A message push method, device and system
By building user portraits with user identity as the center in the knowledge graph, the problem of unstable recommendation accuracy caused by the construction of portraits as units in the existing technology is solved, and more accurate message push is achieved and user experience is improved.
Patent Information
- Application Number
- CN202110166403.3
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2021-02-04
- Publication Date
- 2024-12-03
- Estimated Expiration
- 2041-02-04
AI Technical Summary
In the existing message push technology, there is a problem of inaccurate configuration in building user portraits based on user accounts, resulting in unstable recommendation accuracy, especially when users register multiple accounts.
In the knowledge graph, the user portrait is built with the user identity as the center, and match the relationship between the user identity and the user portrait to push more appropriate recommendation messages for house viewing services.
Improve the accuracy of message recommendations, avoid invalid recommendations caused by inaccurate user portrait configuration, and improve user experience.
Smart Images

Figure CN114520830B_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of Internet, and specifically to a message pushing method, device and system. Background Art
[0002] Nowadays, many applications (Application, APP) launched by major application platforms have instant messaging functions or information push functions to push messages related to application services to users and remind users to handle some matters in the application in a timely manner.
[0003] Generally, applications push messages based on the user accounts logged in to the application. Taking the house viewing application as an example, when a user logs in to his or her user account in the house viewing application installed on the mobile phone, the house viewing application can be triggered by user operations to recommend suitable house viewing services to the user. For the service side, the user can select the appropriate recommended content based on the user's user portrait, and send a recommendation message for the house viewing service containing the recommended content to push the recommended content to the user.
[0004] During the research of existing related technologies, the inventors found that in the existing message push mechanism, user portraits are generally configured based on user accounts. If a user registers multiple user accounts, there may be different user portraits, and different recommended content will be sent respectively. Obviously, due to the inaccurate configuration of user portraits, there is a problem of unstable recommendation accuracy. Summary of the invention
[0005] The present application provides a message push method, device and system for building a user portrait centered on the user identity in a knowledge graph, avoiding the inaccurate configuration caused by building a user portrait centered on the user account in the prior art, and being more in line with the actual situation, thereby improving the recommendation accuracy of messages to a certain extent.
[0006] In a first aspect, the present application provides a method for pushing a message, the method comprising:
[0007] Collecting a user ID from the account information carried by the user account to be pushed, the user account to be pushed is the user account of the house viewing application, the user ID is an ID associated with the user account to be pushed, and the user ID is collected with the user's confirmation;
[0008] Determine the target user profile that matches the user ID based on the knowledge graph, where the knowledge graph is constructed based on the associations between different user IDs and different user profiles;
[0009] Obtain the house viewing service push message adapted to the target user portrait, and push the house viewing service push message to the user account to be pushed. The house viewing service push message includes the recommended content of the house viewing service corresponding to the house viewing application.
[0010] In conjunction with the first aspect of the present application, in a first possible implementation of the first aspect of the present application, the user identifier specifically includes a target mobile phone number of the visiting user, and determining a target user portrait matching the user identifier according to the knowledge graph includes:
[0011] From the different user portraits configured based on different mobile phone numbers in the knowledge graph, determine the target user portrait that is suitable for the target mobile phone number.
[0012] In combination with the first possible implementation of the first aspect of the present application, in the second possible implementation of the first aspect of the present application, the user identification specifically also includes target consumption information and target APP type, and from different user portraits configured based on different mobile phone numbers in the knowledge graph, determining the target user portrait adapted to the target mobile phone number includes:
[0013] Based on different mobile phone numbers in the knowledge graph, combined with consumption information collected with user authorization and different user portraits constructed using APP types, the target mobile phone number, target consumption information and target user portrait adapted to the target APP type are determined.
[0014] In combination with the first aspect of the present application, in a third possible implementation of the first aspect of the present application, determining a target user portrait matching the user identifier according to the knowledge graph includes:
[0015] Determine a target user ID associated with the user ID from the knowledge graph;
[0016] Get the user profile that matches the target user ID as the target user profile.
[0017] In combination with the third possible implementation of the first aspect of the present application, in a fourth possible implementation of the first aspect of the present application, determining a target user identifier associated with the user identifier from the knowledge graph includes:
[0018] A joint user identifier carrying a user identifier is determined from the knowledge graph as the target user identifier. Each joint user identifier in the knowledge graph is generated from multiple user identifiers associated with the same user account under a preset identifier generation rule. Multiple user identifiers associated with the same user account are collected with user confirmation.
[0019] In combination with the fourth possible implementation method of the first aspect of the present application, in the second possible implementation method of the fifth aspect of the present application, the multiple user identifiers, in addition to the mobile phone number, also specifically include any combination of the mobile phone system identifier, the browser identifier, the IP address and the ID card number.
[0020] In combination with the first aspect of the present application, in a sixth possible implementation manner of the first aspect of the present application, obtaining a house viewing service push message adapted to the target user portrait includes:
[0021] Among the various initial house viewing service push messages adapted to the target user portrait, the probability of purchase intention is predicted by combining the portrait content of the target user portrait and the message content of the various initial house viewing service push messages;
[0022] Identify the house viewing service push messages that have the highest predicted probability of purchase intention.
[0023] In a second aspect, the present application provides a message push device, the device comprising:
[0024] A collection unit, used to collect a user identifier from the account information carried by the user account to be pushed, the user account to be pushed is a user account of the house viewing application, the user identifier is an identifier associated with the user account to be pushed, and the user identifier is collected with the confirmation of the user;
[0025] A determination unit, used to determine a target user profile that matches the user identifier according to a knowledge graph, wherein the knowledge graph is constructed based on associations between different user identifiers and different user profiles;
[0026] An acquisition unit, used to acquire a house viewing service push message adapted to a target user profile, wherein the house viewing service push message includes recommended content of the house viewing service corresponding to the house viewing application;
[0027] The push unit is used to push the house viewing service push message to the user account to be pushed.
[0028] In conjunction with the second aspect of the present application, in a first possible implementation of the second aspect of the present application, the user identifier specifically includes a target mobile phone number of the visiting user, and the determination unit is specifically used to:
[0029] From the different user portraits configured based on different mobile phone numbers in the knowledge graph, determine the target user portrait that is suitable for the target mobile phone number.
[0030] In combination with the first possible implementation of the second aspect of the present application, in the second possible implementation of the second aspect of the present application, the user identifier specifically includes target consumption information, target usage APP type, and the determination unit is specifically used to:
[0031] Based on different mobile phone numbers in the knowledge graph, combined with consumption information collected with user authorization and different user portraits constructed using APP types, the target mobile phone number, target consumption information and target user portrait adapted to the target APP type are determined.
[0032] In combination with the second aspect of the present application, in a third possible implementation manner of the second aspect of the present application, the determining unit is specifically configured to:
[0033] Determine a target user ID associated with the user ID from the knowledge graph;
[0034] Get the user profile that matches the target user ID as the target user profile.
[0035] In combination with the third possible implementation of the second aspect of the present application, in a fourth possible implementation of the second aspect of the present application, the determining unit is specifically used to:
[0036] A joint user identifier carrying a user identifier is determined from the knowledge graph as the target user identifier. Each joint user identifier in the knowledge graph is generated from multiple user identifiers associated with the same user account under a preset identifier generation rule. Multiple user identifiers associated with the same user account are collected with user confirmation.
[0037] In combination with the fourth possible implementation method of the second aspect of the present application, in the second possible implementation method of the fifth aspect of the present application, the multiple user identifiers, in addition to the mobile phone number, also specifically include any combination of the mobile phone system identifier, the browser identifier, the IP address and the ID card number.
[0038] In combination with the second aspect of the present application, in a sixth possible implementation manner of the second aspect of the present application, the acquiring unit is specifically configured to:
[0039] Among the various initial house viewing service push messages adapted to the target user portrait, the probability of purchase intention is predicted by combining the portrait content of the target user portrait and the message content of the various initial house viewing service push messages;
[0040] Identify the house viewing service push messages that have the highest predicted probability of purchase intention.
[0041] In the third aspect, the present application also provides a message push system, including a processor and a memory, wherein a computer program is stored in the memory, and when the processor calls the computer program in the memory, the method provided by the first aspect of the present application or any possible implementation method of the first aspect of the present application is executed.
[0042] In a fourth aspect, the present application also provides a computer-readable storage medium, which stores multiple instructions, and the instructions are suitable for a processor to load to execute the method provided by the first aspect of the present application or any possible implementation of the first aspect of the present application.
[0043] From the above content, it can be concluded that the present application has the following beneficial effects:
[0044] Regarding the push of messages, this application first collects the user identifier from the account information carried by the current user account to be pushed, and then determines the target user portrait matched by the current user identifier from the association relationship between different user identifiers and different user portraits pre-constructed in the knowledge graph, and then pushes the house viewing service push message adapted to the target user portrait to the user account to be pushed. In this process, compared with the inaccurate user portrait configuration in the prior art that constructs user portraits centered on user accounts, this application constructs user portraits centered on user identifiers, thereby constructing more accurate user portraits for different users from a more basic perspective, which is more in line with the actual situation, and can thus improve the recommendation accuracy of messages to a certain extent. BRIEF DESCRIPTION OF THE DRAWINGS
[0045] Figure 1 A flowchart of a method for pushing application messages;
[0046] Figure 2 A schematic diagram of a process for determining the target user portrait for this application;
[0047] Figure 3 A schematic diagram of the structure of a device for pushing messages of this application;
[0048] Figure 4 A structural diagram of the push system for this application message. DETAILED DESCRIPTION
[0049] First of all, before introducing this application, let me first introduce the relevant content of this application regarding the application background.
[0050] The message push method, device and computer-readable storage medium provided in the present application can be applied to the message push system, and is used to build a user portrait centered on the user identity in the knowledge graph, thereby avoiding the inaccurate configuration caused by building a user portrait centered on the user account in the prior art, and being more in line with the actual situation, thereby improving the recommendation accuracy of the message to a certain extent.
[0051] The message push method mentioned in the present application may be executed by a message push device or a message push system integrated with the device. The message push system may include different types of processing devices such as server devices, physical hosts or user equipment (UE), which may be adjusted according to the actual situation of the message push form or system architecture.
[0052] The message push device may be implemented in hardware or software, and the UE may specifically be a terminal device such as a smart phone, a tablet computer, a laptop computer, a PDA, a desktop computer, or a personal digital assistant (PDA).
[0053] Figure 1 A schematic diagram of a method for pushing messages of this application is shown in FIG. Figure 1 As shown, the method provided by the present application may specifically include the following steps:
[0054] Step S101, collecting a user identifier from the account information carried by the user account to be pushed, the user account to be pushed is the user account of the house viewing application, the user identifier is an identifier associated with the user account to be pushed, and the user identifier is collected with the user's confirmation;
[0055] Step S102, determining a target user profile that matches the user identifier according to the knowledge graph, where the knowledge graph is constructed based on the association relationship between different user identifiers and different user profiles;
[0056] Step S103, obtaining a house viewing service push message adapted to the target user portrait, and pushing the house viewing service push message to the user account to be pushed, wherein the house viewing service push message includes recommended content of the house viewing service corresponding to the house viewing application.
[0057] From the above Figure 1 It can be seen from the illustrated embodiment that, for the push of messages, the present application first collects the user identifier from the account information carried by the current user account to be pushed, and then determines the target user portrait matched by the current user identifier from the association relationship between different user identifiers and different user portraits pre-constructed in the knowledge graph, and then pushes the house viewing service push message adapted to the target user portrait to the user account to be pushed. In this process, compared with the inaccurate user portrait configuration existing in the prior art which constructs the user portrait centered on the user account, the present application constructs the user portrait centered on the user identifier, thereby constructing more accurate user portraits for different users from a more basic perspective, which is more in line with the actual situation, and can thus improve the recommendation accuracy of messages to a certain extent.
[0058] The following continues Figure 1The steps shown and the specific implementation methods that may be used in practical applications are described in detail:
[0059] In this application, the account to be pushed is specifically the user account of the house viewing application. It can be understood that the house viewing service provider can launch the house viewing application to the user in response to the user's house viewing needs. Before viewing the property on site, the user can learn about the property online through the house viewing service provided by the house viewing application, and further make an appointment for offline house viewing service through the appointment viewing service provided by the house viewing application, or enjoy related real estate introduction services through the dedicated introduction service provided by the house viewing application, or initiate a house purchase business through the house purchase service provided by the house viewing application.
[0060] In the process of using the house viewing application, the push of messages such as update reminders of real estate dynamic information that users are concerned about, real estate recommendations initiated by users, order reminders for house viewing services, real estate recommendations customized by the application, and real estate recommendations broadcast by the application can all be introduced by introducing the message push method provided by this application. The specific push content can be adjusted according to the different house viewing services of the house viewing application, and the specific details are not limited here. In actual applications, due to the improved accuracy of configuring user portraits, the recommendation accuracy of messages can be improved, avoiding too many invalid recommendations, thereby ensuring the user experience of the house viewing application.
[0061] The account information carried by the user account to be pushed may specifically refer to the account information stored in the cloud server, or may refer to the account information stored locally on the UE where the house viewing application is installed. Correspondingly, the user identifier is collected from the account information carried by the user account to be pushed. Specifically, the account information stored in the user account to be pushed may be queried on the server in the system, or the UE that has installed the house viewing application may be triggered to report the collected account information, or the account information automatically reported by the UE that has installed the house viewing application may be received. The specific information may be adjusted according to actual conditions.
[0062] It should be understood that, in addition to basic information such as account identification (ID), the account information may also contain some user information that is sensitive to the user. In the present application, the user identification involved in the collection of the account information is collected with the confirmation of the user. It can be seen that when the message push method provided by the present application is applied, it can be triggered by the user independently. The user can actively start or close the push mechanism of the message push method provided by the present application in the setting information of the house viewing application, or can start or close the push mechanism of the message push method provided by the present application in the control window displayed by the house viewing application.
[0063] In this application, with respect to the user portrait of the user, this application builds the user portrait centered on the user identifier associated with the user, thereby avoiding the limitation of the user account and building a more accurate user portrait for different users from a more basic perspective.
[0064] The user portrait is specifically constructed in the knowledge graph. The knowledge graph constructs the association between different user identifiers and different user portraits. Subsequently, the user portrait can be matched according to the currently collected user identifier.
[0065] A knowledge graph can be understood as describing various entities or concepts. In this application, what is described is a user portrait. The attribute-value pair (AVP) in the user portrait is used to characterize the intrinsic characteristics of the user portrait, and the relationship between different user portraits is connected through different user identifiers. In this way, the knowledge graph involved in the house viewing application of this application is constructed. The knowledge graph can be understood as a huge graph. The nodes in the graph represent user portraits, and the edges in the graph are composed of user identifiers.
[0066] The construction of the knowledge graph may specifically include the collection of initial user identifiers, configuring different adapted user portraits according to the message push content involved in the house viewing application, and then using the Euclidean distance between different user portraits and different user identifiers in the configured semantic similarity and logical correlation as their correlation, so as to obtain the association relationship between different user identifiers and different user portraits involved in the house viewing application.
[0067] The present application can configure adaptive house viewing service push messages for different user portraits. Thus, after the adaptive target user portrait is determined through the knowledge graph, the adaptive house viewing service push message for the target user portrait can be fed back, thereby achieving the purpose of improving the accuracy of message push.
[0068] The house viewing service push message can be pre-configured for the user portrait, or configured for the user portrait in real time. In actual applications, it can be implemented through a message push list. In this list, the house viewing service push messages that can be pushed for different user portraits are described. These messages can be written into the table after being determined in advance, or the content can be adjusted after being written into the table.
[0069] As a practical implementation method, the present application can specifically use the mobile phone number as the user identifier to construct a user portrait. In this way, the target user portrait adapted to the target mobile phone number of the visiting user associated with the current account to be pushed can be determined from the different user portraits configured based on different mobile phone numbers in the knowledge graph.
[0070] It can be understood that in actual applications, when users use the house viewing application to conduct a series of house viewing services, they can leave their mobile phone numbers for the staff to facilitate telephone communication, or make appointments for house viewing services through their mobile phone numbers, etc., which involve the use of mobile phone numbers. Therefore, the mobile phone numbers that are frequently used by users in the house viewing service can be used as the user's indicative user identification, which has a more reliable and accurate user identification effect than the account ID.
[0071] Secondly, as a supplement to mobile phone numbers, this application can also be based on the different mobile phone numbers carried in the account information of different user accounts, combined with consumption information collected with user authorization and the type of APP used, to build user portraits adapted to different user identifiers.
[0072] In this way, the currently adapted target user profile can be determined from different user portraits constructed based on different mobile phone numbers in the knowledge graph, combined with consumption information collected with user authorization, APP types used, and other information.
[0073] It can be understood that in the message push scenario involved in the house viewing application, consumption information, APP type used, and even other user authorization information or manually supplemented information can further provide strong data support for the construction of user portraits.
[0074] Furthermore, in order to improve the matching accuracy of user portraits and to better identify the real users behind different user accounts, this application also proposes a user identification association mechanism.
[0075] It is understandable that the collected user IDs may not be completely consistent with the user IDs involved in the knowledge graph. For example, in the knowledge graph, in order to facilitate the use of user IDs, the user IDs may be processed in a unified manner in terms of ID form and ID content, and this processing may be different from the initial user ID collected from the current account information. Therefore, in the process of determining the target user portrait, this application Figure 2 A schematic diagram of a process for determining a target user portrait in the present application is shown, which may specifically include:
[0076] Step S201, determining a target user identifier associated with the user identifier from the knowledge graph;
[0077] The target user identifier can be determined, for example, by calculating the Euclidean distance based on semantic similarity, logical relevance, etc., and the user identifier with the smallest Euclidean distance is used as the user identifier with the highest similarity, and is used as the target user identifier.
[0078] Step S202, obtaining a user portrait adapted to the target user identifier as the target user portrait.
[0079] After the target user identification obtained through the previous unified processing is determined, the user profile adapted to the target user identification can be used as the target user profile.
[0080] It is understandable that, in actual applications, matching can be performed for each collected user identification separately, or matching can be performed for these user identifications as a whole.
[0081] As another exemplary implementation method, the present application may introduce a joint user identification mechanism to improve the accurate identification of the user behind the user account, and use the joint user identification as the target user identification for the above matching.
[0082] In this case, each joint user identifier in the knowledge graph is specifically generated by multiple user identifiers associated with the same user account under a preset identifier generation rule, and the multiple user identifiers associated with the same user account are collected with user confirmation.
[0083] It can be understood that when each user uses the house viewing application, there may be more than two user identifiers that are considered to be unique in his or her account information. Even if the user logs in to different user accounts on the UE, these user identifiers are generally unique and unchanged. In this way, these user identifiers that are considered to be unique are used to generate a joint user identifier through the identifier generation strategy preset in this application. In this way, even if the user changes the logged-in user account on the UE, or changes the UE of the logged-in user account, after the user identifier is collected from the UE, the corresponding joint user identifier can be determined. At this time, the joint user identifier can identify the real user behind it, so as to achieve the purpose of accurately identifying different real users with different joint user identifiers.
[0084] For example, the multiple user identifiers used to generate the joint user identifier may include, in addition to mobile phone numbers, any combination of unique user information such as mobile phone system identifiers, browser identifiers, IP addresses, and ID card numbers.
[0085] It can be understood that the user identifier mentioned here for generating a joint user identifier is a unique user identifier selected based on the need to identify the real user, and the above also mentioned different user portraits constructed based on the mobile phone number, consumption information collected with the user's authorization, APP type and other information. The two have different purposes for using user identifiers. One is based on the need to accurately identify the real user, and the other is based on the need to accurately identify the user portraits. The user identifiers involved in the two processes can essentially be used in combination. The above content takes into account the difference between the two needs, and the adjustments made to the disclosed user identifier. The user identifier that is not directly disclosed can also be used as a further supplement to the user identifier.
[0086] After the target user portrait is determined, the house viewing service push message adapted to the target user portrait can be pushed to the user account to be pushed.
[0087] Among them, corresponding to the need to improve the push accuracy, this application can also introduce the purchase intention prediction probability value when pushing messages to quantify the purchase intention on the user side, and combine the service needs to select the house viewing service push message with the highest purchase intention probability for push.
[0088] Correspondingly, the acquisition and processing of the house viewing service push message may include:
[0089] Among the various initial house viewing service push messages adapted to the target user portrait, the probability of purchase intention is predicted by combining the portrait content of the target user portrait and the message content of the various initial house viewing service push messages;
[0090] Identify the house viewing service push messages that have the highest predicted probability of purchase intention.
[0091] It can be understood that by pushing the house viewing service push message with the highest predicted purchase intention value, the user side may be more likely to accept the recommended content in the house viewing service push message. This is not only beneficial for users of the house viewing application to receive more acceptable content recommendations, but also has better application value for the commercial application of the house viewing application.
[0092] The above is an explanation of the message push method of the present application. In order to better implement the message push method provided by the present application, the present application also provides a message push device.
[0093] See also Figure 3 , Figure 3 This is a schematic diagram of a structure of a device for pushing messages of this application. In this application, the device 300 may specifically include the following structure:
[0094] The collecting unit 301 is used to collect the user identifier from the account information carried by the user account to be pushed, the user account to be pushed is the user account of the house viewing application, the user identifier is an identifier associated with the user account to be pushed, and the user identifier is collected with the confirmation of the user;
[0095] A determination unit 302 is used to determine a target user profile that matches the user identifier according to a knowledge graph, where the knowledge graph is constructed based on associations between different user identifiers and different user profiles;
[0096] An acquisition unit 303 is used to acquire a house viewing service push message adapted to the target user profile, where the house viewing service push message includes recommended content of the house viewing service corresponding to the house viewing application;
[0097] The push unit 304 is used to push the house viewing service push message to the user account to be pushed.
[0098] In conjunction with the second aspect of the present application, in a first possible implementation manner of the second aspect of the present application, the user identifier specifically includes a target mobile phone number of the visiting user, and the determination unit 302 is specifically used to:
[0099] From the different user portraits configured based on different mobile phone numbers in the knowledge graph, determine the target user portrait that is suitable for the target mobile phone number.
[0100] In combination with the first possible implementation of the second aspect of the present application, in the second possible implementation of the second aspect of the present application, the user identifier specifically further includes target consumption information and target usage APP type, and the determination unit 302 is specifically used to:
[0101] Based on different mobile phone numbers in the knowledge graph, combined with consumption information collected with user authorization and different user portraits constructed using APP types, the target mobile phone number, target consumption information and target user portrait adapted to the target APP type are determined.
[0102] In combination with the second aspect of the present application, in a third possible implementation manner of the second aspect of the present application, the determining unit 302 is specifically configured to:
[0103] Determine a target user ID associated with the user ID from the knowledge graph;
[0104] Get the user profile that matches the target user ID as the target user profile.
[0105] In combination with the third possible implementation of the second aspect of the present application, in a fourth possible implementation of the second aspect of the present application, the determining unit 302 is specifically configured to:
[0106] A joint user identifier carrying a user identifier is determined from the knowledge graph as the target user identifier. Each joint user identifier in the knowledge graph is generated from multiple user identifiers associated with the same user account under a preset identifier generation rule. Multiple user identifiers associated with the same user account are collected with user confirmation.
[0107] In combination with the fourth possible implementation method of the second aspect of the present application, in the second possible implementation method of the fifth aspect of the present application, the multiple user identifiers, in addition to the mobile phone number, also specifically include any combination of the mobile phone system identifier, the browser identifier, the IP address and the ID card number.
[0108] In combination with the second aspect of the present application, in a sixth possible implementation manner of the second aspect of the present application, the acquiring unit 303 is specifically configured to:
[0109] Among the various initial house viewing service push messages adapted to the target user portrait, the probability of purchase intention is predicted by combining the portrait content of the target user portrait and the message content of the various initial house viewing service push messages;
[0110] Identify the house viewing service push messages that have the highest predicted probability of purchase intention.
[0111] The present application also provides a message push system, which may include one device or multiple devices. Taking a device as an example, refer to Figure 4 , Figure 4 A schematic diagram of a push system for a message of the present application is shown. Specifically, the push system for a message of the present application includes a processor 401, a memory 402, and an input / output device 403. The processor 401 is used to execute a computer program stored in the memory 402 to implement the following Figure 1 The steps of the message push method in the corresponding embodiment; or, the processor 401 is used to execute the computer program stored in the memory 402 to implement the following Figure 3 Corresponding to the functions of each unit in the embodiment, the memory 402 is used to store the processor 401 executing the above Figure 1 The computer program required for the message pushing method in the corresponding embodiment.
[0112] Exemplarily, the computer program may be divided into one or more modules / units, one or more modules / units are stored in the memory 402, and executed by the processor 401 to complete the present application. One or more modules / units may be a series of computer program instruction segments capable of completing specific functions, and the instruction segments are used to describe the execution process of the computer program in the computer device.
[0113] The message push system may include, but is not limited to, the processor 401, the memory 402, and the input-output device 403. Those skilled in the art will appreciate that the illustration is merely an example of the message push system and does not constitute a limitation on the message push system, and may include more or fewer components than those shown in the illustration, or a combination of certain components, or different components, for example, the message push system may also include a network access device, a bus, etc., and the processor 401, the memory 402, the input-output device 403, and the network access device, etc. are connected via a bus.
[0114] The processor 401 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor, etc. The processor is the control center of the message push system, and uses various interfaces and lines to connect various parts of the entire system.
[0115] The memory 402 can be used to store computer programs and / or modules. The processor 401 implements various functions of the computer device by running or executing the computer programs and / or modules stored in the memory 402 and calling the data stored in the memory 402. The memory 402 can mainly include a program storage area and a data storage area, wherein the program storage area can store an operating system, at least one application required for a function, etc.; the data storage area can store data created according to the use of the message push system, etc. In addition, the memory can include a high-speed random access memory, and can also include a non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (SecureDigital, SD) card, a flash card (Flash Card), at least one disk storage device, a flash memory device, or other volatile solid-state storage devices.
[0116] When the processor 401 is used to execute the computer program stored in the memory 402, the following functions can be implemented:
[0117] Collecting a user ID from the account information carried by the user account to be pushed, the user account to be pushed is the user account of the house viewing application, the user ID is an ID associated with the user account to be pushed, and the user ID is collected with the user's confirmation;
[0118] Determine the target user profile that matches the user ID based on the knowledge graph, where the knowledge graph is constructed based on the associations between different user IDs and different user profiles;
[0119] Obtain the house viewing service push message adapted to the target user portrait, and push the house viewing service push message to the user account to be pushed. The house viewing service push message includes the recommended content of the house viewing service corresponding to the house viewing application.
[0120] Those skilled in the art can clearly understand that for the convenience and brevity of description, the specific working process of the message push device, system and its corresponding units described above can refer to the following. Figure 1 The description of the message pushing method in the corresponding embodiment will not be repeated here.
[0121] A person of ordinary skill in the art will appreciate that all or part of the steps in the various methods of the above embodiments may be completed by instructions, or by controlling related hardware through instructions. The instructions may be stored in a computer-readable storage medium and loaded and executed by a processor.
[0122] To this end, the present application provides a computer-readable storage medium, in which a plurality of instructions are stored, and the instructions can be loaded by a processor to execute the present application as follows: Figure 1 For the steps in the message push method in the corresponding embodiment, the specific operations can refer to the following Figure 1 The description of the message pushing method in the corresponding embodiment will not be repeated here.
[0123] The computer-readable storage medium may include: a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, etc.
[0124] Due to the instructions stored in the computer-readable storage medium, the present application can be executed. Figure 1 The steps in the message push method in the corresponding embodiment, therefore, the present application can be implemented as follows Figure 1 The beneficial effects that can be achieved by the message push method in the corresponding embodiment are detailed in the previous description and will not be repeated here.
[0125] The message push method, device, system and computer-readable storage medium provided by the present application are introduced in detail above. Specific examples are used in this article to illustrate the principles and implementation methods of the present application. The description of the above embodiments is only used to help understand the method of the present application and its core idea; at the same time, for technical personnel in this field, according to the idea of the present application, there will be changes in the specific implementation method and application scope. In summary, the content of this specification should not be understood as a limitation on the present application.
Claims
1. A message push method, characterized in that: The method comprises: Collecting a user identifier from the account information carried by the user account to be pushed, the user account to be pushed is a user account of the house viewing application, the user identifier is an identifier associated with the user account to be pushed, and the user identifier is collected with the user's confirmation; Determine a target user profile that matches the user identifier according to a knowledge graph, wherein the knowledge graph is constructed based on associations between different user identifiers and different user profiles; Obtaining a house viewing service push message adapted to the target user profile, and pushing the house viewing service push message to the user account to be pushed, wherein the house viewing service push message includes recommended content of the house viewing service corresponding to the house viewing application; The step of determining the target user portrait matching the user identifier according to the knowledge graph includes: Calculate the semantic similarity and logical correlation between the first joint user identifier in the knowledge graph and the collected user identifier; the user identifier is a second joint user identifier collected with user confirmation, and the second joint user identifier includes: any combination of unique user information such as mobile phone number, mobile phone system identifier, browser identifier, IP address, and ID card number; Calculating the Euclidean distance based on the semantic similarity and the logical correlation, and determining a first joint user identifier associated with the user identifier from the knowledge graph based on a minimum Euclidean distance, and determining the first joint user identifier as a target user identifier; Obtain a user portrait adapted to the target user identifier in the knowledge graph as the target user portrait.
2. The method according to claim 1, characterized in that The user identifier specifically includes a target mobile phone number of the visiting user, and determining a target user profile matching the user identifier according to the knowledge graph includes: From different user portraits configured based on different mobile phone numbers in the knowledge graph, determine the target user portrait adapted for the target mobile phone number.
3. The method according to claim 2, characterized in that The user identification specifically includes target consumption information and target APP type. The determining of the target user profile adapted to the target mobile phone number from different user profiles configured based on different mobile phone numbers in the knowledge graph includes: Based on different mobile phone numbers in the knowledge graph, combined with consumption information collected under user authorization and different user portraits constructed using APP types, the target mobile phone number, the target consumption information and the target user portrait adapted for the target APP type are determined.
4. The method according to claim 1, characterized in that: The determining, according to the knowledge graph, a target user portrait matching the user identifier includes: Determining a target user identifier associated with the user identifier from the knowledge graph; Obtain a user profile adapted to the target user identifier as the target user profile.
5. The method according to claim 4, characterized in that The determining, from the knowledge graph, a target user identifier associated with the user identifier includes: A joint user identifier carrying the user identifier is determined from the knowledge graph as the target user identifier. Each joint user identifier in the knowledge graph is specifically generated from multiple user identifiers associated with the same user account under a preset identifier generation rule. The multiple user identifiers associated with the same user account are collected with user confirmation.
6. The method according to claim 5, characterized in that In addition to the mobile phone number, the multiple user identifications also specifically include any combination of mobile phone system identification, browser identification, IP address and ID card number.
7. The method according to claim 1, characterized in that The step of obtaining a house viewing service push message adapted to the target user profile includes: Among the multiple initial house viewing service push messages adapted to the target user portrait, the probability of purchase intention is predicted by combining the portrait content of the target user portrait and the message content of the multiple initial house viewing service push messages; The house viewing service push message that obtains the highest purchase intention prediction probability value is identified.
8. A message push device, characterized in that: The device comprises: A collection unit, configured to collect a user identifier from the account information carried by the user account to be pushed, wherein the user account to be pushed is a user account of the house viewing application, and the user identifier is an identifier associated with the user account to be pushed, and the user identifier is collected with the confirmation of the user; A determination unit, configured to determine a target user profile that matches the user identifier according to a knowledge graph, wherein the knowledge graph is constructed based on associations between different user identifiers and different user profiles; an acquisition unit, configured to acquire a house viewing service push message adapted to the target user profile, wherein the house viewing service push message includes recommended content of the house viewing service corresponding to the house viewing application; A push unit, used for pushing the house viewing service push message to the user account to be pushed; The acquisition unit is further used to calculate the semantic similarity and logical correlation between the first joint user identifier in the knowledge graph and the collected user identifier; the user identifier is a second joint user identifier collected with user confirmation, and the second joint user identifier includes: any combination of unique user information such as a mobile phone number, a mobile phone system identifier, a browser identifier, an IP address, and an ID card number; Calculating the Euclidean distance based on the semantic similarity and the logical correlation, and determining a first joint user identifier associated with the user identifier from the knowledge graph based on a minimum Euclidean distance, and determining the first joint user identifier as a target user identifier; Obtain a user portrait adapted to the target user identifier in the knowledge graph as the target user portrait.
9. A message push system, characterized in that: The method comprises a processor and a memory, wherein the memory stores a computer program, and the processor executes the method according to any one of claims 1 to 7 when calling the computer program in the memory.
10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a plurality of instructions, and the instructions are suitable for being loaded by a processor to execute the method according to any one of claims 1 to 7.
Citation Information
Patent Citations
Portrait data acquisition method and device based on demand word
CN108763555A
Data pushing method and related device
CN112269926A
