Goods source recommendation method and device, electronic equipment and storage medium

Abstract

The invention provides a goods source recommendation method and device, electronic equipment and a storage medium. The method comprises the steps of obtaining historical information of a goods source list, wherein the goods source list comprises one or more goods source positions; according to historical information, first beta distribution and second beta distribution corresponding to one or more goods source positions are established, the first beta distribution is used for indicating completion expectation distribution of a first type of goods sources, the second beta distribution is used for indicating completion expectation distribution of a second type of goods sources, the first type of goods sources are unexposed goods sources, and the second type of goods sources are unexposed goods sources; the goods source of the second type is an exposed goods source; for each goods source position, recommending a first goods source or a second goods source through the goods source position according to the first beta distribution and the second beta distribution corresponding to the goods source position; and according to the received operation information of the goods source position, the goods source of the goods source position is updated in real time, so that the transaction rate and the transaction speed of the goods source are improved.

Description

Technical Field

[0001] The present application relates to the field of logistics technology, and in particular to a method, device, electronic device and storage medium for recommending a source of goods. Background Art

[0002] With the development of online freight, various transportation platforms have emerged. Users can search for sources of goods on the transportation platforms and accept orders for transportation.

[0003] In related technologies, the transportation platform can screen out candidate sources of goods based on search conditions, the number of orders received by users in recent time, the number of fulfillment, the number of clicks on the source of goods in recent time, the amount of feedback, and other characteristics, and push the candidate sources of goods to users through the source of goods list.

[0004] However, users usually only browse the sources of goods that are ranked first in the source list. In the above-mentioned related technologies, after the user refreshes the source list, the sources of goods that are ranked first in the source list usually do not change, causing the user to believe that the transportation platform has insufficient cargo and lacks new cargo, which makes the user lose the desire to find goods, resulting in a low transaction rate and transaction speed of the source of goods. Summary of the invention

[0005] The present application provides a source of goods recommendation method, device, electronic device and storage medium to solve the problem that the sources of goods ranked first in the source of goods list usually do not change, which causes users to believe that the transportation platform has insufficient goods and lacks new goods, causing users to lose the desire to find goods, thereby resulting in a low transaction rate and transaction speed of the sources of goods, thereby achieving the purpose of improving the transaction rate and transaction speed of the sources of goods.

[0006] In a first aspect, the present application provides a method for recommending a source of goods, comprising:

[0007] Acquire historical information of a supply source list, the supply source list including one or more supply source locations, the historical information including historical behavior data corresponding to the one or more supply source locations, the historical behavior data being used to indicate historical behavior statistics corresponding to the supply source locations;

[0008] According to the historical information, a first beta distribution and a second beta distribution are established corresponding to the one or more supply source locations, respectively, wherein the first beta distribution is used to indicate the expected distribution of completed orders of a first type of supply source, and the second beta distribution is used to indicate the expected distribution of completed orders of a second type of supply source, wherein the first type of supply source is an unexposed supply source, and the second type of supply source is an exposed supply source;

[0009] For each of the supply source positions, according to the first beta distribution and the second beta distribution corresponding to the supply source position, recommend a first supply source or a second supply source through the supply source position, wherein the first supply source is a supply source that has not been exposed within the first time period, and the second supply source is a supply source that has been exposed within the first time period;

[0010] According to the received operation information of the source location, the source of goods at the source location is updated in real time.

[0011] Through the supply recommendation method provided in the first aspect, the historical information of the supply list is obtained, and the historical information of the supply list can reflect the user's preference information for novel supplies and non-novel supplies at different supply locations, so as to make personalized recommendations for users at different supply locations, and recommend supplies that users are more interested in to users, thereby helping to improve the accuracy of supply recommendation. According to the historical information, a first beta distribution and a second beta distribution corresponding to one or more supply locations are established, respectively, so that the order completion expectation of the supply location can be evaluated for different types of supplies, and the user's order completion expectation for the first type of supply and the second type of supply at each supply location is obtained, thereby providing a basis for supply recommendation, which helps to improve the accuracy of supply recommendation. For each supply location, according to the first beta distribution and the second beta distribution corresponding to the supply location, the first supply or the second supply is recommended by the supply location, so that the user can be recommended a suitable supply at each supply location in the supply list according to the user's preference, so as to improve the transaction rate of the supply. According to the operational information of the supply location received, the supply at the supply location is updated in real time. Through continuous iterative updates, novel or non-novel sources of supply can be continuously inserted into the supply list, thereby realizing dynamic recommendation of sources of supply, allowing users to continuously receive new sources of supply without changing search conditions or frequently browsing the supply list, thereby improving the transaction rate and transaction speed of the sources.

[0012] In a possible design, updating the supply of the supply location in real time according to the received operation information of the supply location includes:

[0013] For each of the supply source locations, updating the parameters of the first Beta distribution and the parameters of the second Beta distribution corresponding to the supply source location according to the received operation information of the supply source location;

[0014] After a second period of time, or when refresh information is received, the first source of supply or the second source of supply is recommended through the source of supply location according to the first Beta distribution and the second Beta distribution corresponding to the source of supply location, and the refresh information is used to refresh the source of supply list.

[0015] In a possible design, the historical behavior data includes first behavior data and second behavior data;

[0016] The first behavior data includes a first statistic and a second statistic, the first statistic is used to indicate the number of clicks or transaction volume of the first type of supply at the supply location within the historical time window, and the second statistic is used to indicate the number of clicks or transaction volume of the second type of supply at the supply location within the historical time window;

[0017] Among them, the second behavior data includes a third statistic and a fourth statistic, the third statistic is used to indicate the exposure of the first type of source of supply at the source location within the historical time window, and the fourth statistic is used to indicate the exposure of the second type of source of supply at the source location within the historical time window.

[0018] In a possible design, establishing the first Beta distribution and the second Beta distribution corresponding to the one or more supply source locations respectively according to the historical information includes:

[0019] For each of the source locations, the first Beta distribution is determined according to the first statistic and the third statistic, and the second Beta distribution is determined according to the second statistic and the fourth statistic.

[0020] In a possible design, for each of the source locations, determining the first Beta distribution according to the first statistic and the third statistic, and determining the second Beta distribution according to the second statistic and the fourth statistic includes:

[0021] Determine the first statistic as a first parameter of the first Beta distribution, determine the difference between the third statistic and the first statistic as a second parameter of the first Beta distribution, and obtain the first Beta distribution;

[0022] The second statistic is determined as the third parameter of the second Beta distribution, and the difference between the fourth statistic and the second statistic is determined as the fourth parameter of the second Beta distribution, so as to obtain the second Beta distribution.

[0023] In a possible design, for each of the supply source locations, updating the parameters of the first beta distribution and the parameters of the second beta distribution corresponding to the supply source location according to the received operation information of the supply source location includes:

[0024] In the case where the first operation information is received within the third time period, when the supply at the supply source location is the first supply source, the first parameter is updated according to the first preset coefficient, and the first operation information is used to instruct the user to click on the supply at the supply source location, or the first operation information is used to instruct the user to trade the supply at the supply source location;

[0025] When the source of goods at the source location is the second source of goods, updating the third parameter according to the second preset coefficient;

[0026] In the case where the first operation information is not received within the third time period, when the source of goods at the source location is the first source of goods, updating the second parameter according to a third preset coefficient and exposure information, wherein the exposure information is used to indicate the exposure of the source of goods at the source location within the third time period;

[0027] When the source of goods at the source location is the second source of goods, the fourth parameter is updated according to a fourth preset coefficient and the exposure information.

[0028] In a possible design, for each of the supply source locations, recommending a first supply source or a second supply source according to the supply source location according to a first beta distribution and a second beta distribution corresponding to the supply source location includes:

[0029] determining a first expectation according to the first beta distribution, and determining a second expectation according to the second beta distribution;

[0030] When the first expectation is greater than the second expectation, inserting a first source of goods into the source position, the type of the first source of goods being the first type;

[0031] When the first expectation is less than or equal to the second expectation, a second source of goods is inserted into the source position, and the type of the second source of goods is the second type, or the source of goods at the source position is kept unchanged.

[0032] In one possible design, the method further includes:

[0033] Obtaining the search conditions at the current moment, wherein the search conditions are used to indicate the attributes of the source of goods required by the user;

[0034] Determine the supply source whose attributes meet the search conditions as the third supply source;

[0035] Determine a fourth source of goods and a fifth source of goods according to the third source of goods, wherein the fourth source of goods includes the sources of goods in the third source of goods that have not been exposed within the first time period, and the fifth source of goods includes the sources of goods in the third source of goods that have been exposed within the first time period;

[0036] One of the fourth sources of supply is determined as the first source of supply, and one of the fifth sources of supply is determined as the second source of supply.

[0037] In a second aspect, the present application provides a supply recommendation device, including: a module for executing the method in the first aspect and any possible involvement in the first aspect.

[0038] In a third aspect, the present application provides an electronic device, including: a processor;

[0039] The processor is used to execute the computer executable program or instructions in the memory, so that the electronic device executes the method in the first aspect and any possible design of the first aspect.

[0040] In a fourth aspect, the present application provides an electronic device, including: a memory and a processor;

[0041] The memory is used to store program instructions; the processor is used to call the program instructions in the memory so that the electronic device executes the method in the first aspect and any possible design of the first aspect.

[0042] In a fifth aspect, the present application provides a computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor in an electronic device, the computer program implements the method in the first aspect and any possible design of the first aspect. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] Figure 1 A flowchart of a method for recommending a source of goods provided in one embodiment of the present application.

[0044] Figure 2 A schematic diagram of a supply list provided for one embodiment of the present application.

[0045] Figure 3 A flowchart of a method for recommending a source of goods provided in one embodiment of the present application.

[0046] Figure 4 A flowchart of a method for recommending a source of goods provided in one embodiment of the present application.

[0047] Figure 5 A flow chart of a method for updating parameters of a first beta distribution and parameters of a second beta distribution provided in one embodiment of the present application.

[0048] Figure 6 A flow chart of a method for recommending a first source of goods or a second source of goods by source location provided in one embodiment of the present application.

[0049] Figure 7 A flow chart of a method for determining the source of goods provided in one embodiment of the present application.

[0050] Figure 8 A schematic diagram of the structure of a supply source recommendation device provided in one embodiment of the present application.

[0051] Fig. 9 A schematic diagram of the structure of an electronic device provided in one embodiment of the present application.

[0052] Fig.10A schematic diagram of the structure of an electronic device provided in one embodiment of the present application. DETAILED DESCRIPTION

[0053] In this application, "at least one" means one or more, and "plurality" means 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 associated objects 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, b, or c alone can represent: a, b, c, a and b, a and c, or a, b, and c, 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.

[0054] The directions or positional relationships indicated by terms such as "center", "longitudinal", "lateral", "up", "down", "left", "right", "front", and "back" are based on the directions or positional relationships shown in the accompanying drawings and are only for the convenience of describing the present application and simplifying the description. They do not indicate or imply that the device or element referred to must have a specific direction, be constructed and operated in a specific direction, and therefore should not be understood as a limitation on the present application.

[0055] The terms "connected" and "connected" should be understood in a broad sense. For example, the "connected" or "connected" of a circuit structure can refer to not only physical connection, but also electrical connection or signal connection. For example, it can be directly connected, that is, physically connected, or indirectly connected through at least one intermediate element, as long as the circuit is connected, or it can be the internal connection of two elements; signal connection can refer to signal connection through a circuit or through a media medium, such as radio waves. For ordinary technicians in this field, the specific meanings of the above terms in this application can be understood according to specific circumstances.

[0056] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the accompanying drawings.

[0057] Exemplarily, the present application provides a method, device, electronic device, computer-readable storage medium, and computer program product for recommending sources of goods. For each user, the transportation platform uses the historical behavior data of each source location in the source list to fit the order completion expectations of novel sources and non-novel sources at the source location, and determines to insert novel sources or non-novel sources at the source location. According to the received operation information, the order completion expectations of novel sources and non-novel sources at the source location are continuously updated, and the source of goods at the source location is updated, so as to dynamically update the source list, recommend more different sources of goods to users, and improve users' willingness to find goods, thereby improving the transaction rate and transaction speed of the source.

[0058] Among them, the supply source recommendation method provided in the present application can be executed by an electronic device, or by a supply source recommendation device in an electronic device.

[0059] Among them, the electronic device can be a server, a desktop computer, a mobile phone, a tablet computer, a laptop computer, a wearable device, a vehicle-mounted device, an augmented reality (AR) / virtual reality (VR) device, etc.

[0060] Among them, the source recommendation device can be implemented by a combination of software and / or hardware. For example, the source recommendation device can be an application (APP), a web page or a public account, etc. For example, the source recommendation device can be a transportation platform. In order to simplify the description, the embodiment of the present application is described by taking the transportation platform as an example.

[0061] Next, combine Figure 1 , the supply recommendation method provided in the embodiment of the present application is described.

[0062] See also Figure 1 , Figure 1 This is a flow chart of a method for recommending a source of goods provided in one embodiment of the present application. Figure 1 As shown, the method includes:

[0063] S101. Obtain historical information of a supply list.

[0064] The supply list includes one or more supply locations.

[0065] Each supply location includes a supply.

[0066] The supply list is a list generated by the transportation platform, through which the transportation platform can recommend or display various different supply sources to the user.

[0067] Among them, the source list has various forms.

[0068] In some examples, the source list is a list generated by the transportation platform based on search criteria.

[0069] Among them, the search conditions include departure place, destination, route, cargo type, required vehicle length and required vehicle type, etc. Users can set search conditions according to their cargo search needs.

[0070] The transportation platform filters out the sources of goods that meet the search criteria based on the search criteria, and generates a source list based on the sources of goods that meet the search criteria, and displays it to users through the order search and other pages of the APP.

[0071] For example, the search condition may be "Departure place: Beijing, Destination: Shanghai, Required vehicle length: 5 meters". The transportation platform selects all cargo sources with a departure place of Beijing, a destination of Shanghai, and a required vehicle length of 5 meters, and generates a cargo source list.

[0072] In other examples, the source list is a list generated by the transportation platform based on historical behavioral data.

[0073] Specifically, the transportation platform can screen out recommended sources of goods based on the user's historical behavior data on the transportation platform, such as the user's transaction volume and click volume for a certain type of goods, generate a source list based on the recommended sources of goods, and recommend or display it to users through pages such as the APP's homepage recommendations.

[0074] The source list can be Figure 2 As shown, in Figure 2 In the supply list, there are 5 supply locations, each of which corresponds to a supply. Users can click on any supply location to enter the detail page of the supply corresponding to that supply location.

[0075] When drivers search for cargo through the cargo source list, different users will have different preferences for different cargo source locations.

[0076] For example Figure 2 In the example, some users may prefer to choose the supply location 1, while some users may prefer to choose the supply location 5.

[0077] In addition, different users may have different preferences for whether the current supply at the supply source location is the first type of supply or the second type of supply.

[0078] Among them, the first type of source of goods is novel source of goods, which means that the source of goods has not been exposed for a period of time.

[0079] Among them, the second type of supply is non-novel supply, which means supply that has been exposed for a period of time.

[0080] Among them, unexposed sources refer to sources that have not been browsed by users, and exposed sources refer to sources that have been browsed by users.

[0081] For example Figure 2 For source location 1, some users are more inclined to select source location 1 when source 1 is a novel source, while some users are more inclined to select source location 1 when source 1 is a non-novel source.

[0082] Based on this, the transportation platform can obtain the historical information of the source list. The historical information of the source list can reflect the user's preference information for novel sources and non-novel sources of goods in different source locations, so that the transportation platform can make personalized recommendations for users in different source locations and recommend sources of goods that users are more interested in, thereby helping to improve the accuracy of source recommendations.

[0083] The historical information includes historical behavior data corresponding to one or more supply source locations.

[0084] The historical behavior data is used to indicate the historical behavior statistics corresponding to the source location.

[0085] The transportation platform can collect user behavior data on the platform.

[0086] For example, for the supply list, the transportation platform will record the number of times users click on or trade in new sources and non-new sources at a certain supply location, thereby obtaining the number of clicks or trades for new sources at the supply location, as well as the number of clicks or trades for non-new sources at the supply location.

[0087] The transportation platform will also record the number of novel sources and the number of non-novel sources exposed to users at a certain source location, thereby obtaining the exposure of novel sources at the source location and the exposure of non-novel sources at the source location.

[0088] The above-mentioned click volume, transaction volume and exposure volume are historical behavior statistics.

[0089] Based on this, the transportation platform obtains the historical information of the source list, thereby obtaining information that can reflect the user's preferences for each source location in the source list, so that when recommending sources of goods, the source of goods can be recommended according to the user's preferences, which helps to improve the user experience and increase the transaction rate of sources of goods.

[0090] S102. Establish a first Beta distribution and a second Beta distribution corresponding to one or more supply source locations according to historical information.

[0091] Among them, Beta distribution refers to a set of continuous probability distributions defined in the interval (0, 1). Beta distribution includes two parameters, namely α and β.

[0092] Among them, α / (α+β) is the mean of the distribution. The larger α+β is, the narrower the distribution is, so the random numbers generated according to the Beta distribution are closer to the center of the distribution.

[0093] The user's order completion expectations for the first type of supply and the second type of supply at each supply source location can be fitted by the Beta distribution.

[0094] For example, in historical behavior statistics, the ratio of clicks to exposures of the first type of supply at a source location can reflect the user's average click expectation for the first type of supply at that source location, and the average click expectation can in turn reflect the user's average order completion expectation for the first type of supply at that source location. Alternatively, the ratio of transaction volume to exposures of the first type of supply at a source location can directly reflect the user's average order completion expectation for the first type of supply at that source location.

[0095] Thus, the transportation platform can establish a beta distribution of the first type of sources at a source location based on the clicks or transaction volume, and exposure of the first type of sources at that source location, and establish a beta distribution of the second type of sources at that source location based on the clicks or transaction volume, and exposure of the second type of sources at that source location.

[0096] Based on this, for a source location, the transportation platform can establish the first Beta distribution and the second Beta distribution corresponding to the source location based on historical information and based on the user's expectations for completing orders for the first type of source and the second type of source at each source location.

[0097] Among them, the first beta distribution is used to indicate the expected distribution of completed orders of the first type of source of goods.

[0098] The transportation platform can determine the parameters of the first Beta distribution based on the historical behavior statistics related to the first type of source of goods in the historical information, thereby obtaining the first Beta distribution.

[0099] For example, for each source location, the transportation platform can determine the number of clicks on the first type of source at that source location as α of the first Beta distribution, and determine the difference between the exposure and clicks of the first type of source at that source location as β of the first Beta distribution, thereby obtaining the first Beta distribution.

[0100] Among them, the second beta distribution is used to indicate the expected distribution of completed orders of the second type of supply.

[0101] The transportation platform can determine the parameters of the first Beta distribution according to the historical behavior statistics related to the second type of source of goods in the historical information, thereby obtaining the second Beta distribution.

[0102] For example, for each source location, the transportation platform can determine the number of clicks on the second type of source at that source location as α of the second Beta distribution, and determine the difference between the exposure and clicks of the second type of source at that source location as β of the second Beta distribution, thereby obtaining the second Beta distribution.

[0103] Taking the number of cargo source locations as 5 as an example, the beta distribution established by the transportation platform for cargo source locations 1 to 5 can be shown in Table 1 below.

[0104] Table 1

[0105] The first type of supply The second type of supply Source location 1 <![CDATA[Beta1 novelty ]]> <![CDATA[Beta1 non-novelty ]]> Source location 2 <![CDATA[Beta2 novelty ]]> <![CDATA[Beta2 non-novelty ]]> Source location 3 <![CDATA[Beta3 novelty ]]> <![CDATA[Beta3 non-novelty ]]> Source location 4 <![CDATA[Beta4 novelty ]]> <![CDATA[Beta4 non-novelty ]]> Source location 5 <![CDATA[Beta5 novelty ]]> <![CDATA[Beta5 non-novelty ]]>

[0106] Based on this, the transportation platform establishes a first Beta distribution and a second Beta distribution corresponding to one or more source locations according to historical information, so as to evaluate the order completion expectations of each source location for different types of sources of goods, and obtain the user's order completion expectations for the first type of source of goods and the second type of source of goods at each source location, thereby providing a basis for the transportation platform to make cargo recommendations, which helps to improve the accuracy of the transportation platform's cargo recommendations.

[0107] S103. For each source location, according to the first Beta distribution and the second Beta distribution corresponding to the source location, recommend a first source or a second source based on the source location.

[0108] Since the first Beta distribution can reflect the user's expectation of completing orders for the first type of supply at the supply location, and the second Beta distribution can reflect the user's expectation of completing orders for the second type of supply at the supply location, the transportation platform can evaluate the user's preference for the first type of supply and the second type of supply at the supply location based on the first Beta distribution and the second Beta distribution.

[0109] Specifically, the transportation platform may randomly sample a first expectation in the first Beta distribution, where the first expectation is used to reflect the user's expectation of completing an order for the first type of source of goods, and randomly sample a second expectation in the second Beta distribution, where the second expectation is used to reflect the user's expectation of completing an order for the second type of source of goods.

[0110] When the first expectation is greater than the second expectation, it means that at this source location, the user's expectation for completing the order of the first type of source is greater than the expectation for completing the order of the second type of source. It can be concluded that if the source of goods at this source location is the first type of source, the user's expectation for completing the order of this source is higher.

[0111] When the first expectation is less than or equal to the second expectation, it means that at this source location, the user's expectation for completing the order of the second type of source is greater than the expectation for completing the order of the first type of source. It can be concluded that if the source of goods at this source location is the second type of source, the user's expectation for completing the order of this source is higher.

[0112] Based on this, for each source location, the transportation platform determines which type of source of goods the user has higher expectations for completing orders based on the first Beta distribution and the second Beta distribution corresponding to the source location, and thus determines whether to recommend the first source of goods or the second source of goods through the source location.

[0113] When the first expectation is greater than the second expectation, the transport platform can insert the first source of goods at the source position. When the first expectation is less than or equal to the second expectation, the transport platform can insert the second source of goods at the source position, thereby realizing the recommendation of the first source of goods or the second source of goods through the source position.

[0114] Among them, the first source of goods is a source that has not been exposed within the first period of time.

[0115] Among them, the second source of goods is a source of goods that has been exposed within the first period of time.

[0116] The first duration is, for example, 1 minute, 2 minutes, or 5 minutes.

[0117] When the first expectation is greater than the second expectation, the transportation platform may regard a source of goods that has not been exposed within the first period of time as a novel source of goods, and determine the source of goods as the first source of goods, insert it into the source of goods position, thereby recommending the novel source of goods to the user. Since the user prefers the novel source of goods at this source of goods position, the transaction rate of the source of goods can be improved.

[0118] When the first expectation is less than or equal to the second expectation, the transportation platform may regard a source of goods that has been exposed within the first period of time as a non-novel source of goods, and determine the source of goods as the second source of goods, insert it into the source of goods position, thereby recommending non-novel sources of goods to users. Since users prefer non-novel sources of goods at this source of goods position, the transaction rate of the source of goods can be improved.

[0119] Taking the number of source locations as 5 as an example, source A1, source A2 and source A3 are sources that have not been exposed in the first period of time, source B1 and source B2 are sources that have been exposed in the first period of time, and the transportation platform determines that the first expectation of source location 1, source location 2 and source location 3 is greater than the second expectation, and the second expectation of source location 4 and source location 5 is greater than the first expectation, then the source list can be shown in Table 2 below.

[0120] Table 2

[0121] Source location 1 Source A1 Source location 2 Source A2 Source location 3 Source A3 Source location 4 Source B1 Source location 5 Source B2

[0122] Based on this, for each source location, the transportation platform inserts the first source or the second source at the source location according to the first Beta distribution and the second Beta distribution corresponding to the source location, and recommends the first source or the second source through the source location, so that it can recommend suitable sources of goods to users at each source location in the source list according to the user's preferences, thereby improving the transaction rate of the sources.

[0123] S104. Update the supply of the supply location in real time according to the received operation information of the supply location.

[0124] After the transportation platform recommends the first or second source of supply based on the source location, the user may click on or complete one or more source locations in the source list. Then, for each source location, the user will have new preferences, thereby affecting the beta distribution of the source location.

[0125] Based on this, for each source location, the transportation platform can update the first Beta distribution and the second Beta distribution of the source location based on the received operational information of the source location, so that new sources of goods can be re-recommended through the source location based on the new first Beta distribution and the new second Beta distribution.

[0126] Specifically, when the cargo source location is the first cargo source, the transportation platform may update the parameters of the first Beta distribution according to the received operation information of the cargo source location, thereby obtaining a new first Beta distribution.

[0127] When the cargo source location is the second cargo source, the transportation platform may update the parameters of the second Beta distribution according to the received operation information of the cargo source location, thereby obtaining a new second Beta distribution.

[0128] The operation information of the supply source location is used to indicate the user's operation on the supply source location. The operation may include click, transaction, and exposure.

[0129] Based on this, the transportation platform can re-recommend new sources of goods based on the source location after a period of time according to the new first Beta distribution and the new second Beta distribution.

[0130] Through continuous iteration and updating, the transportation platform can continuously insert novel or non-novel sources of goods into the source list, thereby realizing dynamic recommendation of sources of goods, allowing users to continuously receive new sources of goods, thereby improving the transaction rate and speed of sources of goods.

[0131] In an embodiment of the present application, the transportation platform obtains historical information of the supply list, and the historical information of the supply list can reflect the user's preference information for novel supply sources and non-novel supply sources at different supply source locations, so that the transportation platform can make personalized recommendations for users at different supply source locations, and recommend supply sources that users are more interested in to users, thereby helping to improve the accuracy of supply source recommendations. The transportation platform establishes a first beta distribution and a second beta distribution corresponding to one or more supply source locations based on historical information, and can evaluate the order completion expectations of the supply source location for different types of supply sources, and obtain the user's order completion expectations for the first type of supply source and the second type of supply source at each supply source location, thereby providing a basis for the transportation platform to recommend supply sources, which helps to improve the accuracy of the transportation platform to recommend supply sources. For each supply source location, the transportation platform recommends the first supply source or the second supply source through the supply source location according to the first beta distribution and the second beta distribution corresponding to the supply source location, so that it can recommend suitable supply sources to users at each supply source location in the supply source list according to the user's preferences, so as to improve the transaction rate of the supply source. The transportation platform updates the supply of goods at the supply location in real time based on the operational information received from the supply location. Through continuous iterative updates, the transportation platform can continuously insert new or non-new sources of goods into the supply list, thereby realizing dynamic recommendation of sources of goods, allowing users to continuously receive new sources of goods without changing search conditions or frequently browsing the supply list, thereby improving the transaction rate and speed of the sources of goods.

[0132] Based on the above exemplary description, in S104, the transportation platform may update the source of goods at the source location in real time according to the method shown in S104A to S104B below.

[0133] See also Figure 3 , Figure 3 This is a flow chart of a method for recommending a source of goods provided in one embodiment of the present application. Figure 3 As shown, S104 can be implemented by S104A to S104B as follows:

[0134] S104A. For each source location, update the parameters of the first beta distribution and the parameters of the second beta distribution corresponding to the source location according to the received operation information of the source location.

[0135] For each cargo source location, when the received operation information of the cargo source location is operation information for the first cargo source, the transportation platform updates the parameters of the first Beta distribution corresponding to the cargo source location, thereby obtaining an updated first Beta distribution.

[0136] When the received operation information of the cargo source location is operation information for the second cargo source, the transportation platform updates the parameters of the second Beta distribution corresponding to the cargo source location, thereby obtaining an updated second Beta distribution.

[0137] S104B: After the second time period, or when the refresh information is received, continue to recommend the first source of goods or the second source of goods according to the first beta distribution and the second beta distribution corresponding to the source of goods location,

[0138] The second duration may be 20 seconds, 1 minute, or 2 minutes, etc.

[0139] The refresh information is used to refresh the supply list. For example, the refresh information may be a refresh instruction received by the transportation platform after the user clicks refresh.

[0140] After the second period of time, the transportation platform can determine a new source of goods for each source location through the updated first Beta distribution and second Beta distribution, thereby automatically recommending the new source of goods to users. The new source of goods can be recommended to users without any operation by the users, thereby realizing dynamic recommendation of sources of goods and improving the transaction rate and speed of sources of goods.

[0141] Of course, when the transport platform receives refresh information, that is, when the user refreshes the supply list, the transport platform can also determine a new supply for each supply location through the updated first Beta distribution and second Beta distribution, thereby recommending new supplies to users, realizing dynamic supply recommendation, and improving the transaction rate and speed of the supply.

[0142] Based on the above exemplary description, the historical behavior data includes first behavior data and second behavior data.

[0143] The first behavior data includes a first statistic and a second statistic.

[0144] The first statistic is used to indicate the click volume or transaction volume of the first type of supply at the supply location within the historical time window.

[0145] The historical time window is, for example, the last 30 days, 7 days, etc. The longer the historical time window is set, the richer the historical behavior data is, so that the first beta distribution and the second beta distribution determined by the transportation platform based on the historical information are more accurate, thereby improving the accuracy of the source recommendation.

[0146] For example, if the user clicks on the first type of supply at supply location 1 100 times in the past 30 days, then the first statistic is 100 times.

[0147] The second statistic is used to indicate the click volume or transaction volume of the second type of supply at the supply location within the historical time window.

[0148] The second behavior data includes a third statistic and a fourth statistic.

[0149] The third statistic is used to indicate the exposure of the first type of supply at the supply location within the historical time window.

[0150] For example, if the first type of source at source position 1 is exposed to users 100 times in the past 30 days, then the third statistic is 100 times.

[0151] The fourth statistic is used to indicate the exposure of the second type of supply at the supply location within the historical time window.

[0152] Based on the above exemplary description, in S102, the transportation platform may establish a first Beta distribution and a second Beta distribution corresponding to one or more cargo source locations according to the method shown in S102A below.

[0153] See also Figure 4 , Figure 4 This is a flow chart of a method for recommending a source of goods provided in one embodiment of the present application. Figure 4 As shown, S102 can be implemented by S102A as follows:

[0154] S102A. For each source location, determine a first Beta distribution according to the first statistic and the third statistic, and determine a second Beta distribution according to the second statistic and the fourth statistic.

[0155] Among them, the relationship between the click volume or transaction volume and exposure of a source location can reflect the user's expectation of completing the order for the source of goods at the source location.

[0156] Taking the ratio between the number of clicks and the number of exposures of the first type of supply at a supply source location as an example, the larger the ratio, the higher the user's interest in the first type of supply at the supply source location, that is, the higher the user's expectation of completing the order for the first type of supply at the supply source location. The smaller the ratio, the lower the user's interest in the first type of supply at the supply source location, that is, the lower the user's expectation of completing the order for the first type of supply at the supply source location.

[0157] Based on this, the transportation platform determines the first Beta distribution for each source location according to the first statistic and the third statistic, and determines the second Beta distribution according to the second statistic and the fourth statistic, so that when making source recommendations, it can refer to the user's expectation for the completion of the first type of source at a source location within the historical time window, and the user's expectation for the completion of the second type of source at a source location, so that when making source recommendations, more suitable sources of goods can be recommended to users to increase the transaction rate of the sources of goods.

[0158] Based on the above exemplary description, in S102A, the transportation platform may establish a first Beta distribution and a second Beta distribution corresponding to one or more cargo source locations according to the following method.

[0159] The transportation platform determines the first statistic as the first parameter of the first Beta distribution, and determines the difference between the third statistic and the first statistic as the second parameter of the first Beta distribution, thereby obtaining the first Beta distribution. The transportation platform determines the second statistic as the third parameter of the second Beta distribution, and determines the difference between the fourth statistic and the second statistic as the fourth parameter of the second Beta distribution, thereby obtaining the second Beta distribution.

[0160] Among them, the first parameter is α of the first beta distribution, and the second parameter is β of the first beta distribution.

[0161] Among them, the third parameter is α of the second beta distribution, and the fourth parameter is β of the second beta distribution.

[0162] Assume that the first statistic is D novelty , the second statistic is D non-novelty , the third statistic is B novelty , the fourth statistic is B non-novelty .

[0163] Then the first beta distribution of the transportation platform can be obtained as: Beta(D novelty , B novelty -D novelty ). The second beta distribution is: Beta(D non-novelty , B non-novelty -D non-novelty ).

[0164] According to the expected value formula of the Beta distribution: α / (α+β), the expected value of the first Beta distribution is D novelty / B novelty , that is, the ratio between the click volume / transaction volume and exposure of the first type of source, and the expected value of the second beta distribution is D non-novelty / B non-novelty , that is, the ratio between the click volume / transaction volume and exposure of the second type of supply.

[0165] In the exploration phase of the Beta distribution, when α+β is small, that is, when the exposure is small, the Beta distribution is wide, and the random number obtained according to the Beta distribution may be large. Then, for the first Beta distribution, the probability that the user clicks / trades the first type of source is also large, and for the second Beta distribution, the probability that the user clicks / trades the second type of source is also large.

[0166] In the utilization stage of the Beta distribution, when α+β is large, that is, when the exposure is large, the Beta distribution is very narrow, the expectation of completing the order is relatively certain, and the random number obtained according to the Beta distribution will basically fall near the average expectation. At this time, if α / (α+β) is close to 1, then for the first Beta distribution, the probability of users clicking / trading the first type of source is also high, and for the second Beta distribution, the probability of users clicking / trading the second type of source is also high.

[0167] On the contrary, if α / (α+β) is close to 0, then for the first beta distribution, the probability of a user clicking on / transacting the first type of supply is also smaller, and for the second beta distribution, the probability of a user clicking on / transacting the second type of supply is also smaller.

[0168] Based on this, the first Beta distribution and the second Beta distribution can be used to fit the user's order completion expectations for the first type of source of goods and the order completion expectations for the second type of source of goods at the source location, thereby helping to improve the accuracy of the transportation platform's source recommendations based on the first Beta distribution and the second Beta distribution.

[0169] Based on the above exemplary description, in S104A, the transportation platform may update the parameters of the first Beta distribution and the parameters of the second Beta distribution corresponding to the cargo source location according to the methods shown in S201 to S207 below.

[0170] See also Figure 5 , Figure 5 A flow chart of a method for updating parameters of a first beta distribution and parameters of a second beta distribution provided in one embodiment of the present application. Figure 5 As shown, the method includes:

[0171] S201. Determine whether first operation information is received within a third time period.

[0172] If the first operation information is received, S202 is executed; if the first operation information is not received, S205 is executed.

[0173] There are multiple situations for the first operation information.

[0174] In some examples, the first operation information is used to instruct the user to click on the source of supply at the source location.

[0175] In other examples, the first operation information is used to indicate the source of goods of the source location formed by the user.

[0176] Among them, the third time period is a period of time after the first source of supply or the second source of supply is recommended through the source location.

[0177] After recommending the first or second source of goods through the source location, the transportation platform can record the user's behavioral operations at the source location. Thus, the transportation platform can iteratively update the first Beta distribution and the second Beta distribution based on the user's behavioral operations at the source location. That is, in each iteration, the parameters of the first Beta distribution and the parameters of the second Beta distribution are corrected according to the user's behavioral operations at the source location, so that each source recommendation based on the first Beta distribution and the second Beta distribution is more accurate.

[0178] If the transportation platform receives the first operation information, the click volume or transaction volume of the first type of source or the second type of source of goods at the source location increases. If the transportation platform does not receive the first operation information, the first type of source or the second type of source of goods at the source location is only exposed to the user, that is, the exposure volume of the first type of source or the second type of source of goods at the source location increases.

[0179] S202: Determine whether the source of goods at the source location is the first source of goods.

[0180] If the source of goods at the source location is the first source of goods, execute S203; if the source of goods at the source location is not the first source of goods, that is, the source of goods at the source location is the second source of goods, execute S204.

[0181] S203: Update the first parameter according to the first preset coefficient.

[0182] When the transportation platform receives the first operation information and the source of goods at the source location is the first source of goods, the click volume or transaction volume of the first type of source of goods at the source location increases. Based on this, the transportation platform can update the first parameter according to the first preset coefficient.

[0183] The first preset coefficient is, for example, 1. For example, if the first operation information indicates that the number of clicks on the source of goods at the source location is 2, then the transportation platform will distribute the first Beta distribution: Beta (D novelty , B novelty -D novelty ) novelty Increase by 2.

[0184] S204: Update the third parameter according to the second preset coefficient.

[0185] When the transportation platform receives the first operation information and the source of goods at the source location is the second source of goods, the click volume or transaction volume of the second type of source of goods at the source location increases. Based on this, the transportation platform can update the third parameter according to the second preset coefficient.

[0186] The second preset coefficient is, for example, 1. For example, if the first operation information indicates that the number of clicks on the source of goods at the source location is 2, then the transportation platform will distribute the second Beta distribution: Beta (D non-novelty, B non-novelty -D non-novelty ) non-novelty Increase by 2.

[0187] S205. Determine whether the source of goods at the source location is the first source of goods.

[0188] If the source of goods at the source location is the first source of goods, execute S206; if the source of goods at the source location is not the first source of goods, that is, the source of goods at the source location is the second source of goods, execute S207.

[0189] S206: Update the second parameter according to the third preset coefficient and the exposure information.

[0190] The exposure information is used to indicate the exposure of the source of goods at the source location within the third time period.

[0191] When the transportation platform does not receive the first operation information and the source of goods at the source location is the first source of goods, the exposure of the first type of source of goods at the source location increases. Based on this, the transportation platform can update the second parameter according to the third preset coefficient and exposure information.

[0192] The third preset coefficient is, for example, 1. For example, if the exposure information indicates that the exposure amount of the source of the source location in the third time period is 2 times, then the transportation platform will distribute the first beta: Beta (D novelty , B novelty -D novelty ) novelty Increase by 2.

[0193] S207: Update a fourth parameter according to a fourth preset coefficient and exposure information.

[0194] When the transportation platform does not receive the first operation information and the source of goods at the source location is the second source of goods, the exposure of the second type of source of goods at the source location increases. Based on this, the transportation platform can update the fourth parameter according to the fourth preset coefficient and exposure information.

[0195] The fourth preset coefficient is, for example, 1. For example, if the exposure information indicates that the exposure amount of the source of the source location in the third time period is 2 times, then the transportation platform will distribute the second Beta: Beta (D non-novelty , B non-novelty -D non-novelty ) non-novelty Increase by 2.

[0196] Based on this, the transportation platform iteratively updates the first Beta distribution and the second Beta distribution according to the number of clicks or transaction volume and exposure of the source location. That is, in each iteration, the user's preference for the source location is taken into account, and the parameters of the first Beta distribution and the second Beta distribution are corrected to improve the accuracy of each source recommendation based on the first Beta distribution and the second Beta distribution, thereby helping to improve the accuracy of the transportation platform's source recommendation based on the first Beta distribution and the second Beta distribution.

[0197] Based on the above exemplary description, in S103, the transport platform can be as follows: Figure 6 The method shown recommends the first source of supply or the second source of supply by the source location.

[0198] See also Figure 6 , Figure 6 A flowchart of a method for recommending a first source of goods or a second source of goods by the source location provided in an embodiment of the present application. Figure 6 As shown, the method includes:

[0199] S301. Determine a first expectation according to a first beta distribution, and determine a second expectation according to a second beta distribution.

[0200] Specifically, for each cargo source location, the transportation platform may determine the expected value of the first Beta distribution as the first expectation, and determine the expected value of the second Beta distribution as the second expectation.

[0201] The first expectation can reflect the user's expectation of completing the order of the first type of goods, and the second expectation can reflect the user's expectation of completing the order of the second type of goods.

[0202] S302: Determine whether the first expectation is greater than the second expectation.

[0203] If the first expectation is greater than the second expectation, S303 is executed; if the first expectation is less than or equal to the second expectation, S304 is executed.

[0204] If the first expectation is greater than the second expectation, it means that for the supply location, the user's expectation of completing the order for the first type of supply is higher than the expectation of completing the order for the second type of supply. Based on this, the transportation platform can update the supply of the supply location to the first type of supply.

[0205] If the first expectation is less than or equal to the second expectation, it means that for the supply location, the user's expectation of completing the order for the second type of supply is higher than the expectation of completing the order for the first type of supply. Based on this, the transportation platform can update the supply of the supply location to the second type of supply.

[0206] S303, inserting the first source of goods into the source of goods position.

[0207] Among them, the type of the first source of goods is the first type.

[0208] Based on this, the transportation platform can recommend the first source of goods by the source location, so that the user can select the first source of goods at the source location. The first source of goods is the first type of source of goods that the user prefers more, which helps to improve the transaction rate and transaction speed of the source of goods.

[0209] S304: insert a second source of goods into the source of goods position, or keep the source of goods at the source of goods position unchanged.

[0210] Among them, the type of the second source of goods is the second type.

[0211] Taking into account that the supply at the supply location has been exposed to users before the supply is recommended through the supply location, that is, the supply at the supply location is the second type of supply, then the transportation platform can also keep the supply at the supply location unchanged.

[0212] Based on this, the transportation platform can recommend a second source of goods by the source location, so that the user can select a second source of goods at the source location. The second source of goods is the second type of source of goods that the user prefers more, which helps to improve the transaction rate and transaction speed of the source of goods.

[0213] Based on the above exemplary description, before inserting the source of goods into the source of goods location, the transportation platform can Figure 7 The method shown determines a first source of supply and a second source of supply.

[0214] See also Figure 7 , Figure 7 A flow chart of a method for determining the source of goods provided in one embodiment of the present application. Figure 7 As shown, the method includes:

[0215] S401. Obtain the search conditions at the current moment.

[0216] The search condition is used to indicate the properties of the source of goods required by the user.

[0217] Among them, the search conditions include departure place, destination, route, cargo type, required vehicle length and required vehicle type, etc. Users can set search conditions according to their cargo search needs.

[0218] S402. Determine the supply source whose attributes meet the search criteria as the third supply source.

[0219] The transportation platform obtains the search conditions at the current moment, so that it can filter the sources of goods according to the search conditions and determine the third sources of goods that meet the search conditions, thereby ensuring that the sources of goods recommended to users meet the users' search needs and improving the user experience.

[0220] S403. Determine the fourth source of goods and the fifth source of goods based on the third source of goods.

[0221] Among them, the fourth source of goods includes the sources of goods in the third source that have not been exposed within the first period of time.

[0222] Among them, the fifth source of goods includes the sources of goods in the third source that have been exposed within the first period of time.

[0223] There are unexposed sources and exposed sources among the third sources. Based on this, the transportation platform subdivides the third sources into two parts to facilitate the accurate selection of unexposed sources and exposed sources from the third sources.

[0224] S404. Determine one of the fourth sources of supply as the first source of supply, and determine one of the fifth sources of supply as the second source of supply.

[0225] The transportation platform can randomly select a source of goods from the fourth source of goods as the first source of goods, and randomly select a source of goods from the fifth source of goods as the second source of goods, so as to accurately recommend sources of goods to users.

[0226] Figure 8 This is a schematic diagram of the structure of a supply recommendation device provided in one embodiment of the present application. Figure 8 As shown, the device includes: an acquisition module 101, a creation module 102, a recommendation module 103 and an update module 104.

[0227] An acquisition module 101 is used to acquire historical information of a supply source list, where the supply source list includes one or more supply source locations, and the historical information includes historical behavior data corresponding to the one or more supply source locations, where the historical behavior data is used to indicate historical behavior statistics corresponding to the supply source locations;

[0228] Establishing module 102, used to establish a first beta distribution and a second beta distribution corresponding to one or more supply source locations respectively according to historical information, the first beta distribution is used to indicate the expected distribution of completed orders of a first type of supply source, and the second beta distribution is used to indicate the expected distribution of completed orders of a second type of supply source, the first type of supply source is an unexposed supply source, and the second type of supply source is an exposed supply source;

[0229] The recommendation module 103 is used to recommend a first source of goods or a second source of goods according to the first beta distribution and the second beta distribution corresponding to each source of goods location, wherein the first source of goods is a source of goods that has not been exposed in the first time period, and the second source of goods is a source of goods that has been exposed in the first time period;

[0230] The updating module 104 is used to update the supply of the supply location in real time according to the received operation information of the supply location.

[0231] It should be noted that the supply recommendation device of the embodiment of the present application can be used to execute the technical solution of the above-mentioned method embodiment, and its implementation principle and technical effect are similar, which will not be repeated here.

[0232] In some examples, the update module 104 is specifically configured to:

[0233] For each supply source location, update the parameters of the first beta distribution and the parameters of the second beta distribution corresponding to the supply source location according to the received operation information of the supply source location;

[0234] After the second period of time, or when the refresh information is received, the first source of supply or the second source of supply is recommended based on the first Beta distribution and the second Beta distribution corresponding to the source of supply location, and the refresh information is used to refresh the source list.

[0235] In some examples, the historical behavior data includes first behavior data and second behavior data;

[0236] The first behavior data includes a first statistic and a second statistic, the first statistic is used to indicate the click volume or transaction volume of a first type of supply at the supply location within the historical time window, and the second statistic is used to indicate the click volume or transaction volume of a second type of supply at the supply location within the historical time window;

[0237] Among them, the second behavior data includes a third statistic and a fourth statistic. The third statistic is used to indicate the exposure of the first type of source of supply at the source location within the historical time window, and the fourth statistic is used to indicate the exposure of the second type of source of supply at the source location within the historical time window.

[0238] In some examples, the module 102 is established to:

[0239] For each source location, a first Beta distribution is determined based on the first statistic and the third statistic, and a second Beta distribution is determined based on the second statistic and the fourth statistic.

[0240] In some examples, the module 102 is established to:

[0241] Determine the first statistic as a first parameter of a first Beta distribution, determine the difference between the third statistic and the first statistic as a second parameter of the first Beta distribution, and obtain a first Beta distribution;

[0242] The second statistic is determined as the third parameter of the second Beta distribution, and the difference between the fourth statistic and the second statistic is determined as the fourth parameter of the second Beta distribution, so as to obtain the second Beta distribution.

[0243] In some examples, the update module 104 is specifically configured to:

[0244] In the case where the first operation information is received within the third time period, when the supply at the supply source location is the first supply source, the first parameter is updated according to the first preset coefficient, and the first operation information is used to instruct the user to click on the supply at the supply source location, or the first operation information is used to instruct the user to become the supply at the supply source location;

[0245] When the source of goods at the source location is the second source of goods, updating the third parameter according to the second preset coefficient;

[0246] In the case where the first operation information is not received within the third time period, when the source of goods at the source location is the first source of goods, the second parameter is updated according to the third preset coefficient and the exposure information, where the exposure information is used to indicate the exposure of the source of goods at the source location within the third time period;

[0247] When the source of goods at the source location is the second source of goods, the fourth parameter is updated according to the fourth preset coefficient and the exposure information.

[0248] In some examples, the recommendation module 103 is specifically configured to:

[0249] determining a first expectation based on a first beta distribution and determining a second expectation based on a second beta distribution;

[0250] When the first expectation is greater than the second expectation, insert the first source of goods into the source position, and the type of the first source of goods is the first type;

[0251] When the first expectation is less than or equal to the second expectation, a second source of goods is inserted into the source position, and the type of the second source of goods is the second type, or the source of goods at the source position is kept unchanged.

[0252] In some examples, the recommendation module 103 is further configured to:

[0253] Get the current search conditions, which are used to indicate the properties of the source of goods required by the user;

[0254] Determine the supply sources whose attributes meet the search conditions as the third supply sources;

[0255] According to the third source, the fourth source and the fifth source are determined. The fourth source includes the sources of the third source that have not been exposed in the first period of time, and the fifth source includes the sources of the third source that have been exposed in the first period of time;

[0256] One of the fourth sources of supply is determined as the first source of supply, and one of the fifth sources of supply is determined as the second source of supply.

[0257] Fig. 9 This is a schematic diagram of the structure of an electronic device provided by an embodiment of the present application. Fig. 9As shown, the electronic device may include: a processor 201 and a memory 202, wherein the memory 202 stores a computer program, and when the processor 201 executes the computer program, the embodiment of the present application is implemented. Figures 1 to 7 Recommended method of sourcing shown.

[0258] Fig.10 This is a schematic diagram of the structure of an electronic device provided by an embodiment of the present application. Fig.10 As shown, the electronic device may include: a processor 301, and when the processor 301 executes a computer executable program or an instruction in a memory to execute a computer program, the embodiment of the present application is implemented. Figures 1 to 7 Recommended method of sourcing shown.

[0259] Another embodiment of the present application further provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the present application can be implemented. Figures 1 to 7 Recommended method of sourcing shown.

[0260] Another embodiment of the present application further provides a computer program product, including: an execution instruction, the execution instruction is stored in a readable storage medium, at least one processor of the electronic device can read the execution instruction from the readable storage medium, and at least one processor executes the execution instruction so that the electronic device implements the embodiment of the present application Figures 1 to 7 Recommended method of sourcing shown.

[0261] In the several embodiments provided in this application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic, for example, the division of modules or units is only a logical function division, and there may be other division methods in actual implementation, for example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed.

[0262] Those skilled in the art will appreciate that, although some embodiments herein include certain features included in other embodiments, the combination of features of different embodiments is meant to be within the scope of the present application and form different embodiments. For example, in the claims, any one of the claimed embodiments may be used in any combination.

[0263] As described above, the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A method for recommending a source of goods, characterized in that: The method comprises: Acquire historical information of a supply source list, the supply source list including one or more supply source locations, the historical information including historical behavior data corresponding to the one or more supply source locations, the historical behavior data being used to indicate historical behavior statistics corresponding to the supply source locations; According to the historical information, a first beta distribution and a second beta distribution are established corresponding to the one or more supply source locations, respectively, wherein the first beta distribution is used to indicate the expected distribution of completed orders of a first type of supply source, and the second beta distribution is used to indicate the expected distribution of completed orders of a second type of supply source, wherein the first type of supply source is an unexposed supply source, and the second type of supply source is an exposed supply source; For each of the supply source positions, according to the first beta distribution and the second beta distribution corresponding to the supply source position, recommend a first supply source or a second supply source through the supply source position, wherein the first supply source is a supply source that has not been exposed within the first time period, and the second supply source is a supply source that has been exposed within the first time period; According to the received operation information of the source location, the source of goods at the source location is updated in real time.

2. The method according to claim 1, characterized in that The step of updating the supply of the supply location in real time according to the received operation information of the supply location includes: For each of the supply source locations, updating the parameters of the first Beta distribution and the parameters of the second Beta distribution corresponding to the supply source location according to the received operation information of the supply source location; After a second period of time, or when refresh information is received, the first source of supply or the second source of supply is recommended through the source of supply location according to the first Beta distribution and the second Beta distribution corresponding to the source of supply location, and the refresh information is used to refresh the source of supply list.

3. The method according to claim 1 or 2, characterized in that: The historical behavior data includes first behavior data and second behavior data; The first behavior data includes a first statistic and a second statistic, the first statistic is used to indicate the number of clicks or transaction volume of the first type of supply at the supply location within the historical time window, and the second statistic is used to indicate the number of clicks or transaction volume of the second type of supply at the supply location within the historical time window; Among them, the second behavior data includes a third statistic and a fourth statistic, the third statistic is used to indicate the exposure of the first type of source of supply at the source location within the historical time window, and the fourth statistic is used to indicate the exposure of the second type of source of supply at the source location within the historical time window.

4. The method according to claim 3, characterized in that: The establishing, according to the historical information, a first Beta distribution and a second Beta distribution corresponding to the one or more supply source locations respectively, comprises: For each of the source locations, the first Beta distribution is determined according to the first statistic and the third statistic, and the second Beta distribution is determined according to the second statistic and the fourth statistic.

5. The method according to claim 4, characterized in that The step of determining the first Beta distribution according to the first statistic and the third statistic for each of the source locations, and determining the second Beta distribution according to the second statistic and the fourth statistic, comprises: Determine the first statistic as a first parameter of the first Beta distribution, determine the difference between the third statistic and the first statistic as a second parameter of the first Beta distribution, and obtain the first Beta distribution; The second statistic is determined as the third parameter of the second Beta distribution, and the difference between the fourth statistic and the second statistic is determined as the fourth parameter of the second Beta distribution, so as to obtain the second Beta distribution.

6. The method according to claim 5, characterized in that The updating of the first beta distribution parameter and the second beta distribution parameter corresponding to each of the supply source locations according to the received operation information of the supply source location includes: In the case where the first operation information is received within the third time period, when the supply at the supply source location is the first supply source, the first parameter is updated according to the first preset coefficient, and the first operation information is used to instruct the user to click on the supply at the supply source location, or the first operation information is used to instruct the user to trade the supply at the supply source location; When the source of goods at the source location is the second source of goods, updating the third parameter according to the second preset coefficient; In the case where the first operation information is not received within the third time period, when the source of goods at the source location is the first source of goods, updating the second parameter according to a third preset coefficient and exposure information, wherein the exposure information is used to indicate the exposure of the source of goods at the source location within the third time period; When the source of goods at the source location is the second source of goods, the fourth parameter is updated according to a fourth preset coefficient and the exposure information.

7. The method according to any one of claims 4 to 6, characterized in that: The recommending, for each of the supply source locations, a first supply source or a second supply source according to the supply source location according to the first beta distribution and the second beta distribution corresponding to the supply source location, comprises: determining a first expectation according to the first beta distribution, and determining a second expectation according to the second beta distribution; When the first expectation is greater than the second expectation, inserting a first source of goods into the source position, the type of the first source of goods being the first type; When the first expectation is less than or equal to the second expectation, a second source of goods is inserted into the source position, and the type of the second source of goods is the second type, or the source of goods at the source position is kept unchanged.

8. The method according to claim 7, characterized in that The method further comprises: Obtaining the search conditions at the current moment, wherein the search conditions are used to indicate the attributes of the source of goods required by the user; Determine the supply source whose attributes meet the search conditions as the third supply source; Determine a fourth source of goods and a fifth source of goods according to the third source of goods, wherein the fourth source of goods includes the sources of goods in the third source of goods that have not been exposed within the first time period, and the fifth source of goods includes the sources of goods in the third source of goods that have been exposed within the first time period; One of the fourth sources of supply is determined as the first source of supply, and one of the fifth sources of supply is determined as the second source of supply.

9. An electronic device, characterized in that: The method comprises a memory and a processor, wherein the memory stores a computer program that can be run on the processor, and when the processor executes the program, the method according to any one of claims 1 to 8 is implemented.

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 method according to any one of claims 1 to 8 is implemented.

Images