed to the terminal device corresponding to the first user.

2. The method according to claim 1, characterized in that: The historical portrait feature of the first user includes at least one of the following information: the historical arrival volume of the first user, the historical click volume of the first user, the historical click rate of the first user, and the historical click rate per unit time of the first user; The historical arrival volume of the first user refers to the quantity of external sources of goods pushed to the first user in the most recent first preset time period; The historical click volume of the first user refers to the number of pushed external product sources clicked by the first user in the most recent first preset time period; The historical click rate of the first user refers to the ratio of the historical click volume of the first user to the historical reach volume of the first user; The historical click-through rate per unit time of the first user refers to the ratio of the number of external sources of goods pushed by the first user to the number of external sources of goods pushed to the first user in each unit time of the most recent first preset time period.

3. The method according to claim 1, characterized in that The first user activity feature includes at least one of the following information: the current arrival volume of the first user, the current click volume of the first user, the full-scene click volume of the first user, and the duration of the first user's most recent active behavior; the active behavior includes clicking on a source of goods, searching for a source of goods, or opening a freight application; The current arrival volume of the first user refers to the quantity of the supply pushed to the first user in the most recent second preset time period; the second preset time period is less than the first preset time period; The current click volume of the first user refers to the number of pushed sources of goods clicked by the first user in the most recent second preset time period; The full-scenario click volume of the first user refers to the number of sources of goods clicked by the first user in all scenarios within the most recent second preset time period.

4. The method according to claim 1, characterized in that: The matching characteristics between the first user and the delivery source to be pushed include at least one of the following: driver-cargo matching score, empty driving ratio and driver-cargo matching information corresponding to each freight information; the freight information includes at least one of the following information: vehicle length, vehicle type, load, cargo type, departure place and destination; The driver-cargo matching score is used to indicate the matching degree between the to-be-delivered source and the first user; The idle driving ratio refers to the ratio of the idle driving distance of the first user to the transportation distance of the source to be pushed; The driver-cargo matching information of each freight information is used to indicate the degree to which each freight information in the to-be-promoted source of goods matches the first user's preference for the corresponding source of goods information.

5. The method according to claim 1, characterized in that The step of obtaining the source of the content to be pushed includes: Determine the frequency of picking up goods from a supply pool according to the login status of the freight application corresponding to the first user; the login status includes an online status and an offline status; the supply pool includes supplies that meet the freight push scenario currently in which the first user is in; Obtaining a first source of goods from the source pool at the pickup frequency and according to a preset pickup method; When the driver-cargo matching score of the first source of cargo is greater than or equal to the matching score threshold, and the time from the current moment to the last push is greater than or equal to the time threshold, the first source of cargo is determined to be the source of cargo to be pushed; the driver-cargo matching score is used to indicate the score of the degree of matching between the source of cargo to be pushed and the first user.

6. The method according to claim 5, characterized in that The matching score threshold is determined according to a current login state of the freight application corresponding to the first user and a running state of the freight application corresponding to the first user.

7. The method according to claim 5, characterized in that The supply pool includes a quick pass pool, a shared pool, and a support pool; obtaining the first supply from the supply pool according to the pickup frequency and a preset pickup method includes: At the frequency of picking up goods, the following processing is performed each time the first source of goods is obtained: If there is a source of goods in the quick pass pool, the earliest source of goods in the quick pass pool is obtained as the first source of goods; if there is no source of goods in the quick pass pool and the support conditions are not met at present, the source of goods with the highest driver-goods matching score is obtained from the shared pool as the first source of goods; if there is no source of goods in the quick pass pool and the support conditions are currently met, the source of goods with the highest driver-goods matching score is obtained from the support pool as the first source of goods.

8. The method according to claim 7, characterized in that The method further comprises: After receiving the push information that does not meet the value condition and the timeliness condition, the push information is placed in the quick pass pool, the sharing pool or the support pool according to the preset pool entry method; After receiving the push information that meets the value condition or the time limit condition, the push information that meets the value condition or the time limit condition is pushed to the terminal device.

9. A message push method, characterized in that: The method comprises: The terminal device receives a delivery source to be pushed pushed by a server, wherein the delivery source to be pushed is determined by the server based on at least one of the first user's historical profile feature, the first user's activity feature, and the first user's matching feature with the delivery source to be pushed, to determine the delivery source push frequency based on the first user's expected acceptance of the delivery source to be pushed; and is pushed in accordance with the delivery source push frequency; the first user is a logged-in user of a freight application in the terminal device; The terminal device displays the source to be pushed.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 9 are implemented.

Images