Information push method, device and medium

Abstract

The present application relates to an information push method, device and medium, wherein the method comprises: obtaining target social information of a target object according to authorization information of the target object; determining an associated object associated with the target object and a target object feature of the target object according to the target social information; obtaining an associated object feature of the associated object; determining a target insurance according to the target object feature and the associated object feature; and sending the push information of the target insurance to the target object. The present application improves the accuracy of pushing insurance.

Description

Technical Field

[0001] The present application relates to the field of intelligent recommendation technology, and mainly to an information push method, device and medium. Background Art

[0002] With the increasing development of Internet technology, the use of Internet technology to push information to users has become a new way of pushing information. The push speed of Internet technology is fast and has a wide coverage. Compared with traditional push technology, it has certain advantages. For example, in the insurance business, insurance can be recommended online.

[0003] At present, the technical solution of pushing insurance to users is generally indiscriminate push, that is, push to all users. This push method is costly, the insurance pushed is poorly targeted, the hit rate for users is low, and it is easy to be blocked by users, affecting subsequent push. Summary of the invention

[0004] The embodiments of the present application provide an information push method, device, and medium, which can perform insurance push based on the characteristics of a target object and the characteristics of an associated object associated with the target object, thereby improving the accuracy of the push.

[0005] In a first aspect, an embodiment of the present application provides an information push method, wherein:

[0006] Acquire target social information of the target object according to the authorization information of the target object;

[0007] Determining, according to the target social information, an associated object associated with the target object and a target object feature of the target object;

[0008] Obtaining associated object characteristics of the associated object;

[0009] Determine target insurance according to the target object characteristics and the associated object characteristics;

[0010] Send push information of the target insurance to the target object.

[0011] In a second aspect, an embodiment of the present application provides an information push device, wherein:

[0012] A processing unit, configured to obtain target social information of the target object according to authorization information of the target object; determine an associated object associated with the target object and a target object feature of the target object according to the target social information; obtain an associated object feature of the associated object; and determine a target insurance according to the target object feature and the associated object feature;

[0013] A communication unit is used to send push information of the target insurance to the target object.

[0014] In a third aspect, an embodiment of the present application provides another information push device, comprising a processor, a memory, a communication interface, and one or at least one program, wherein the one or at least one program is stored in the memory and configured to be executed by the processor, and the program includes instructions for some or all of the steps described in the first aspect.

[0015] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, wherein the computer program enables a computer to execute to implement some or all of the steps described in the first aspect.

[0016] Implementing the embodiments of the present application will have the following beneficial effects:

[0017] After adopting the above-mentioned information push method, device and medium, the target social information of the target object is first obtained according to the authorization information of the target object, and then the associated object associated with the target object and the target object characteristics of the target object are determined according to the target social information, thereby improving the accuracy of determining the associated object and the target object characteristics. Then, the associated object characteristics of the associated object are obtained, the target insurance is determined according to the target object characteristics and the associated object characteristics, and the push information of the target insurance is sent to the target object. In other words, the insurance pushed to the target object is the insurance related to the target object characteristics and the associated object characteristics, thereby improving the accuracy of the push. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0019] in:

[0020] Figure 1 A flowchart of an information push method provided in an embodiment of the present application;

[0021] Figure 2 A schematic diagram of the logical structure of an information push device provided in an embodiment of the present application;

[0022] Figure 3 A schematic diagram of the physical structure of an information push device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0023] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. According to the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0024] The terms "first", "second", etc. in the specification and claims of this application and the above-mentioned drawings are used to distinguish different objects, rather than to describe a specific order. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or units is not limited to the listed steps or units, but optionally includes steps or units that are not listed, or optionally includes other steps or units inherent to these processes, methods, products or devices.

[0025] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0026] The network architecture used in the embodiment of the present application includes a server and an electronic device. Among them, the electronic device can be a personal computer (PC), a laptop or a smart phone, and can also be an all-in-one machine, a handheld computer, a tablet computer (pad), a smart TV playback terminal, a vehicle-mounted terminal or a portable device, etc. The electronic device on the PC side, such as an all-in-one machine, etc., its operating system can include but is not limited to Linux system, Unix system, Windows series system (such as Windowsxp, Windows 7, etc.), Mac OS X system (operating system of Apple computer) and other operating systems. The electronic device on the mobile side, such as a smart phone, etc., its operating system can include but is not limited to Android system, IOS (operating system of Apple mobile phone), Window system and other operating systems.

[0027] The server is used to provide services for electronic devices. The electronic devices in the embodiments of the present application can install and run applications, and the server can be a server corresponding to the application installed in the electronic device, providing application services for the application. Among them, the application can be a separately integrated application, or a small program embedded in other applications, or an operating platform in the form of a web page, etc., which is not limited here. In the embodiments of the present application, the application corresponding to the server and the electronic device is referred to as the target application. The target application can be any application related to the insurance business, which is not limited here. The embodiments of the present application do not limit the number of electronic devices and servers, and the server can provide services to multiple electronic devices at the same time. The server can be implemented as an independent server or a server cluster consisting of multiple servers.

[0028] In an embodiment of the present application, an electronic device or a server may pre-store social information that can be obtained in an application that the user has authorized. The social information can be understood as shared information that the user publicly shares with friends or strangers in a social network, similar to Weibo, or the Moments in WeChat, etc. The social information may include photos, videos, text, audio, etc., which are not limited here.

[0029] The social information can be understood as the information generated by users in social networks, such as consumption information, credit information, occupation information, interest information, etc. Among them, consumption information may include payment information of users who make payment operations in applications or use third-party applications, such as payment amount, payment account, receiving account, payment method, etc.

[0030] Credit information may include loan information of users performing loan operations in the application or third-party applications or other users, such as loan amount, loan time, collateral assets, overdue probability, overdue time, repayment method, etc.

[0031] Occupational information may include the user's occupation, position, occupation type, work unit, salary level, technical field, and other work-related information.

[0032] Interest information may include information of interest or concern marked by the user in the application, and may also include information obtained from information frequently browsed by the user (e.g., web pages, games, videos, audio, etc.), or may be information obtained based on professional information, consumer information, and credit information. It is understandable that social information can reflect the information that the user is concerned about to a certain extent. By analyzing the interest information in the social information, it is convenient to improve the accuracy of analyzing the insurance that the user is interested in. This application does not limit social information, interest information, consumer information, credit information, and professional information. Interest information, consumer information, credit information, and professional information can be obtained through shared information in social information.

[0033] In an embodiment of the present application, an electronic device or a server may pre-store a knowledge graph for describing the association relationship between various objects in a social network. The knowledge graph is a semantic-based structured information organization method that describes concepts and their relationships in the physical world in symbolic form. Its basic components are "entity-relationship-entity" triples, as well as entities and their related attribute-value pairs. Entities are interconnected through relationships to form a network-like knowledge structure. Through the knowledge graph, business data can be transformed from information to knowledge, which is particularly suitable for organizing large-scale, strongly related business concept entities.

[0034] The present application does not limit the method for establishing a knowledge graph. Basic information of multiple users can be collected and then analyzed to obtain the associated images corresponding to each user. In a possible example, the method for establishing a knowledge graph includes the following steps A1 to A4, wherein:

[0035] A1: Search a target webpage to obtain at least one first object and a first keyword corresponding to the first object.

[0036] The target webpage may be a webpage of a target application, or any search application, or any insurance-related application, etc. The present application does not limit the target webpage. It should be noted that the target webpage may include one or more webpages.

[0037] The first object may be a user involved in the target web page. The first keyword may include characteristic information of the first object, such as basic information such as name, age, address, work unit, and education, and may also include user interest characteristics, such as sports, music, etc., and may also include user physical characteristics, such as genetic disease history, physical examination report, etc. The first keyword may be a vocabulary of the first object in the target web page, or a vocabulary obtained based on the information of the first object in the target web page. The first keyword includes the characteristics of the first object and the characteristics of the associated object with which there is an associated relationship, and also includes the event cause, event name, and event result of the event corresponding to the first object. It should be noted that the number of first objects may be one or more, and the first keyword may be one or more keywords corresponding to one first object, or one or more keywords corresponding to multiple first objects, which are not limited here.

[0038] This application does not limit the search method for the target web page, and crawler technology can be used for searching. The crawler technology is also called a web crawler, web spider, web robot, or web chaser, etc. It is a program or script that automatically captures network information according to certain rules. Specifically, the search dimension can be determined based on experience or information in a reference website (for example, a social question-and-answer platform, a dictionary in a vertical field, etc.), and then the initial vocabulary can be determined based on each dimension. A web crawler search is performed based on the initial vocabulary to obtain the first keyword corresponding to the first object and multiple first objects. It should be noted that when the number of searches exceeds a preset value, or the search time exceeds a preset time, the search step for the first object or the first keyword can be terminated.

[0039] A2: Process the first keyword to obtain at least two second keywords.

[0040] Among them, the second keyword is a word obtained after processing the first keyword. The processing method can be to merge the first keyword or to expand the first keyword, etc. This application does not limit the processing method of the second keyword. It should be noted that the number of second keywords is at least two, that is, there are multiple second keywords. It can be understood that when an object in a social network corresponds to multiple keywords, a social network relationship model can be constructed based on the relationship between each keyword and the relationship between each object. The social network relationship model can be understood as a knowledge graph.

[0041] In a possible example, step A2 includes the following steps A21 to A25, wherein:

[0042] A21: Search for event information corresponding to the first object according to the first keyword.

[0043] Among them, the event information can be hot news in the target webpage or other applications, or social information that can be obtained by the first object, etc., which is not limited here. Hot news can be determined based on the click-through rate in the webpage or application, and the level of the news. The click-through rate refers to the number of netizens viewing the news, which can be used to describe the degree of attention paid by netizens to the news. The level of news can be determined based on the impact and coverage of the news event, or the type or field of the news. It can be understood that hot news can better reflect the focus of netizens than ordinary news, and has a certain timeliness. Updating the first keyword based on hot news can improve the coverage of the first keyword. Social information can better reflect the work and life attitude of the first object than the information in the target webpage. Updating the first keyword based on social information can also improve the coverage of the first keyword, which is convenient for improving the comprehensiveness of the knowledge graph.

[0044] The present application does not limit the search method for event information. Web crawler technology can be used for search, and weights can be set for different first keywords in advance, and then web crawler searches can be performed separately according to the weights of the first keywords. It can be understood that searching based on different weights can further improve the accuracy of the search and facilitate improving the search efficiency.

[0045] It should be noted that, when searching for event information corresponding to the first object according to the first keyword, the search may be performed according to the first keywords corresponding to each first object, or may be performed according to the first keywords corresponding to multiple first objects, and this is not limited here.

[0046] A22: Acquire a third keyword corresponding to the first object according to the event information.

[0047] Among them, the third keyword is the keyword corresponding to the first object in the event information. The third keyword may correspond to one or more first objects, or may be the same or similar to the first keyword, or different from the first keyword, which is not limited here. The third keyword can be obtained according to dimensions such as the cause of the event, the name of the event, and the result of the event in the event information. This application does not limit the method for obtaining the third keyword, and this application does not limit the number of third keywords, which can be one or more.

[0048] A23: Select a fourth keyword different from the first keyword from the third keywords.

[0049] The fourth keyword is a keyword in the third keywords that is different from the first keywords, that is, the third keywords except the fourth keyword are the same as at least one first keyword.

[0050] A24: When the fifth keyword among the first keyword and the fourth keyword is similar to the sixth keyword among the first keyword and the fourth keyword, the fifth keyword and the sixth keyword are combined to obtain a seventh keyword.

[0051] The fifth keyword may be any keyword of the first keyword and the fourth keyword. When one of the first keyword and the fourth keyword is similar to the fifth keyword, the keyword is determined to be the sixth keyword. The present application does not limit the method for determining whether the fifth keyword and the sixth keyword are similar. The similarity value between the keywords can be obtained. When the similarity value between the two keywords is greater than a preset threshold, it is determined that the two keywords are similar and the two keywords are the fifth keyword and the sixth keyword, respectively.

[0052] The seventh keyword is a word obtained by combining the fifth keyword and the sixth keyword. It can be one of the fifth keyword and the sixth keyword, or a unified word corresponding to the fifth keyword and the sixth keyword. It can be understood that there are differences in keywords searched from different sources. Merging similar keywords can streamline keywords and improve the efficiency of subsequent searches. Merging similar keywords can also improve the standardization of vocabulary in the knowledge graph.

[0053] A25: Combine the keywords of the first keyword and the fourth keyword except the fifth keyword and the sixth keyword with the seventh keyword to obtain at least two second keywords.

[0054] It can be understood that in steps A21 to A25, the event information corresponding to at least one first object is first searched based on the first keyword, and then the third keyword corresponding to the first object is obtained based on the event information. Then, a fourth keyword different from the first keyword is selected from the third keyword, and the fifth keyword and the sixth keyword similar to the first keyword and the fourth keyword are merged to obtain the seventh keyword, and finally the keywords other than the fifth keyword and the sixth keyword in the first keyword and the fourth keyword are combined with the seventh keyword to obtain at least two second keywords. That is to say, based on the original first keyword, a new third keyword corresponding to the first object is searched based on the time information obtained by searching the first keyword. The original first keyword and the keywords similar to the newly searched third keyword are merged, and the remaining keywords are combined to obtain the second keyword, which improves the accuracy of obtaining the second keyword, increases the vocabulary in the knowledge graph, and facilitates improving the comprehensiveness of the knowledge graph.

[0055] A3: Obtain the association relationship between the first objects.

[0056] The association relationship may be a spouse, child, parent, brother, friend, colleague, etc. The association relationship between the first objects may include an association relationship between one of the first objects and another first object. For example, the first objects include object 1, object 2, and object 3, wherein object 1 and object 2 are husband and wife, and object 2 and object 3 are sisters. Then the association relationship between the first objects includes the husband and wife relationship between object 1 and object 2, and the sister relationship between object 2 and object 3. The association relationship may be determined by event information, or by social information of the first object, etc., which is not limited here.

[0057] A4: Create a knowledge graph based on the association relationship and the second keyword.

[0058] It can be understood that in steps A1 to A4, the target web page is searched to obtain at least one first object and a first keyword corresponding to the first object, and then the first keyword is processed to obtain at least two second keywords, thereby increasing the coverage of the acquired keywords. Then, the association relationship between the first objects is obtained, and a knowledge graph is established based on the association relationship and the second keyword, thereby increasing the coverage of the knowledge graph and facilitating the improvement of the accuracy of analyzing user features based on the knowledge graph.

[0059] The above social information and knowledge graph can also be stored in a block created on the blockchain network. Blockchain is a new application model of computer technologies such as distributed data storage, peer-to-peer transmission, consensus mechanism, and encryption algorithm. Blockchain is essentially a decentralized database, a string of data blocks generated by cryptographic methods. Each data block contains a batch of network transaction information, which is used to verify the validity of its information (anti-counterfeiting) and generate the next block. Blockchain can include the underlying blockchain platform, the platform product service layer, and the application service layer. It can be seen that by storing data in a distributed manner through blockchain, while ensuring data security, information can be shared between different platforms.

[0060] An information push method proposed in an embodiment of the present application can be executed by an information push device, wherein the device can be implemented by software and / or hardware, and can generally be integrated in an electronic device or a server, which can improve the accuracy of the push.

[0061] Please refer to Figure 1 , Figure 1 This is a flow chart of an information push method provided by the present application. The method comprises the following steps S101 to S105, wherein:

[0062] S101: Acquire target social information of the target object according to authorization information of the target object.

[0063] In an embodiment of the present application, when the method is executed by a server, the target object may be any user, or a user who has registered information in an application related to insurance business or a target application, or a user who has browsed insurance information, etc. When the method is executed by an electronic device, the target object may be a user corresponding to the electronic device, who may be a user logged in to the system of the electronic device or the target application, or a designated user entered in the target application, etc. The present application does not limit the target object, and the target application may refer to the above, which will not be repeated here.

[0064] The authorization information includes permission information of at least one application that the user is allowed to access, which can be understood as access by a third-party application, or access by a server to a third-party application. For example, the electronic device includes a first application, a second application, and a third application. When the authorization information includes the first application and the second application, the target social information of the target object in the first application and the second application can be obtained.

[0065] The target social information can be understood as the social information that the electronic device or server can obtain through the authorization information of the target object. The types of target social information are as described above, which may include sharing information uploaded by the target object, and may also include interest information, consumption information, credit information, occupational information, etc., which will not be repeated here. It should be noted that the target social information may include one or more social information.

[0066] S102: Determine, according to the target social information, an associated object associated with the target object and a target object feature of the target object.

[0067] In an embodiment of the present application, an associated object is associated with a target object, and the associated object can be used as a reference object for the target object to purchase insurance. For example, the associated object is a colleague or friend of the target object, and the insurance that the target object may purchase is determined based on the insurance purchased by the associated object. The associated object may also be used as the insured person in the insurance purchased by the target object. For example, the associated object is a family member of the target object, and the insurance that the family members of the target object can purchase can be pushed to the target object. The present application does not limit the method for determining the associated object. In one possible example, determining the associated object associated with the target object based on the target social information includes the following steps B1 to B3, wherein:

[0068] B1: Identify a second object involved in the target social information.

[0069] The second object is an object other than the target object involved in the target social information, and may be an object directly described in the target social information, or may be an object included in the target social information. For example, if the target social information is a picture or a video, the second object may be a person appearing in the picture or the video. It is understood that the name of the person involved in the target social information may be an alias such as a nickname or a nickname, and the identity and formal name of the second object may be determined through the address book of the target object or other pre-stored databases, such as the name in the ID card. When the second object involved in the target social information is a person image, the identity of the second object may be determined through the image library of the target object.

[0070] B2: Acquire an association value between the target object and the second object according to the target social information.

[0071] Among them, the association value is used to describe the degree of association between the target object and the second object, and can be determined by the association relationship between the target object and the second object, and / or the number of times the second object appears in the target social information. This application does not limit the method for obtaining the association value.

[0072] B3: When the association value is greater than or equal to a first threshold, determining that the second object is an associated object associated with the target object.

[0073] This application does not limit the first threshold, and it can be set according to the number of second objects, etc.

[0074] It can be understood that in steps B1 to B3, the second object involved in the target social information is first identified, and then the association value between the target object and the second object is obtained based on the target social information, and the second object whose association value is greater than or equal to the first threshold is selected as the associated object associated with the target object. This can improve the accuracy of determining the associated object and facilitate improving the effectiveness of the recommendation.

[0075] It should be noted that the associated object may be an item such as a car, and this application does not limit the type of the associated object.

[0076] In the embodiments of the present application, the target object characteristics are used to describe the characteristics of the target object, which may include consumption characteristics, interest characteristics, social characteristics, credit characteristics, occupational characteristics, etc. The present application does not limit the method for obtaining the target object characteristics, and the corresponding characteristics may be obtained based on the corresponding dimensions of consumption, interest, social, credit, and occupation, and the consumption characteristics, interest characteristics, etc. of the target object may also be obtained based on consumption information, interest information, social information, credit information, and occupational information.

[0077] S103: Acquire the associated object feature of the associated object.

[0078] Among them, the characteristics of the associated object can refer to the description of the characteristics of the target object, which will not be repeated here. This application does not limit the method for obtaining the characteristics of the associated object. When the associated object is a person, it can be obtained based on the dimensions corresponding to the consumption, interest, credit, and occupation of the associated object. When the associated object is an item, it can be obtained based on the item parameters of the associated object. The item parameters may include the value of the item, usage time, service life, or characteristics of the owner, etc.

[0079] Step S103 includes the following three implementation modes, wherein:

[0080] In a first implementation manner, first social information of the associated object is acquired according to authorization information of the associated object; and an associated object feature of the associated object is acquired according to the first social information.

[0081] The first social information is social information that can be obtained by the electronic device or server through the authorization information of the associated object, and can refer to the description of the target social information, which will not be repeated here. It can be understood that if the first social information of the associated object can be obtained according to the authorization information of the associated object, then the associated object characteristics of the associated object can be obtained according to the first social information, which can improve the accuracy of obtaining the associated object characteristics.

[0082] In a second implementation manner, second social information corresponding to the associated object is obtained from the target social information; and an associated object feature of the associated object is obtained according to the second social information.

[0083] The second social information is the social information of the associated object in the target social information. It can be understood that obtaining the associated object feature according to the second social information corresponding to the associated object in the target social information can improve the efficiency of obtaining the second social information and improve the success rate of obtaining the associated object feature.

[0084] In a third implementation, a target keyword of the associated object is extracted from the target social information; the target keyword is input into the knowledge graph to obtain an associated object feature of the associated object.

[0085] Among them, the target keywords may include the name, age, address, work unit, education level, etc. of the associated object. The knowledge graph can refer to the above and will not be repeated here. It can be understood that inputting the target keywords of the associated object in the target social information into the knowledge graph to obtain the associated object features of the associated object can improve the efficiency of analyzing the associated object features and the success rate of obtaining the associated object features.

[0086] S104: Determine target insurance according to the target object characteristics and the associated object characteristics.

[0087] In the embodiment of the present application, the target insurance may be an insurance product recommended to the target object for the associated object. It can be understood that the target object characteristics and the associated object characteristics respectively describe the characteristics of the target object and the associated object, and the target insurance determined according to the target object characteristics and the associated object characteristics is pushed to the target object, which can improve the success rate of the target object purchasing insurance for the associated object.

[0088] The present application does not limit the method for determining the target insurance. In a possible example, step S104 includes the following steps C1 to C3, wherein:

[0089] C1: Searching for the first insurance corresponding to the associated object feature.

[0090] Among them, the first insurance corresponds to the characteristics of the associated object, and can be understood as insurance suitable for the associated object to purchase. For example, if the associated object is the child of the target object, the target insurance can be children's insurance.

[0091] C2: Obtaining a first purchase probability of the first insurance according to the target object characteristics.

[0092] The first purchase probability is used to describe the probability that the target object purchases the first insurance for the associated object. This application does not limit the method for obtaining the first purchase probability. In a possible example, the target object characteristics include interest characteristics and consumption characteristics. Step C2 includes the following steps C21 to C23, wherein:

[0093] C21: Acquire the interest value of the target object for the first insurance according to the interest feature.

[0094] Among them, the interest feature can be used to determine whether the target object is interested in purchasing the first insurance. The interest feature can be obtained based on the dimensions based on the interest feature, such as sharing information, consumption information, credit information, and occupational information in the target social information, etc., which are not limited here. It can be understood that obtaining the interest value of the target object corresponding to the first insurance based on the interest feature can improve the success rate of analyzing the target object's purchase of the first insurance, which is convenient for improving the success rate of push.

[0095] C22: Obtaining the payment probability of the target object for the first insurance according to the consumption characteristics.

[0096] Among them, consumption characteristics can be used to determine whether the target object will purchase insurance. Consumption characteristics can be obtained based on sharing information, consumption information, credit information, and occupational information in the target social information, etc., which are based on consumption characteristics. It can be understood that obtaining the payment probability of the target object corresponding to the first insurance based on consumption characteristics can improve the success rate of analyzing the target object's purchase of the first insurance, which is convenient for improving the success rate of push.

[0097] C23: Obtain a first purchase probability of the first insurance according to the interest value and the payment probability.

[0098] Among them, the first purchase probability can be a weighted average of the interest value and the payment probability, or can be the maximum or minimum value corresponding to the interest value and the payment probability, etc. This application does not limit the method for obtaining the first purchase probability based on the interest value and the payment probability.

[0099] It can be understood that in steps C21 to C23, the target object's interest value and payment probability for the first insurance are obtained based on the interest characteristics and consumption characteristics, and then the first purchase probability of the first insurance is obtained based on the interest value and the payment probability. The consumption characteristics and interest characteristics of the target object are taken into consideration, which improves the accuracy of obtaining the first purchase probability and facilitates improving the success rate of the push.

[0100] C3: When the first purchase probability is greater than or equal to a second threshold, determining that the first insurance is the target insurance of the associated object.

[0101] This application does not limit the second threshold value, and it can be set according to the consumption characteristics of the target object.

[0102] It can be understood that in steps C1 to C3, the first insurance corresponding to the associated object feature is first searched, and then the first purchase probability of the first insurance is obtained according to the target object feature of the target object. When the first purchase probability is greater than or equal to the second threshold, the first insurance is determined to be the target insurance. In other words, the target insurance determined according to the target object feature and the associated object feature can be pushed to the target object, thereby increasing the success rate of the target object purchasing insurance for the associated object.

[0103] In the embodiment of the present application, the target insurance may be an insurance product recommended to the target object for purchase. In a possible example, step S104 includes the following steps D1 to D4, wherein:

[0104] D1: Obtain the second insurance purchased by the associated object.

[0105] The second insurance can be purchased by the associated object for itself, or for a family member or an item, which is not limited here. It should be noted that the number of the second insurance can be one or more.

[0106] D2: Obtaining a similarity value between the target object feature and the associated object feature.

[0107] The similarity value is used to describe the similarity between the target object features and the associated object features, and can be obtained by comparing feature information of each dimension. The present application does not limit the method for obtaining the similarity value.

[0108] D3: Obtain a second purchase probability of the second insurance according to the target object characteristics and the similarity value.

[0109] The second purchase probability can refer to the description of the first purchase probability, which will not be repeated here. The second purchase probability of the second insurance is obtained according to the target object characteristics and the similarity value. It can be understood that the second purchase probability is obtained according to the target object characteristics on the basis of the similarity value, which improves the accuracy of obtaining the second purchase probability and facilitates improving the accuracy of determining the target insurance.

[0110] D4: When the second purchase probability is greater than or equal to a third threshold, determining that the second insurance is target insurance.

[0111] The present application does not limit the third threshold value, and it may be determined by the number of the second insurance, etc.

[0112] It can be understood that in steps D1 to D4, the second insurance purchased by the associated object is obtained, and the second purchase probability of the target object purchasing the second insurance is obtained based on the similarity value between the target object feature and the associated object feature of the target object, and the target object feature, and when the second purchase probability is greater than or equal to the third threshold, it is determined that the second insurance can be used as the insurance that the target object can purchase, which is convenient for improving the push efficiency. And according to the insurance purchased by the object associated with the user, the insurance is pushed to the target object, which can improve the push efficiency.

[0113] S105: Send push information of the target insurance to the target object.

[0114] In an embodiment of the present application, the push information of the target insurance may be the product information of the target insurance, or the product information corresponding to the associated object in the target insurance, etc., which can improve the recommendation effect. The push information can be described in the form of text, image or video, which is not limited here. When the method is executed by the server, the push information of the target insurance can be sent to the target object according to the contact information of the target object. The contact information of the target object can be the device identifier of the electronic device pre-stored by the target object or the email address, telephone number, etc. of the target object, which is not limited here. When the method is executed by an electronic device, and the user who logs in to the target application in the electronic device is not the target object, the push information of the target insurance can be sent to the target object according to the contact information of the target object. When the method is executed by an electronic device, and the user who logs in to the target application in the electronic device is the target object, sending the push information of the target insurance to the target object can be understood as displaying the push information of the target insurance in the electronic device.

[0115] It can be understood that in steps S101 to S105, the target social information of the target object is first obtained according to the authorization information of the target object, and then the associated object associated with the target object and the target object characteristics of the target object are determined according to the target social information, thereby improving the accuracy of determining the associated object and the target object characteristics. Then, the associated object characteristics of the associated object are obtained, the target insurance is determined according to the target object characteristics and the associated object characteristics, and the push information of the target insurance is sent to the target object. In other words, the insurance pushed to the target object is the insurance related to the target object characteristics and the associated object characteristics, thereby improving the accuracy of the push.

[0116] The method of the embodiment of the present application is described in detail above, and the device of the embodiment of the present application is provided below.

[0117] and Figure 1 The embodiment shown is consistent with that shown in FIG. Figure 2 , Figure 2 is a structural diagram of an information push device proposed in this application, such as Figure 2 As shown, the information push device 200 includes:

[0118] The processing unit 201 is configured to obtain target social information of the target object according to the authorization information of the target object; determine the associated object associated with the target object and the target object characteristics of the target object according to the target social information; obtain the associated object characteristics of the associated object; and determine the target insurance according to the target object characteristics and the associated object characteristics;

[0119] The communication unit 202 is used to send the push information of the target insurance to the target object.

[0120] In a possible example, the processing unit 201 is also used to search the target web page to obtain at least one first object and a first keyword corresponding to the first object; process the first keyword to obtain at least two second keywords; obtain the association relationship between the first objects; and establish a knowledge graph based on the association relationship and the second keywords.

[0121] In a possible example, the processing unit 201 is specifically configured to extract target keywords of the associated object from the target social information; input the target keywords into the knowledge graph to obtain associated object features of the associated object.

[0122] In a possible example, the processing unit 201 is specifically used to search for event information corresponding to the first object based on the first keyword; obtain a third keyword corresponding to the first object based on the event information; select a fourth keyword different from the first keyword from the third keyword; when the fifth keyword in the first keyword and the fourth keyword is similar to the sixth keyword in the first keyword and the fourth keyword, merge the fifth keyword and the sixth keyword to obtain a seventh keyword; combine the keywords in the first keyword and the fourth keyword except the fifth keyword and the sixth keyword with the seventh keyword to obtain at least two second keywords.

[0123] In a possible example, the processing unit 201 is specifically used to identify a second object involved in the target social information; obtain an association value between the target object and the second object according to the target social information; and when the association value is greater than or equal to a first threshold, determine that the second object is an associated object associated with the target object.

[0124] In one possible example, the processing unit 201 is specifically used to search for a first insurance corresponding to the associated object characteristics; obtain a first purchase probability of the first insurance according to the target object characteristics; and determine that the first insurance is the target insurance of the associated object when the first purchase probability is greater than or equal to a second threshold.

[0125] In a possible example, the target object characteristics include interest characteristics and consumption characteristics, and the processing unit 201 is specifically used to obtain the interest value of the target object for the first insurance based on the interest characteristics; obtain the payment probability of the target object for the first insurance based on the consumption characteristics; and obtain the first purchase probability of the first insurance based on the interest value and the payment probability.

[0126] In a possible example, the processing unit 201 is specifically used to obtain a second insurance purchased by the associated object; obtain a similarity value between the target object feature and the associated object feature; obtain a second purchase probability of the second insurance based on the target object feature and the similarity value; when the second purchase probability is greater than or equal to a third threshold, determine that the second insurance is the target insurance.

[0127] The detailed execution process of each unit in the information push device 200 can refer to the execution steps in the aforementioned method embodiment, which will not be repeated here.

[0128] and Figure 1 For details, please refer to Figure 3 , Figure 31 is a schematic diagram of the structure of another information push device provided in an embodiment of the present application, wherein the information push device is an electronic device or a server corresponding to an information push application. Figure 3 As shown, the information push device 300 includes a processor 310 , a memory 320 , a communication interface 330 , and one or at least one program 340 . Figure 2 The related functions implemented by the communication unit 202 shown can be implemented through the communication interface 330. Figure 2 The related functions implemented by the processing unit 201 shown can be implemented by the processor 310 .

[0129] The one or at least one program 340 is stored in the memory 320 and is configured to be executed by the processor 310. The program 340 includes instructions for executing the following steps:

[0130] Acquire target social information of the target object according to the authorization information of the target object;

[0131] Determining, according to the target social information, an associated object associated with the target object and a target object feature of the target object;

[0132] Obtaining associated object characteristics of the associated object;

[0133] Determine target insurance according to the target object characteristics and the associated object characteristics;

[0134] Send push information of the target insurance to the target object.

[0135] In a possible example, before acquiring the associated object feature of the associated object, the program 340 is further used to execute instructions of the following steps:

[0136] Searching a target webpage to obtain at least one first object and a first keyword corresponding to the first object;

[0137] Processing the first keyword to obtain at least two second keywords;

[0138] Acquire the association relationship between the first objects;

[0139] A knowledge graph is established based on the association relationship and the second keyword.

[0140] In a possible example, in the aspect of acquiring the associated object feature of the associated object, the program 340 is specifically used to execute the following steps:

[0141] Extracting target keywords of the associated object from the target social information;

[0142] The target keyword is input into the knowledge graph to obtain the associated object features of the associated object.

[0143] In a possible example, in the aspect of processing the first keyword to obtain at least two second keywords, the program 340 is specifically used to execute instructions of the following steps:

[0144] Searching for event information corresponding to the first object according to the first keyword;

[0145] Acquire a third keyword corresponding to the first object according to the event information;

[0146] Selecting a fourth keyword different from the first keyword from the third keyword;

[0147] When a fifth keyword among the first keyword and the fourth keyword is similar to a sixth keyword among the first keyword and the fourth keyword, the fifth keyword and the sixth keyword are combined to obtain a seventh keyword;

[0148] The keywords of the first keyword and the fourth keyword except the fifth keyword and the sixth keyword are combined with the seventh keyword to obtain at least two second keywords.

[0149] In a possible example, in determining the associated object associated with the target object according to the target social information, the program 340 is specifically used to execute instructions of the following steps:

[0150] identifying a second object involved in the target social information;

[0151] Acquire an association value between the target object and the second object according to the target social information;

[0152] When the association value is greater than or equal to a first threshold, the second object is determined to be an associated object associated with the target object.

[0153] In a possible example, in determining the target insurance according to the target object characteristics and the associated object characteristics, the program 340 is specifically used to execute the following steps:

[0154] Searching for a first insurance corresponding to the associated object feature;

[0155] Acquire a first purchase probability of the first insurance according to the target object characteristics;

[0156] When the first purchase probability is greater than or equal to a second threshold, the first insurance is determined to be the target insurance of the associated object.

[0157] In a possible example, the target object characteristics include interest characteristics and consumption characteristics. In the aspect of obtaining the first purchase probability of the first insurance according to the target object characteristics, the program 340 is specifically used to execute the following steps:

[0158] Acquire the interest value of the target object for the first insurance according to the interest feature;

[0159] Acquire the payment probability of the target object for the first insurance according to the consumption characteristics;

[0160] A first purchase probability of the first insurance is obtained according to the interest value and the payment probability.

[0161] In a possible example, in determining the target insurance according to the target object characteristics and the associated object characteristics, the program 340 is specifically used to execute the following steps:

[0162] Obtain the second insurance purchased by the associated object;

[0163] Obtaining a similarity value between the target object feature and the associated object feature;

[0164] Obtaining a second purchase probability of the second insurance according to the target object feature and the similarity value;

[0165] When the second purchase probability is greater than or equal to a third threshold, the second insurance is determined to be a target insurance.

[0166] An embodiment of the present application also provides a computer storage medium, wherein the computer storage medium stores a computer program, which enables a computer to execute part or all of the steps of any method recorded in the method embodiment, and the computer includes an electronic device and a server.

[0167] The present application also provides a computer program product, which includes a non-transitory computer-readable storage medium storing a computer program, and the computer program is operable to cause a computer to execute to implement some or all steps of any method described in the method embodiment. The computer program product can be a software installation package, and the computer includes an electronic device and a server.

[0168] It should be noted that, for the above-mentioned method embodiments, for the sake of simplicity, they are all expressed as a series of action combinations, but those skilled in the art should be aware that the present application is not limited by the described order of actions, because according to the present application, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all preferred embodiments, and the actions and modes involved are not necessarily required by the present application.

[0169] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0170] In the several embodiments provided in the present application, it should be understood that the disclosed device can be implemented in other ways. For example, the device embodiments described above are only schematic, such as the division of units, which is only a logical function division. There may be other division methods in actual implementation, such as at least one unit or component can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, and the indirect coupling or communication connection of devices or units can be electrical or other forms.

[0171] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on at least one network unit. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0172] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software program mode.

[0173] If the integrated unit is implemented in the form of a software program model and sold or used as an independent product, it can be stored in a computer-readable memory. According to this understanding, the technical solution of the present application, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, which is stored in a memory and includes several instructions for a computer device (which can be a personal computer, server or network device, etc.) to perform all or part of the steps of the various embodiments of the present application. The aforementioned memory includes: U disk, read-only memory (ROM), random access memory (RAM), mobile hard disk, magnetic disk or optical disk, etc., and other media that can store program codes.

[0174] A person skilled in the art may understand that all or part of the steps in the various methods of the above embodiments may be completed by instructing the relevant hardware through a program, and the program may be stored in a computer-readable memory, which may include a flash drive, ROM, RAM, a magnetic disk or an optical disk, etc.

[0175] The embodiments of 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 those skilled in the art, according to the idea of ​​the present application, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as a limitation on the present application.

Claims

1. An information push method, characterized in that: include: Searching a target webpage to obtain at least one first object and a first keyword corresponding to the first object, wherein the first keyword is a word obtained based on information about the first object in the target webpage, and the first keyword includes features of the first object, features of a management object with an associated relationship, an event cause, an event name, and an event result of an event corresponding to the first object; searching for event information corresponding to the first object based on the first keyword, wherein the event information includes hot news in the target webpage and social information that can be obtained from the first object; According to the event cause, event name and event result in the event information, a third keyword corresponding to the first object is obtained; a fourth keyword different from the first keyword is selected from the third keyword; when the fifth keyword in the first keyword and the fourth keyword is similar to the sixth keyword in the first keyword and the fourth keyword, the fifth keyword and the sixth keyword are combined to obtain a seventh keyword; the keywords in the first keyword and the fourth keyword except the fifth keyword and the sixth keyword are combined with the seventh keyword to obtain at least two second keywords; the association relationship between the first objects is obtained; and a knowledge graph is established according to the association relationship and the second keyword; Acquire target social information of the target object according to the authorization information of the target object; Determining, according to the target social information, an associated object associated with the target object and a target object feature of the target object; Acquiring associated object features of the associated object, wherein the associated object is an object other than the target object involved in the target social information, and the associated object features include associated object consumption features, associated object interest features, associated object social features, associated object credit features, and associated object occupation features. Acquiring the associated object features of the associated object includes: extracting a target keyword of the associated object from the target social information; inputting the target keyword into the knowledge graph to obtain the associated object features of the associated object, and the target keyword may include the name, age, address, work unit, and education level of the associated object; Determine a target insurance according to the target object characteristics and the associated object characteristics, the target insurance is an insurance product recommended to the target object for the associated object to purchase, the target object characteristics include interest characteristics and consumption characteristics, and the determining the target insurance according to the target object characteristics and the associated object characteristics includes: searching for a first insurance corresponding to the associated object characteristics, the first insurance being an insurance suitable for the associated object to purchase; obtaining the interest value of the target object for the first insurance according to the interest characteristics; obtaining the payment probability of the target object for the first insurance according to the consumption characteristics; obtaining a first purchase probability of the first insurance according to the interest value and the payment probability; and determining the first insurance as the target insurance when the first purchase probability is greater than or equal to a second threshold; Send push information of the target insurance to the target object.

2. The method according to claim 1, characterized in that The determining, according to the target social information, an associated object associated with the target object includes: identifying a second object involved in the target social information; Acquire an association value between the target object and the second object according to the target social information; When the association value is greater than or equal to a first threshold, the second object is determined to be an associated object associated with the target object.

3. The method according to claim 2, characterized in that The determining of target insurance according to the target object characteristics and the associated object characteristics includes: Obtain the second insurance purchased by the associated object; Obtaining a similarity value between the target object feature and the associated object feature; Acquire a second purchase probability of the second insurance according to the target object feature and the similarity value; When the second purchase probability is greater than or equal to a third threshold, the second insurance is determined to be a target insurance.

4. An information push device, the device is used to execute the method according to any one of claims 1 to 3, characterized in that: include: A processing unit, configured to obtain target social information of the target object according to the authorization information of the target object; Determining, according to the target social information, an associated object associated with the target object and a target object feature of the target object; Acquire the associated object characteristics of the associated object; determine the target insurance according to the target object characteristics and the associated object characteristics; A communication unit is used to send push information of the target insurance to the target object.

5. An information push device, characterized in that: The method comprises a processor, a memory, a communication interface and one or at least one program, wherein the one or at least one program is stored in the memory and configured to be executed by the processor, and the program comprises instructions for executing the steps in any one of the methods of claims 1 to 3.

6. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, which enables a computer to execute to implement the method according to any one of claims 1 to 3.

Images