A media information recommendation method and device

Abstract

The application relates to a media information recommendation method and device, wherein the method comprises the following steps: receiving a media information acquisition request of a media information display end; acquiring environment information, wherein the environment information comprises information of an environment determined by a geographical position; generating a respective recommendation value of each to-be-recommended media information, wherein the recommendation value is obtained according to a first value and a second value of the to-be-recommended media information, the first value is obtained according to a first matching degree between the environment information and product information of a to-be-determined product, and the second value represents a second matching degree between the to-be-determined product and user willingness represented by event information; and determining target media information from the to-be-recommended media information according to the recommendation value of each to-be-recommended media information. On one hand, the target media information recommended to the user can reflect subjective demands of the user; on the other hand, the target media information determined in combination with the environment information is suitable for the environment where the user is located, and can meet objective demands of the user.

Description

Technical Field

[0001] This application relates to the field of data processing technology, and in particular to a media information recommendation method and apparatus. Background Technology

[0002] With the development of the internet, people are becoming increasingly reliant on it, and their daily lives, including clothing, food, housing, and transportation, are often inextricably linked to mobile applications. In order to better serve users, data tracking technology has emerged.

[0003] Tracking data can be used to recommend media information. However, while recommending media information to users based on tracking data can ensure that the recommended media information matches the user's subjective wishes, it is difficult to guarantee the user experience when using the product corresponding to the media information after the user purchases it. Summary of the Invention

[0004] This application provides a media information recommendation method and apparatus to solve the problem that the media data recommended to users in the prior art is difficult to meet the objective needs of users.

[0005] In a first aspect, this application provides a media information recommendation method, which includes: receiving a media information acquisition request from a media information display terminal; acquiring environmental information, wherein the environmental information includes information about the environment determined by geographical location; generating a recommendation value for each piece of media information to be recommended, wherein the recommendation value represents the degree to which the media information to be recommended is suitable as target media information, the recommendation value is obtained based on a first value and a second value of the media information to be recommended, the first value is obtained based on a first matching degree between the environmental information and product information of the product to be determined, the product to be determined is the product corresponding to the media information to be recommended, the second value represents a second matching degree between the product to be determined and the user's intention represented by event information, the event information is information collected based on preset embedded points on the media information display terminal; and determining target media information from the media information to be recommended based on the recommendation value of each piece of media information to be recommended, wherein the target media information is the media information to be recommended to be sent to the media information display terminal.

[0006] In an optional embodiment of this specification, the event information includes at least one of the following: information about an initialization event, information about an operation event, environmental information including actual climate information of the user's geographical location, and product information including reference climate information, which indicates the applicable climate of the product corresponding to the media information to be recommended. Determining the first value includes: when the event information includes information about an initialization event, using the geographical location information parsed from the initialization event information as the target location information; obtaining the actual climate information of the target location from a climate information data source based on the target location information; and determining the first value based on a first matching degree between the actual climate information and the reference climate information.

[0007] In an optional embodiment of this specification, determining a first value based on a first degree of matching between actual climate information and reference climate information includes: determining a first weight value based on the granularity value of the target location, wherein the first weight value is negatively correlated with the granularity value; and weighting the first degree of matching between the actual climate information and the reference climate information using the first weight value to obtain the first value.

[0008] In an optional embodiment of this specification, determining the second value includes: determining the second value based on at least one of the following: the number of times a specified user clicks on the reference media information, the duration of the user browsing the reference media information, and the number of times the user shares the reference media information, wherein the reference media information is historical media information that has been shown to the user in the past and whose first matching degree with the media information to be recommended is greater than a first matching degree threshold.

[0009] In an optional embodiment of this specification, the method further includes, before determining the second value: after each shared reference media information, if specified information is received from the receiving end of the shared reference media information, the number of times the specified user shares the reference media information is weighted using a specified weight to obtain a weighted number, wherein the specified weight is greater than 1 and positively correlated with the duration, and the specified information is sent when the receiving end of the shared reference media information detects an operation event on the shared reference media information; determining the second value includes: using the sum or product of the number of times the specified user clicks the reference media information, the duration of the specified user browsing the reference media information, and the weighted number, as the second alignment degree; and processing the second alignment degree using a Sigmoid function to obtain the second value.

[0010] In an optional embodiment of this specification, generating recommendation values ​​for each piece of media information to be recommended includes at least one of the following:

[0011] Obtain the historical user satisfaction with the product corresponding to the recommended media information as the third value; generate the recommendation value for each media information to be recommended based on the first, second, and third values ​​of the media information to be recommended.

[0012] The product recommendation score is extracted from the media information to be recommended and used as the fourth value. The product recommendation score is the data added to the media information to be recommended when it is generated. Based on the first, second and fourth values ​​of the media information to be recommended, the recommendation values ​​of each media information are generated.

[0013] In an optional embodiment of this specification, after determining the target media information from the media information to be recommended, the method further includes: sending the target media information to the media information display terminal.

[0014] Secondly, this application provides a media information recommendation device, comprising:

[0015] The receiving module is configured to receive media information acquisition requests.

[0016] The acquisition module is configured to acquire environmental information and event information. The environmental information includes information about the environment determined by the geographical location, and the event information is information collected based on preset embedded points.

[0017] The generation module is configured to generate recommendation values ​​for each piece of media information to be recommended. The recommendation value indicates the degree to which the media information to be recommended is suitable as target media information. The recommendation value is obtained based on the first value and the second value of the media information to be recommended. The first value is obtained based on the first matching degree between environmental information and product information of the product to be determined. The product to be determined is the product corresponding to the media information to be recommended. The second value indicates the second matching degree between the product to be determined and the user's intention indicated by the event information.

[0018] The target media information determination module is configured to determine the target media information from each piece of media information to be recommended based on the recommendation value of each piece of media information to be recommended.

[0019] Thirdly, this application provides an electronic device, including a processor, a communication interface, a memory, and a communication bus, wherein the processor, the communication interface, and the memory communicate with each other through the communication bus;

[0020] Memory, used to store computer programs;

[0021] When a processor executes a program stored in memory, it implements the steps of any media information recommendation method in the first aspect.

[0022] Fourthly, this application provides a computer-readable storage medium having a computer program stored thereon, characterized in that, when the computer program is executed by a processor, it implements the steps of any media information recommendation method in the first aspect.

[0023] The technical solutions provided in this application have the following advantages compared with the prior art:

[0024] The media information recommendation method and apparatus described in this specification, on the one hand, determine the target media information to be recommended to the user based on event information collected by embedded points, so that the target media information recommended to the user can reflect the user's subjective needs; on the other hand, the target media information determined by combining environmental information is also suitable for the user's environment and can meet the user's objective needs, so that the user can have a better user experience when using the product corresponding to the target media information. Attached Figure Description

[0025] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with the invention and, together with the description, serve to explain the principles of the invention.

[0026] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, for those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0027] Figure 1 A schematic diagram illustrating a scenario involving a media information recommendation process provided in an embodiment of this application;

[0028] Figure 2 A flowchart illustrating a media information recommendation process provided in an embodiment of this application;

[0029] Figure 3 A flowchart illustrating a media information recommendation process provided in an embodiment of this application;

[0030] Figure 4 This is a diagram illustrating the process of deriving a recommended value from each individual value.

[0031] Figure 5 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Detailed Implementation

[0032] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0033] In media data recommendation scenarios, media data recommendation platforms often acquire user operation information by setting up tracking points in the client-side to infer user preferences. Then, based on these preferences, they recommend media information to the user. On the one hand, user preferences are determined by subjective factors, and media data recommendation methods in related technologies can, to a certain extent, ensure that the recommended media information matches user preferences. On the other hand, user preferences are usually highly subjective and may not always meet objective needs. If media information is used to recommend products to users, and the user purchases the product based on the recommended media information, but the product does not actually meet the user's objective needs, it may lead to a poor user experience.

[0034] In view of this, this specification provides a media data recommendation process that ensures the recommended media data meets both the user's subjective and objective needs. The media data recommendation process in this specification is executed by a media data recommendation server, and the scenarios involved are as follows: Figure 1 As shown. In Figure 1 In the scenario shown, the media data recommendation server is connected to media information display terminals 1 through n via communication connections. The communication between one (any) media information display terminal and the media data recommendation server will now be explained using an example.

[0035] like Figure 2 As shown, the media information recommendation method and apparatus in this specification include the following steps:

[0036] S200: Receives media information acquisition requests from the media information display terminal.

[0037] In this specification, the media information retrieval request is sent from the media information display terminal to the media data recommendation server. In an optional embodiment of this specification, the media information retrieval request is generated by an initialization event and / or operation event detected by the media information display terminal.

[0038] S202: Obtain environmental information.

[0039] The process described in this specification aims to identify media information to be recommended to a user (hereinafter referred to as "target media information"). A user is the object that views the media information. In this specification, a user can be a specific user, such as Zhang San; or it can be a group of users that can be characterized by the same user profile, such as: [Age between 20 and 40 years old, male, cumulative online time exceeding 20 hours].

[0040] The environmental information in this specification represents the attributes of the user's environment. This environment may be determined by geographical location factors. Some of the environmental attributes may change over time, and therefore the environmental information may also change over time. The environmental attributes may include several dimensions, and the sources of environmental information corresponding to different dimensions may be different; therefore, the environmental information in this specification may be obtained from different data sources.

[0041] For example, the dimensions of environmental attributes may include at least one of the following: actual climate information (which can represent the climate conditions of the user's geographical location), and geographical location information (used to identify the user's geographical location). Figure 1 As shown, actual climate information is obtained from climate information data sources (e.g., weather stations).

[0042] In order to ensure that the target media information obtained through the process of this specification can objectively reflect the objective needs of users, environmental information can represent the pattern of environmental changes over a relatively long period of time (e.g., the southern region is generally humid), and / or, environmental information can represent the environmental changes over a relatively short period of time from the current moment (e.g., although the southern region is generally humid, this year is relatively dry and not as humid as in previous years).

[0043] The event information in this specification can be represented by data collected by the client when executing preset event tracking points in the client. In an optional embodiment of this specification, events may include initialization events, operation events, etc. Operation events may include click events, browsing events, sharing events, etc. Specifically, media information retrieval requests can be parsed to obtain event information. In other optional embodiments, some event information is obtained from media information retrieval requests, while other event information from relatively distant historical periods can be obtained by the media data recommendation server from storage media.

[0044] S204: Generate recommendation values ​​for each piece of media information to be recommended.

[0045] The recommended values ​​in this specification indicate the degree to which the recommended media information is suitable as the target media information. The higher the recommended value, the more suitable the recommended media information is as the target media information.

[0046] The process described in this manual can determine the recommendation value for each piece of media information to be recommended, individually. The following explanation uses any one piece of media information from the list of recommended media information as an example to illustrate how to obtain its recommendation value.

[0047] In an optional embodiment of this specification, firstly, the product corresponding to the media information to be recommended is identified as the product to be determined. Then, the product information of the product to be determined is obtained. This specification does not impose specific limitations on how the product information is obtained. For example, the media information to be recommended can be parsed to obtain the product information, or the product information can be found in a product information database based on the identifier of the product to be determined. Afterward, a first matching degree between the product information and the environmental information is determined. Optionally, the determined similarity can be directly used as the first value. Further optionally, after obtaining the similarity of each piece of media information to be recommended, each similarity can be processed (e.g., normalization), and the result of each similarity processing can be used as the first value of the corresponding media information to be recommended.

[0048] The first value indicates the degree to which the media information to be recommended is suitable as target media information from an objective perspective. The higher the first value, the more suitable the media information to be recommended is as target media information from an objective perspective.

[0049] The products mentioned in this manual refer to products whose use is affected by environmental factors, or products whose purpose is to change a certain dimension of the environment. The products mentioned in this manual can be physical products, such as air conditioners and humidifiers; in addition, the products mentioned in this manual can also be virtual products, such as a service.

[0050] The product information in this specification indicates that the product is subject to environmental factors (e.g., the product's applicable temperature range, humidity range, etc.), and / or the ability to change a certain dimension of the environment (e.g., the output power range of an air conditioner, etc.).

[0051] In an optional embodiment of this specification, firstly, historical media information that has been shown to the user in the past and whose first matching degree with the media information to be recommended is greater than a first matching degree threshold is selected as reference media information. Then, based on event information, at least one of the following is determined as a reference indicator: the number of times the user clicked the reference media information, the duration of the user's browsing of the reference media information, and the number of times the user shared the reference media information. A second value is obtained based on each reference indicator. For example, the second value can be obtained by summing the various reference indicators; alternatively, the second value can be determined by multiplying the various reference indicators.

[0052] In an optional embodiment of this specification, after each sharing of reference media information, if a specified message is received from the receiving end of the shared reference media information, the number of times the specified user shares the reference media information is weighted using a specified weight to obtain a weighted count. The specified weight is greater than 1 and positively correlated with the duration. When determining the second value, the sum or product of the number of times the specified user clicks the reference media information (represented by the event information), the duration the specified user browses the reference media information, and the weighted count is used as the second alignment degree. The second alignment degree is processed using the Sigmoid function to obtain the second value. The specified message is sent when the receiving end of the shared reference media information detects an operation event related to the shared reference media information.

[0053] The second value reflects the user's subjective needs. The higher the second value, the more suitable the recommended media information is as the target media information in terms of the user's subjective needs.

[0054] After obtaining the first self-scoring value and the second value, a recommended value for the media information to be recommended can be obtained based on the first self-scoring value and the second value. In one optional embodiment of this specification, the sum of the first self-scoring value and the second value can be used as the recommended value; in another optional embodiment of this specification, the product of the first self-scoring value and the second value can be used as the recommended value. It is evident that the recommended value in this specification can be a comprehensive consideration of both subjective factors expressed by the user and objective factors expressed by the environment.

[0055] S206: Based on the recommendation value of each media information to be recommended, determine the target media information from the media information to be recommended.

[0056] After obtaining the recommendation values ​​for each media item to be recommended, the target media item can be determined from among them based on these values. In one optional embodiment of this specification, the one or more media items with the highest recommendation values ​​are determined as the target media item. In another optional embodiment of this specification, the media item with the lowest recommendation value can be excluded, and the remaining media items can be sampled (e.g., randomly sampled) to obtain the target media item, thus giving the target media item a certain degree of randomness and increasing user interest.

[0057] As can be seen, the media information recommendation method in this specification, on the one hand, determines the target media information to be recommended to the user based on the event information collected by the tracking points, so that the target media information recommended to the user can reflect the user's subjective needs; on the other hand, the target media information determined by combining environmental information is also more suitable for the user's environment and can meet the user's objective needs, so that the user can have a better user experience when using the product corresponding to the target media information.

[0058] In one optional embodiment of this specification, after the target media information is determined, the target media information is sent to the user's terminal for the user to view.

[0059] To ensure that the first value expressing objective factors and the second value expressing subjective factors share some commonality and avoid excessive separation between them, in an optional embodiment of this specification, the event information includes information about an initialization event, the environmental information includes actual climate information of the user's geographical location, and the product information includes reference climate information, which indicates the applicable climate for the product corresponding to the media information to be recommended. The process of determining the first value may include: parsing the user's geographical location from the initialization event information as the target location; obtaining actual climate information of the target location from a climate information data source; and determining the first value based on a first degree of matching between the actual climate information and the reference climate information.

[0060] In this embodiment, the geographical location required to determine the environmental information is determined from the event information, which enables the first and second values ​​obtained thereafter to have a certain degree of consistency.

[0061] The climate information (including actual climate information and reference climate information) in this instruction manual may include at least one of the following: temperature information, humidity information, wind information, light intensity information, and whether the environment is indoors or outdoors.

[0062] In real-world scenarios, the configuration of tracking points can be difficult to standardize. Furthermore, the data collected based on these tracking points is susceptible to other factors, resulting in the granularity of the geographic location represented by the initialization event information potentially being either large or small. The granularity indicates the level of detail in the geographic location division; the finer the division, the larger the granularity. For example, the granularity of a province is larger than that of a county. The accuracy of the actual climate information determined based on a geographic location with a larger granularity is lower, because even within a larger granularity geographic location, there may be areas with significantly different actual climate information.

[0063] To ensure that the granularity of geographical location reflects the actual usability of the product in the recommended values, in an optional embodiment of this specification, a first weight value is determined based on the granularity of the target location, wherein the first weight value is negatively correlated with the granularity value. The first weight value is used to weight the first matching degree between the actual climate information and the reference climate information to obtain a first value. Optionally, the first weight value ranges from [0,1].

[0064] In another optional embodiment of this specification, a second weight value is determined based on the time elapsed between the time when the actual climate information was generated and the current time. A first value is obtained by weighting the first matching degree between the actual climate information and the reference climate information using the first weight value and the second weight value. Optionally, the second weight value ranges from [0,1]. The second weight value is negatively correlated with the time elapsed.

[0065] The recommended media information in this manual can express the advertiser's intention to recommend it to users. The recommended media information mainly conveys positive information about the product. However, the actual effect of the product in actual use is often difficult to predict, and the actual effect is difficult to convey from the recommended media information.

[0066] In view of this, in an optional embodiment of this specification, the media data recommendation server obtains the satisfaction level of each historical user with the products corresponding to the recommended media information, as a third value, such as... Figure 3 As shown in the partial content, when there are multiple historical users, the average satisfaction level of each historical user can be determined as the product satisfaction. Then, based on the first, second, and third values ​​of the media information, the recommendation value of the media information to be recommended is obtained. A higher satisfaction level indicates a better user experience with the product.

[0067] For example, the sum of the first, second, and third values ​​can be used as the recommended value. Alternatively, the product of the first, second, and third values ​​can be used as the recommended value.

[0068] In a further optional embodiment of this specification, each historical user and its corresponding geographical location can be determined first (the geographical location of a historical user can be obtained from the shipping address in the order submitted by the historical user for the product corresponding to the information to be recommended), and this location can be designated as a reference location. Then, the satisfaction level of the historical user corresponding to the reference location whose distance from the target location is not greater than a distance threshold (preset value) is used as the satisfaction level when determining the third value.

[0069] In real-world media data delivery scenarios, advertisers and / or media data recommendation services may preferentially prioritize certain media data for recommendation based on preset business rules. For example, the business rule might be that during an event period, media information corresponding to products participating in the event will be prioritized for delivery. The media information to be recommended may include a reference identifier for the event, indicating the event the product corresponding to that media information is participating in.

[0070] In an optional embodiment of this specification, a reference identifier can be identified from the media information to be recommended. It is then determined whether the reference identifier matches the actual identifier of the currently ongoing activity (e.g., identical identifiers are considered a match). If a match is found, the second number is determined as the third weight value; otherwise, the fourth number is determined as the third weight value. The second number is greater than the fourth number. The fourth value is weighted using the third weight value. The fourth value is the product recommendation score, which is data added to the media information to be recommended when generating the media information. The product recommendation score indicates the advertiser's recommendation intent; a higher product recommendation score indicates that the advertiser is more inclined to deliver the media information to users.

[0071] Following the same line of thought, this specification further provides a media information recommendation device, such as... Figure 4 As shown, the media information recommendation device includes one or more of the following modules:

[0072] The receiving module 400 is configured to receive media information acquisition requests from the media information display terminal;

[0073] The acquisition module 402 is configured to include environmental information determined by geographical location.

[0074] The generation module 404 is configured as follows: The recommendation value indicates the degree to which the media information to be recommended is suitable as the target media information. The recommendation value is obtained based on the first value and the second value of the media information to be recommended. The first value is obtained based on the first matching degree of the environmental information and the product information of the product to be determined. The product to be determined is the product corresponding to the media information to be recommended. The second value indicates the second matching degree of the product to be determined and the user's intention indicated by the event information. The event information is based on the information collected from the preset embedding points on the media information display end.

[0075] The target media information determination module 406 is configured to determine the target media information from each media information to be recommended based on the recommendation value of each media information to be recommended. The target media information is the media information to be recommended that is sent to the media information display terminal.

[0076] In an optional embodiment of this specification, the event information includes at least one of the following: information on initialization events, information on operation events, environmental information including actual climate information of the user's geographical location, and product information including reference climate information, which indicates the applicable climate of the product corresponding to the media information to be recommended.

[0077] The generation module 404 is specifically configured as follows: when the event information includes the information of the initialization event, the geographic location information parsed from the initialization event information is used as the target location information; based on the target location information, the actual climate information of the target location is obtained from the climate information data source; and a first value is determined based on the first matching degree between the actual climate information and the reference climate information.

[0078] In an optional embodiment of this specification, the generation module 404 is specifically configured to: determine a first weight value based on the granularity value of the target location, wherein the first weight value is negatively correlated with the granularity value; and use the first weight value to weight the first matching degree of the actual climate information and the reference climate information to obtain a first value.

[0079] In an optional embodiment of this specification, the generation module 404 is specifically configured to: determine a second value based on at least one of the following: the number of times a specified user clicks on the reference media information, the duration of the user browsing the reference media information, and the number of times the user shares the reference media information, wherein the reference media information is historical media information among all historical media information that has been shown to the user in the past, and the first matching degree with the media information to be recommended is greater than a first matching degree threshold.

[0080] In an optional embodiment of this specification, the device further includes a count determination module, configured to, after each shared reference media information, if a specified message is received from the end receiving the shared reference media information, then weight the number of times the specified user shares the reference media information using a specified weight to obtain a weighted count, wherein the specified weight is greater than 1 and positively correlated with the duration, and the specified message is sent when the end receiving the shared reference media information detects an operation event on the shared reference media information.

[0081] The generation module 404 is specifically configured as follows: the sum or product of the number of times the specified user clicked the reference media information, the duration of the specified user's browsing of the reference media information, and the weighted number of clicks, represented by the event information, is used as the second allocation degree; the second allocation degree is processed by the Sigmoid function to obtain the second value.

[0082] In an optional embodiment of this specification, the generation module 404 is specifically configured to: obtain the satisfaction level of each historical user for the product corresponding to the recommended media information as a third value; and generate the recommendation value of each media information to be recommended based on the first value, the second value, and the third value.

[0083] In an optional embodiment of this specification, the generation module 404 is specifically configured to: parse the product recommendation score from the media information to be recommended as the fourth value, wherein the product recommendation score is data added to the media information to be recommended when generating the media information to be recommended; and generate the recommendation value of each media information to be recommended based on the first value, the second value, and the fourth value of the media information to be recommended.

[0084] In an optional embodiment of this specification, the apparatus further includes a sending module configured to send target media information to a media information display terminal.

[0085] like Figure 5 As shown in the figure, this application provides a media information recommendation device, including a processor 111, a communication interface 112, a memory 113, and a communication bus 114, wherein the processor 111, the communication interface 112, and the memory 113 communicate with each other through the communication bus 114.

[0086] Memory 113 is used to store computer programs;

[0087] In one embodiment of this application, when the processor 111 executes the program stored in the memory 113, it implements the media information recommendation control method provided in any of the foregoing method embodiments.

[0088] This application also provides a computer-readable storage medium storing a computer program thereon, which, when executed by a processor, implements the media information recommendation steps provided in any of the foregoing method embodiments.

[0089] It should be noted that, in this document, relational terms such as "first" and "second" are used merely to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusivity, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes the element.

[0090] The above are merely specific embodiments of the present invention, enabling those skilled in the art to understand or implement the invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the invention. Therefore, the present invention is not to be limited to the embodiments shown herein, but is to be accorded the widest scope consistent with the principles and novel features claimed herein.

Claims

1. A media information recommendation method, characterized in that, The method includes: Receive media information retrieval requests from the media information display terminal; Acquire environmental information, wherein the environmental information includes environmental information determined by geographical location, the environmental information representing the pattern of environmental change over a relatively long period of time, and / or representing the environmental change over a relatively short period of time from the current time; Each media information to be recommended is generated with a recommendation value, wherein the recommendation value indicates the degree to which the media information to be recommended is suitable as target media information. The recommendation value is obtained based on a first value and a second value of the media information to be recommended. The first value is obtained based on a first matching degree between the environmental information and the product information of the product to be determined, wherein the product to be determined is the product corresponding to the media information to be recommended. The second value indicates a second matching degree between the product to be determined and the user's intention indicated by event information. The event information is information collected based on preset tracking points on the media information display end. The product information indicates that the product is subject to environmental factors and / or indicates the ability to change a certain dimension of the environment. Based on the recommendation value of each media information to be recommended, target media information is determined from each media information to be recommended, wherein the target media information is the media information to be recommended that is sent to the media information display terminal; The step of determining the target media information from the media information to be recommended includes: excluding the media information with the lowest recommendation value from the media information to be recommended, and randomly sampling the remaining media information to be recommended to obtain the target media information; The event information includes at least one of the following: information about an initialization event and information about an operation event. The product information includes reference climate information, which indicates the applicable climate for the product corresponding to the media information to be recommended. Determining the first value includes: when the event information includes information about an initialization event, using the geographical location information parsed from the initialization event information as the target location information; obtaining the actual climate information of the target location from a climate information data source as the environmental information based on the target location information; and determining the first value based on a first matching degree between the actual climate information and the reference climate information. Determining a first value based on a first matching degree between the actual climate information and the reference climate information includes: determining a first weight value based on the granularity value of the target location, wherein the first weight value is negatively correlated with the granularity value; determining a second weight value based on the time elapsed between the time when the actual climate information was generated and the current time, wherein the second weight value is negatively correlated with the time elapsed; and weighting the first matching degree between the actual climate information and the reference climate information using the first weight value and the second weight value to obtain the first value.

2. The method according to claim 1, characterized in that, Determining the second value includes: A second value is determined based on at least one of the following: the number of times a specified user clicks on the reference media information, the duration of the user browsing the reference media information, and the number of times the user shares the reference media information. The reference media information is historical media information that has been shown to the user in the past and whose matching degree with the media information to be recommended is greater than a first matching degree threshold.

3. The method according to claim 2, characterized in that, Before determining the second value, the method further includes: after each shared reference media information, if a specified message is received from the end receiving the shared reference media information, then a specified weight is used to weight the number of times the specified user shares the reference media information to obtain a weighted number, wherein the specified weight is greater than 1 and positively correlated with the duration, and the specified message is sent when the end receiving the shared reference media information detects an operation event on the shared reference media information; Determining the second value includes: using the sum or product of the number of times the specified user clicked the reference media information, the duration of the specified user's browsing of the reference media information, and the weighted number of clicks as the second matching degree; and processing the second matching degree using the Sigmoid function to obtain the second value.

4. The method according to claim 1, characterized in that, Generate recommendation values ​​for each piece of media information to be recommended, including at least one of the following: The satisfaction level of each historical user with the product corresponding to the media information to be recommended is obtained as a third value. Based on the first value, second value, and third value of the media information to be recommended, generate recommendation values ​​for each of the media information to be recommended. The product recommendation score is parsed from the media information to be recommended and used as the fourth value. The product recommendation score is the data added to the media information to be recommended when the media information to be recommended is generated. Based on the first, second, and fourth values ​​of the media information to be recommended, a recommendation value is generated for each of the media information to be recommended.

5. The method according to claim 1, characterized in that, After determining the target media information from the various media information to be recommended, the method further includes: The target media information is sent to the media information display terminal.

6. A media information recommendation device, used to implement the media information recommendation method as described in any one of claims 1 to 5, characterized in that, The device includes: The receiving module is configured to receive media information acquisition requests. The acquisition module is configured to acquire environmental information and event information, wherein the environmental information includes environmental information determined by geographical location, the event information is information collected based on preset embedded points, and the environmental information represents the environmental change pattern over a relatively long period of time, and / or represents the environmental change over a relatively short period of time from the current moment. The generation module is configured to generate recommendation values ​​for each piece of media information to be recommended, wherein the recommendation value indicates the degree to which the media information to be recommended is suitable as target media information, and the recommendation value is obtained based on a first value and a second value of the media information to be recommended. The first value is obtained based on a first matching degree between the environmental information and the product information of the product to be determined, wherein the product to be determined is the product corresponding to the media information to be recommended, and the second value indicates a second matching degree between the product to be determined and the user's intention indicated by the event information. The product information indicates that the product is subject to environmental factors, and / or indicates the ability to change an attribute of a certain dimension of the environment. The target media information determination module is configured to determine the target media information from each piece of media information to be recommended based on the recommendation value of each piece of media information to be recommended.

7. An electronic device, characterized in that, It includes a processor, a communication interface, a memory, and a communication bus, wherein the processor, the communication interface, and the memory communicate with each other through the communication bus; Memory, used to store computer programs; A processor, when executing a program stored in memory, implements the steps of the media information recommendation method according to any one of claims 1-5.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the media information recommendation method as described in any one of claims 1-5.

Images