CN113254836B

CN113254836B - Intelligent child-care knowledge point information pushing method and system and cloud platform

Info

Publication number: CN113254836B
Application number: CN202110664321.1A
Authority: CN
Inventors: 郭春林; 胡宇; 周自力; 施欧军
Original assignee: Changsha Douya Culture Technology Co ltd
Current assignee: Changsha Douya Culture Technology Co ltd
Priority date: 2021-06-16
Filing date: 2021-06-16
Publication date: 2021-09-14
Anticipated expiration: 2041-06-16
Also published as: CN113254836A

Abstract

The embodiment of the disclosure provides an intelligent child-rearing knowledge point information pushing method, an intelligent child-rearing knowledge point information pushing system and a cloud platform, wherein at least one child-rearing conversation behavior data generated under an online child-rearing knowledge social application is acquired for a community child-rearing conversation group in a preset child-rearing subscription stage, frequent question-answer item analysis is performed based on the at least one child-rearing conversation behavior data to obtain a plurality of reference frequent question-answer items matched with the community child-rearing conversation group, then interest parameter clusters corresponding to the plurality of reference frequent question-answer items are determined, interest knowledge point data of the community child-rearing conversation group are determined, and then application page pushing data of related child-rearing knowledge points matched with the interest knowledge point data are acquired from a pre-subscribed child-rearing knowledge point data source to perform page recommendation. Therefore, the data of the interest knowledge point of the community childbearing conversation group is used for pushing the data of the application page of the related childbearing knowledge point, and the information acquisition efficiency of the related user needing the personalized pushing service is improved.

Description

Intelligent child-care knowledge point information pushing method and system and cloud platform

Technical Field

The disclosure relates to the technical field of computers, in particular to an intelligent child care knowledge point information pushing method, an intelligent child care knowledge point information pushing system and a cloud platform.

Background

In the related art, the services of providing nutrition, health, development and education for internet users at the child-bearing stage are mainly performed by data push and release of some online child-bearing service platforms, but these online child-bearing service platforms also have obvious defects at present, for example, a conventional child-bearing knowledge point information push strategy is usually fixed, for example, content services are provided according to different birth times and sexes of users, and personalized push services cannot be performed according to the own interest knowledge points of each user.

Disclosure of Invention

In order to overcome at least the above disadvantages in the prior art, an object of the present disclosure is to provide an intelligent child care knowledge point information pushing method, system and cloud platform.

In a first aspect, the present disclosure provides an intelligent child care knowledge point information pushing method, which is applied to an intelligent child care cloud platform, wherein the intelligent child care cloud platform is in communication connection with a plurality of intelligent child care service terminals, and the method includes:

acquiring at least one childcare session behavior data generated by a community childcare session group in a preset childcare subscription stage in an intelligent childcare interactive community under an online childcare knowledge social application;

performing frequent question-answer item analysis on the at least one child-care conversation behavior data to obtain a plurality of reference frequent question-answer items matched with the community child-care conversation group;

for each reference frequent question-answering item in a plurality of reference frequent question-answering items, determining interest parameters of the community nursery conversation group and the reference frequent question-answering item in the at least one piece of childbearing session behavior data based on session collaboration data of the community nursery conversation group in the at least one piece of childbearing session behavior data and frequent item description data of the reference frequent question-answering item in the at least one piece of childbearing session behavior data, and obtaining an interest parameter cluster corresponding to the reference frequent question-answering item;

determining interest knowledge point data of the community nursery conversation group according to interest parameter clusters corresponding to the multiple reference frequent question and answer items respectively;

and acquiring application page push data of the related child bearing knowledge points matched with the interest knowledge point data from a pre-subscribed child bearing knowledge point data source according to the interest knowledge point data, and recommending pages to the community child bearing session group.

In a second aspect, an embodiment of the present disclosure further provides an intelligent child care knowledge point information pushing system, where the intelligent child care knowledge point information pushing system includes an intelligent child care cloud platform and a plurality of intelligent child care service terminals in communication connection with the intelligent child care cloud platform;

the intelligent child-rearing cloud platform is used for:

According to any one of the aspects, in the embodiment provided by the disclosure, at least one piece of childbearing session behavior data generated under social application of online childbearing knowledge is acquired for a community childbearing session group in a preset childbearing subscription stage, and frequent question-answer item analysis is performed based on the at least one piece of childbearing session behavior data to obtain a plurality of reference frequent question-answer items matched with the community childbearing session group; and then determining interest parameter clusters corresponding to the multiple reference frequent question and answer items, determining interest knowledge point data of the community nursery conversation group based on the interest parameter clusters corresponding to the multiple reference frequent question and answer items, and then obtaining application page push data of related nursery knowledge points matched with the interest knowledge point data from a pre-subscribed nursery knowledge point data source to perform page recommendation to the community nursery conversation group. Therefore, the data of the interest knowledge point of the community childbearing conversation group is used for pushing the data of the application page of the related childbearing knowledge point, and the information acquisition efficiency of the related user needing the personalized pushing service is improved.

Drawings

In order to more clearly illustrate the technical solutions of the embodiments of the present disclosure, the drawings that need to be called in the embodiments are briefly described below, it should be understood that the following drawings only illustrate some embodiments of the present disclosure, and therefore should not be considered as limiting the scope, and for those skilled in the art, other related drawings can be obtained according to the drawings without inventive efforts.

Fig. 1 is a schematic view of an application scenario of an intelligent child care knowledge point information pushing system according to an embodiment of the present disclosure;

fig. 2 is a schematic flow chart of an intelligent child-care knowledge point information pushing method according to an embodiment of the present disclosure;

fig. 3 is a block diagram schematically illustrating the structure of an intelligent child-care cloud platform for implementing the above-mentioned intelligent child-care knowledge point information pushing method according to the embodiment of the present disclosure.

Detailed Description

The present disclosure is described in detail below with reference to the drawings, and the specific operation methods in the method embodiments can also be applied to the device embodiments or the system embodiments.

Fig. 1 is a schematic view of an application scenario of an intelligent child care knowledge point information pushing system 10 according to an embodiment of the present disclosure. The intelligent child care knowledge point information push system 10 may include an intelligent child care cloud platform 100 and an intelligent child care service terminal 200 communicatively connected to the intelligent child care cloud platform 100. The intelligent child care knowledge point information push system 10 shown in FIG. 1 is only one possible example, and in other possible embodiments, the intelligent child care knowledge point information push system 10 may include only at least some of the components shown in FIG. 1 or may include other components.

In a possible design, the intelligent child care cloud platform 100 and the intelligent child care service terminal 200 in the intelligent child care knowledge point information push system 10 can cooperatively execute the intelligent child care knowledge point information push method described in the following method embodiments, and the detailed description of the method embodiments can be referred to in the following steps of executing the intelligent child care cloud platform 100 and the intelligent child care service terminal 200.

In order to solve the technical problems in the background art, the intelligent child-care knowledge point information pushing method provided by the present embodiment may be executed by the intelligent child-care cloud platform 100 shown in fig. 1, and the intelligent child-care knowledge point information pushing method will be described in detail below.

Step S110, acquiring at least one childcare session behavior data generated by a community childcare session group in a preset childcare subscription stage in the intelligent childcare interactive community under the online childcare knowledge social application.

In one possible design approach, the intelligent childcare cloud platform 100 may construct a historical interest assessment model that can obtain childcare session behavior data generated by the community childcare session group in real time during online childcare interaction of the community childcare session group.

In one possible design approach, in the child-care interaction process of the community child-care conversation group, the child-care conversation behavior data can be continuously collected in an application enabling stage under the social application of online child-care knowledge, and the child-care conversation behavior data collected in one application enabling stage forms a group of child-care conversation behavior data.

Step S120, performing frequent question-answer item analysis on the at least one child-care conversation behavior data to obtain a plurality of reference frequent question-answer items matched with the community child-care conversation group.

In this embodiment, when determining a plurality of reference frequent question-and-answer items matched with a community nursery conversation group in an online nursery interaction process of the community nursery conversation group, frequent question-and-answer item analysis may be performed based on each group of nursery conversation behavior data in at least one nursery conversation behavior data, and frequent item description data of the reference frequent question-and-answer items of the plurality of reference frequent question-and-answer items matched with the community nursery conversation group in each group of nursery conversation behavior data is determined. Then, a plurality of reference frequent question-and-answer items matching the community nursery conversation group are determined based on the frequent item description data of the reference frequent question-and-answer items.

For example, in each group of childbearing conversational behavior data, frequent question-answer contents of a frequent question-answer item matching the community childbearing conversational group are determined, and based on the frequent question-answer contents, a reference frequent question-answer item matching the first matching label vector of the community childbearing conversational group is determined. And determining frequent question-answer content of a frequent question-answer item matched with the second matching label vector of the community nursery conversation group in each group of nursery conversation behavior data, and determining a reference frequent question-answer item matched with the community nursery conversation group based on the frequent question-answer content.

For another example, in one possible design approach, frequent item description data of a reference frequent question-and-answer item of a plurality of reference frequent question-and-answer items is determined as follows.

The acquired at least one childbearing session behavior data is respectively recorded into a frequent item mining model, the at least one childbearing session behavior data is respectively subjected to frequent item parameter analysis based on the frequent item mining model, and a plurality of reference frequent question-answer items matched with a community childbearing session group and contained in the at least one childbearing session behavior data are analyzed.

For example, the frequent item parameter analysis is performed by a plurality of different frequent item parameter analysis layers (e.g., four frequent item parameter analysis layers) included in the frequent item mining model, and the obtained reference frequent question and answer items matched with the community nursery conversation group may include a first frequent question and answer item TRE1, a second frequent question and answer item TRE2, a third frequent question and answer item TRE3, a fourth frequent question and answer item TRE4, and the like matched with the community nursery conversation group. The first frequent question and answer item TRE1, the second frequent question and answer item TRE2, the third frequent question and answer item TRE3, and the fourth frequent question and answer item TRE4 may respectively correspond to the four frequent item parameter analysis layers one to one. Different frequent item parameter analysis units can perform frequent item parameter analysis based on different dimensions to obtain corresponding frequent question and answer items under different dimensions.

In another design idea, description component extraction may be performed on a plurality of reference frequent question and answer items through description component extraction, so as to obtain childbearing conversation behavior data after the description component extraction.

Taking the example that the description component extracted includes a plurality of reference frequent question-answer items matched with the community nursery conversation group, a description component set of a plurality of frequent question-answer items corresponding to the plurality of reference frequent question-answer items in the nursery test hotspot delivery scene can be obtained. Then, the obtained description component sets of the multiple frequent question and answer items corresponding to the multiple reference frequent question and answer items are used as the frequent item description data of the reference frequent question and answer items corresponding to the multiple reference frequent question and answer items in the corresponding childbearing session behavior data. Thus, a set of childbearing session behavior data may correspond to a plurality of reference frequent question-answering items, each of which corresponds to a set of descriptive components of a frequent question-answering item. The child bearing test hotspot launching scene may be a preset application scene for describing a child bearing hotspot to be currently launched.

In one possible design approach, after a plurality of reference frequent question and answer items matched with a community nursery conversation group are determined in acquired nursery conversation behavior data, for the determined plurality of reference frequent question and answer items, interest parameters between the community nursery conversation group and each of the plurality of reference frequent question and answer items can be respectively determined, and interest parameter clusters corresponding to the plurality of reference frequent question and answer items are further determined.

For example, the method is not limited to the specific steps of determining an interest parameter cluster between the community nursery conversation group and the first reference frequent question and answer item TRE1, determining an interest parameter cluster between the community nursery conversation group and the second reference frequent question and answer item TRE2, determining an interest parameter cluster between the community nursery conversation group and the third reference frequent question and answer item TRE3, and determining an interest parameter cluster between the community nursery conversation group and the fourth reference frequent question and answer item TRE 4.

In detail, in step S130, for each of a plurality of reference frequent question-and-answer items, based on the session collaboration data of the community nursery session group in the at least one nursery session behavior data and the frequent item description data of the reference frequent question-and-answer item in the at least one nursery session behavior data, the interest parameters of the community nursery session group and the reference frequent question-and-answer item in the at least one nursery session behavior data are determined, and the interest parameter cluster corresponding to the reference frequent question-and-answer item is obtained.

In one possible design approach, based on each set of childbearing conversational behavior data in the acquired at least one set of childbearing conversational behavior data, a plurality of reference frequent question-answer items matched with the community childbearing conversational group, frequent item description data of the reference frequent question-answer items corresponding to each reference frequent question-answer item, and conversational collaboration data of the community childbearing conversational group may be determined in the set of childbearing conversational behavior data. Then, based on the frequent item description data of the reference frequent question-and-answer item and the session collaboration data of the community nursery session group, an interest parameter between the community nursery session group and the reference frequent question-and-answer item is determined.

Therefore, the interest parameters between the reference frequent question and answer items and the community nursery conversation group in the acquired at least one piece of nursery conversation behavior data can be respectively determined. For example, each set of childbearing session behavior data requires determination of a combination of at least one or more of an interest parameter between the first reference frequent question and answer item TRE1 of the community childbearing session group and the community childbearing session group, an interest parameter between the second reference frequent question and answer item TRE2 matched with the community childbearing session group and the community childbearing session group, an interest parameter between the third reference frequent question and answer item TRE3 matched with the community childbearing session group and the community childbearing session group, an interest parameter between the fourth reference frequent question and answer item TRE4 matched with the community childbearing session group and the community childbearing session group, and the like.

Illustratively, after the interest parameter between the first reference frequent question and answer item TRE1 of the community childbearing conversation group and the community childbearing conversation group, the interest parameter between the second reference frequent question and answer item TRE2 matched with the community childbearing conversation group and the community childbearing conversation group, the interest parameter between the third reference frequent question and answer item TRE3 matched with the community childbearing conversation group and the interest parameter between the fourth reference frequent question and answer item TRE4 matched with the community childbearing conversation group and the community childbearing conversation group are sorted according to the generation time of the childbearing conversation behavior data, the interest parameter cluster is obtained.

The first interest parameter in the interest parameter cluster may be an interest parameter corresponding to the first set of acquired childbearing session behavior data, the second interest parameter may be an interest parameter corresponding to the second set of acquired childbearing session behavior data, and so on.

The following describes an acquisition manner of an interest parameter by taking as an example that each piece of session behavior data in at least one piece of childbearing session behavior data determines an interest parameter between a reference frequent question-and-answer item and a community childbearing session group. For example, for a set of childbearing conversational behavior data, an interest parameter between a reference frequent question-and-answer item 1 that matches a community childbearing conversational group and the community childbearing conversational group is determined.

In a possible design idea, when determining interest parameters between a community childbearing session group and a reference frequent question and answer item for each group of childbearing session behavior data in at least one piece of childbearing session behavior data, the interest parameters may be directly determined based on frequent question and answer features in the currently traversed childbearing session behavior data, and item content analysis may be performed on frequent question and answer content according to a description component set corresponding to the reference frequent question and answer item in the currently traversed childbearing session behavior data to determine frequent question and answer content for indicating the reference frequent question and answer item, and the interest parameters may be determined according to the frequent question and answer content, that is, the interest parameters are obtained based on the frequent question and answer features.

In one implementation, determining the interest parameter based on the frequent question-and-answer feature, for example, may include the following steps a-c.

Step a, in the current traversed child-bearing session behavior data, determining a frequent question-answer characteristic as a candidate question-answer characteristic based on a description component set corresponding to the frequent question-answer content of the reference frequent question-answer item. The currently traversed child-bearing session behavior data may refer to a set of currently processed child-bearing session behavior data, and after one set is processed, another set is processed, so that the other set becomes the currently traversed child-bearing session behavior data. The manner of obtaining the description component set of the frequent question and answer items is introduced in step S120, and is not described herein.

In one possible design approach, based on a description component set corresponding to frequent question-answering contents of a reference frequent question-answering project, a frequent question-answering feature may be determined as a candidate question-answering feature according to a set manner (e.g., a random or sequential traversal manner). The candidate question-answer features may be any one of the description component sets of frequent question-answer items for indicating frequent question-answer features in the currently traversed data of childbearing session behavior with reference to the related attributes of the frequent question-answer items.

And b, determining candidate child-rearing session behavior data matched with the latest session group image tag of the community child-rearing session group in the currently traversed child-rearing session behavior data based on the candidate question-answer feature, and taking the intersection session behavior feature of the candidate child-rearing session behavior data and the latest session group image tag as an image matching behavior feature, wherein the latest session group image tag is obtained based on session cooperation data of the community child-rearing session group in the currently traversed child-rearing session behavior data in a preset product stage before the current session product stage, and indicates the current session image tag of the community child-rearing session group in the currently traversed child-rearing session behavior data. In this embodiment, a feature vector of an intersection of the candidate childbearing session behavior data and the latest session group image tag may be used as the intersection session behavior feature.

Wherein the latest session group portrait label may be obtained based on session collaboration data of the community nursery session group in the currently traversed nursery session behavior data, and is used to indicate a current session portrait label of the community nursery session group in the currently traversed nursery session behavior data.

For example, current traversal nursery session behavior data of the community nursery session group acquired through the historical interest assessment model, session operations of the community nursery session group corresponding to the data content of the acquired current traversal nursery session behavior data, and thus the latest session group portrait tag indicating the session portrait tag and attribute information of the community nursery session group in the current traversal nursery session behavior data is associated with the frequent question and answer item portrait. The candidate childbearing conversational behavior data is conversational behavior data with portrait correlation relation with the candidate question-answer feature and the latest conversational group portrait label. Therefore, based on the correlation data of the candidate childbearing session behavior data and the latest session group image tag, the image matching behavior feature can be determined.

And c, determining interest parameters of the community childbearing session group and the reference frequent question and answer item in the currently traversed childbearing session behavior data based on the candidate question and answer characteristics and the portrait matching behavior characteristics, and obtaining an interest parameter cluster corresponding to the reference frequent question and answer item based on the interest parameters corresponding to the at least one childbearing session behavior data.

In the embodiment, the interest parameters between the community nursery conversation group and a reference frequent question and answer item can be determined by determining the interest parameters of the community nursery conversation group and the reference frequent question and answer item in the currently traversed nursery conversation behavior data. Based on the above, it is necessary to map the candidate question-answering features and the portrait matching behavior features to the portrait dimensions of the childbearing conversation group, and determine the interest parameters based on the mapped feature vectors. Alternatively, a relative interest parameter may be determined based on the candidate question-answering feature and the portrait matching behavior feature, and the relative interest parameter determined under the candidate question-answering feature and the portrait matching behavior feature may be mapped to the actual interest parameter under the community childbearing session feature.

In a possible implementation manner, in step c, based on the candidate question-answering features and the portrait matching behavior features, the interest parameters of the community childbearing session group and the reference frequent question-answering item in the currently traversed childbearing session behavior data are determined, which may be implemented in the following two ways.

Firstly, determining a characteristic interest probability variation trend between the candidate question answering characteristics and the portrait matching behavior characteristics, carrying out characteristic regularization processing on the characteristic interest probability variation trend according to a preset characteristic regularization template, and taking characteristic regularization data obtained after the characteristic regularization processing as interest parameters of the community child-rearing conversation group and the reference frequent question answering item. Wherein the preset feature regularization template is determined based on model weight data of a historical interest assessment model. For example, in this embodiment, the feature regularization template may perform regularization transformation according to a feature interest probability variation trend value, and use regularization data as an interest parameter. For example, the model weight data of the historical interest evaluation model may include a template identifier corresponding to a specific feature regularization template and corresponding configuration data.

Secondly, mapping the candidate question-answer characteristics and the portrait matching behavior characteristics into corresponding reference frequent question-answer characteristics and target portrait matching behavior characteristics under portrait dimensions of the child-rearing conversation group respectively based on model weight data of the historical interest evaluation model, and determining interest parameters of the community child-rearing conversation group and the reference frequent question-answer items based on the reference frequent question-answer characteristics and the target portrait matching behavior characteristics.

It should be noted that, in a possible design idea, a feature interest probability variation trend between the candidate question-answering feature and the image matching behavior feature may also be used as an interest parameter between the community nursery conversation group and a reference frequent question-answering item.

In another design approach, another way to determine the interest parameter cluster based on the frequent question-and-answer feature may include the following steps e-g.

Step e, sequentially traversing each piece of session behavior data in the at least one piece of childbearing session behavior data, mapping a plurality of frequent question-answer characteristics in a description component set corresponding to frequent question-answer contents of the reference frequent question-answer project to an image dimension of a childbearing session group based on model weight data of a historical interest evaluation model in the currently traversed childbearing session behavior data to obtain a corresponding reference frequent question-answer characteristic set, and mapping session collaboration data of the community childbearing session group to the image dimension of the childbearing session group to obtain a corresponding session image collaboration characteristic.

Wherein the historical interest assessment model is a data collection module that generates at least one childbearing session behavioral data.

And f, analyzing the item content of the reference frequent question-answer item based on the reference frequent question-answer feature set, and determining the frequent question-answer content of the reference frequent question-answer item in the currently traversed child-bearing session behavior data under the portrait dimension of the child-bearing session group. The portrait dimension of the nursery conversation group refers to a dimension for expressing or describing features related to the nursery conversation group through frequent item description data.

And g, determining interest parameters of the community nursery conversation group and the reference frequent question and answer item based on the frequent question and answer content and the conversation portrait collaborative feature, and obtaining an interest parameter cluster corresponding to the reference frequent question and answer item based on the interest parameters corresponding to the at least one nursery conversation behavior data.

In a possible design idea, the portrait dimension of the nursery conversation group can be the attribute distribution of portrait labels of the community nursery conversation group, and the actual meaning of the interest parameter can represent the business jump interest probability variation trend between the community nursery conversation group and the reference frequent question and answer item. Therefore, the interest parameters of the community nursery conversation group and the reference frequent question and answer items can be determined according to the frequent question and answer contents determined by the item content analysis and the conversation portrait collaborative characteristics, or the attention degree between the community nursery conversation group and the reference frequent question and answer items can also be determined.

Step S140, according to the interest parameter clusters corresponding to the multiple reference frequent question and answer items, determining the interest knowledge point data of the community nursery conversation group.

In a possible design approach, the point-of-interest knowledge data of the community nursery conversation group may be service operation interest with or without a reference frequent question and answer item, or may also be a quantized indicator for indicating interest degree of the corresponding reference frequent question and answer item, which is not limited specifically.

Illustratively, in a first possible approach, the point-of-interest knowledge data between the community nursery session group and the reference frequent question-and-answer item may be determined based on a plurality of consecutive interest parameters in a plurality of target interest parameter clusters.

In one possible design approach, the point of interest knowledge data for the community nursery session group may be determined based on the cluster of interest parameters. Therefore, in a plurality of interest parameter clusters, one interest parameter cluster may be determined as a target interest parameter cluster, or all interest parameter clusters may be used as target interest parameter clusters and then sequentially traversed.

The point-of-interest knowledge data of the community nursery conversation group is explained by taking any target interest parameter cluster in the plurality of determined target interest parameter clusters as an example. For example, one interest parameter cluster is determined from a plurality of interest parameter clusters as a target interest parameter cluster, and at this time, if it is determined that the interest parameters between the community nursery conversation group and the reference frequent question-and-answer item 1 corresponding to the target interest parameter cluster are gradually decreased based on the interest probabilities of a plurality of consecutive interest parameters in the target interest parameter cluster, it is determined that the community nursery conversation group does not have business operation interest in the reference frequent question-and-answer item 1, and vice versa. As can be seen from the above, the present disclosure is also applicable to the following cases, in which the point-of-interest knowledge data of the community nursery conversation group is determined from the interest parameter cluster, and is also related to the image dimension of the established nursery conversation group.

In another possible implementation, the point-of-knowledge data of interest to the community nursery conversation group for the reference frequent question and answer item may be determined based on the attention-interested objects of the community nursery conversation group.

For example, first, the implementation interest knowledge point information of the community nursery conversation group for the reference frequent question and answer item can be determined based on the interest attention object of the community nursery conversation group; wherein the interest attention object of the community nursery conversation group is related to the interest tracing service node of the community nursery conversation group.

Therefore, in a possible design idea, when determining the implementation interest knowledge point information of the community nursery conversation group for the reference frequent question and answer item based on the interest tracing service node of the community nursery conversation group, an interest tracing service node cluster of the community nursery conversation group needs to be determined, and the interest tracing service node cluster comprises a plurality of interest tracing service nodes.

In one possible design approach, based on a plurality of interest parameter clusters, for example, a plurality of corresponding interest tracing service node clusters are respectively determined, that is, different interest parameter clusters correspond to different interest tracing service node clusters.

Specifically, each interest parameter cluster in the multiple interest parameter clusters is respectively subjected to interest label binding, so that an interest tracing service node cluster corresponding to each interest parameter cluster can be respectively obtained. Each interest tracing service node contained in each interest tracing service node cluster can indicate a session image label and an interest operation object of the community nursery session group.

In a possible design idea, the interest knowledge point data of the community nursery session group can be determined according to the interest tracing service node cluster and any one of the interest tracing service node clusters, and the interest knowledge point data of the community nursery session group can also be determined according to the two interest tracing service node clusters.

Therefore, in the plurality of interest tracing service node clusters, any interest tracing service node cluster can be determined to serve as a target interest tracing service node cluster, or all the interest tracing service node clusters are used as the target interest tracing service node cluster to perform traversal processing in subsequent steps.

The interest knowledge point data of the community nursery conversation group is explained by taking any target interest tracing service node cluster in the plurality of determined target interest tracing service node clusters as an example. For example, an interest tracing service node cluster is determined from the interest tracing service node clusters as a target interest tracing service node cluster. At this time, if any interest tracing service node in the target interest tracing service node cluster is based on, the session sketch tag of the community nursery session group is determined, and the service operation interest of the reference frequent question and answer item 1 corresponding to the target interest tracing service node cluster is determined to be possessed or not possessed by the community nursery session group based on the session sketch tag of the community nursery session group.

Firstly, for any target interest tracing service node cluster in a plurality of target interest tracing service node clusters, when a target number of interest tracing service nodes in the target interest tracing service node cluster indicate that interest attention objects of the community nursery session group are inconsistent and the service operation duration of any interest tracing service node in the target number of interest tracing service nodes is less than a first preset duration, determining that the community nursery session group does not have the service operation interest of a matched reference frequent question and answer item matched with the interest attention object;

or, for any target interest tracing service node cluster in the target interest tracing service node clusters, when a target number of interest tracing service nodes included in the target interest tracing service node cluster indicate that the interest attention objects of the community nursery session group are consistent, and the service operation duration of the target number of interest tracing service nodes is longer than a second preset duration, it is determined that the community nursery session group has a service operation interest of a matched reference frequent question and answer item matched with the interest attention object.

In this embodiment, before determining the interest tracing service node cluster corresponding to the reference frequent question and answer item based on the interest parameter cluster corresponding to the reference frequent question and answer item, weight fusion may be performed on the interest parameter cluster corresponding to the reference frequent question and answer item based on a weighting parameter, where the weighting parameter is determined based on the interest parameter cluster corresponding to the reference frequent question and answer item respectively matched with each of the child-bearing session groups before and after the community child-bearing session group among the reference frequent question and answer items matched with the community child-bearing session group, and the service priority of the current e-commerce service of the community child-bearing session group.

Step S150, according to the interest knowledge point data, obtaining application page push data of related child care knowledge points matched with the interest knowledge point data from a pre-subscribed child care knowledge point data source, and performing page recommendation to the community child care conversation group.

In this embodiment, after the point of interest knowledge data is obtained, a page recommendation may be performed for the community nursery conversation group according to the point of interest knowledge data.

For example, step S150 may be implemented by the following exemplary sub-steps.

Substep S151, obtaining target reference application page pushing data matched with the interest knowledge point data, past content feedback data corresponding to the target reference application page pushing data and page function data to be online corresponding to the target reference application page pushing data from a pre-subscribed knowledge point data source, wherein the page function data to be online is determined based on pushing state data of related online services of the interest knowledge point data in the target reference application page pushing data;

a substep S152, calling a preset AI model, and obtaining a priority probability distribution of a page recommendation behavior corresponding to the target reference application page push data based on the past content feedback data and the to-be-online page function data, where the priority probability distribution of the page recommendation behavior is used to express a page recommendation tag of each page recommendation behavior in the target reference application page push data, and the page recommendation tag of any page recommendation behavior is used to express a probability distribution that the any page recommendation behavior is matched with each page plate of the current reference application page;

substep S153, based on the priority probability distribution of the page recommendation behavior, performing page plate data reference on the interest knowledge point data in the target reference application page push data to obtain reference page plate data of the interest knowledge point data in the target reference application page push data;

substep S154, performing page recommendation to the community nursery conversation group based on the reference page plate data of the interest knowledge point data in the target reference application page push data

For example, the substep S152 may be implemented by the following exemplary embodiments.

(1) Calling a preset AI model, and sequentially executing first target number turn feedback tendency attribute mining based on the past content feedback data and the forward feedback data of the page function data to be online to obtain a first feedback tendency attribute characteristic corresponding to the target reference application page push data;

(2) sequentially executing the first target number round weight calculation based on the target tendency attribute influence weight corresponding to the first feedback tendency attribute characteristic to obtain a second feedback tendency attribute characteristic corresponding to the target reference application page push data;

(3) performing target weight fusion on the second feedback tendency attribute characteristics to obtain priority probability distribution of page recommendation behaviors corresponding to the target reference application page pushing data;

for example, the first target number of rounds is three, and any feedback tendency attribute mining comprises one weight fusion and one noise optimization. In step (1), a first weight fusion may be performed on the forward feedback data of the past content feedback data and the to-be-online page function data to obtain a first tendency attribute influence weight corresponding to the target reference application page push data, a first noise optimization may be performed on the first tendency attribute influence weight to obtain a first noise optimization characteristic corresponding to the target reference application page push data, a second weight fusion may be performed on the first noise optimization characteristic to obtain a second tendency attribute influence weight corresponding to the target reference application page push data, a second noise optimization may be performed on the second tendency attribute influence weight to obtain a second noise optimization characteristic corresponding to the target reference application page push data, a third weight fusion may be performed on the second noise optimization characteristic to obtain a third tendency attribute influence weight corresponding to the target reference application page push data, performing third noise optimization on the third tendency attribute influence weight to obtain a first feedback tendency attribute characteristic corresponding to the target reference application page pushing data;

in (2), a first inverse weight fusion may be performed on a target tendency attribute influence weight corresponding to the first feedback tendency attribute feature to obtain a first fusion feedback tendency attribute feature corresponding to the target reference application page push data, a fourth weight fusion may be performed on a third fusion feedback tendency attribute feature of the first fusion feedback tendency attribute feature and the third tendency attribute influence weight to obtain a fourth tendency attribute influence weight corresponding to the target reference application page push data, a second inverse weight fusion may be performed on the fourth tendency attribute influence weight to obtain a second fusion feedback tendency attribute feature corresponding to the target reference application page push data, and a fifth weight fusion may be performed on the second fusion feedback tendency attribute feature and the third fusion feedback tendency attribute feature of the second tendency attribute influence weight And combining to obtain a fifth tendency attribute influence weight corresponding to the target reference application page pushing data, performing third inverse weight fusion on the fifth tendency attribute influence weight to obtain a third fusion feedback tendency attribute characteristic corresponding to the target reference application page pushing data, and performing sixth weight fusion on the third fusion feedback tendency attribute characteristic and the third fusion feedback tendency attribute characteristic of the first tendency attribute influence weight to obtain a second feedback tendency attribute characteristic corresponding to the target reference application page pushing data.

Based on the above description, the following exemplary description of an implementation flow of the integrity provided by the present embodiment follows.

Firstly, in the online childbearing interaction process of the community childbearing conversation group, the intelligent childbearing cloud platform 100 acquires childbearing conversation behavior data generated by at least one community childbearing conversation group in the service use process under the social application of online childbearing knowledge through a service acquisition module;

then, the intelligent child-rearing cloud platform 100 analyzes the frequent question-answer items in at least one child-rearing session behavior data based on the frequent item mining model to obtain a plurality of reference frequent question-answer items matched with the community child-rearing session group, and analyzes a description component set corresponding to each reference frequent question-answer item in the plurality of reference frequent question-answer items.

Then, the intelligent childcare cloud platform 100 maps each frequent question-answer feature in the description component set corresponding to the multiple reference frequent question-answer items to the portrait dimension of the childcare conversation group, and determines a reference frequent question-answer feature set corresponding to the multiple reference frequent question-answer items.

Then, the intelligent childcare cloud platform 100 obtains frequent question-answer contents for indicating a plurality of reference frequent question-answer items corresponding to a group of childcare session behavior data, respectively, based on a preset frequent question-answer content expression form and a reference frequent question-answer feature set corresponding to the plurality of reference frequent question-answer items.

Then, the intelligent child-rearing cloud platform 100 determines interest parameters between the community child-rearing conversation group and the plurality of reference frequent question-answer items respectively based on the frequent question-answer contents of the plurality of reference frequent question-answer items and the portrait dimension of the community child-rearing conversation group in the child-rearing conversation group, and determines interest parameter clusters corresponding to the plurality of reference frequent question-answer items respectively based on the interest parameters between the community child-rearing conversation group corresponding to at least one piece of child-rearing conversation behavior data and the plurality of reference frequent question-answer items.

Finally, the intelligent child rearing cloud platform 100 determines interest knowledge point data of the community child rearing session group based on the obtained interest parameter clusters corresponding to the multiple reference frequent question and answer items, acquires application page push data of related child rearing knowledge points matched with the interest knowledge point data from a pre-subscribed child rearing knowledge point data source according to the interest knowledge point data, and carries out page recommendation on the community child rearing session group.

Fig. 3 illustrates a hardware structure of the intelligent child care cloud platform 100 for implementing the intelligent child care knowledge point information pushing method according to the embodiment of the present disclosure, and as shown in fig. 3, the intelligent child care cloud platform 100 may include a processor 110, a machine-readable storage medium 120, a bus 130, and a communication unit 140.

In a specific implementation process, the processors 110 execute the computer executable instructions stored in the machine readable storage medium 120, so that the processors 110 can execute the intelligent child care knowledge point information pushing method according to the above method embodiment, the processors 110, the machine readable storage medium 120 and the communication unit 140 are connected through the bus 130, and the processors 110 can be used for controlling the transceiving action of the communication unit 140, so as to perform data transceiving with the intelligent child care service terminal 200.

Machine-readable storage medium 120 may store data and/or instructions. In some embodiments, machine-readable storage medium 120 may store data and/or instructions used by intelligent nursing cloud platform 100 to perform or use to accomplish the exemplary methods described in this disclosure. In some embodiments, the machine-readable storage medium 120 may include mass storage, removable storage, volatile read-write memory, read-only memory (ROM), and the like, or any combination thereof. Exemplary mass storage devices may include magnetic disks, optical disks, solid state disks, and the like. Exemplary removable memory may include flash drives, floppy disks, optical disks, memory cards, compact disks, magnetic tape, and the like. Exemplary volatile read and write memories can include Random Access Memory (RAM). Exemplary RAM may include Dynamic Random Access Memory (DRAM), double data rate synchronous dynamic random access memory (DDR SDRAM), Static Random Access Memory (SRAM), thyristor random access memory (T-RAM), and zero capacitance random access memory (Z-RAM), among others. Exemplary read-only memories may include mask read-only memory (MROM), programmable read-only memory (PROM), erasable programmable read-only memory (perrom), electrically erasable programmable read-only memory (EEPROM), compact disc read-only memory (CD-ROM), digital versatile disc read-only memory, and the like. In some embodiments, the machine-readable storage medium 120 may be implemented on the intelligent nursery cloud platform 100. By way of example only, the smart nursery cloud platform 100 may include a private cloud, a public cloud, a hybrid cloud, a community cloud, a distributed cloud, an internal cloud, a multi-tiered cloud, and the like, or any combination thereof.

For a specific implementation process of the processor 110, reference may be made to the above-mentioned various method embodiments executed by the intelligent child-care cloud platform 100, which implement the principle and the technical effect similarly, and the detailed description of the embodiment is omitted here.

In addition, the embodiment of the disclosure also provides a readable storage medium, which is preset with computer-executable instructions, and when a processor executes the computer-executable instructions, the method for pushing the intelligent child care knowledge point information is implemented.

It should be understood that the foregoing description is for purposes of illustration only and is not intended to limit the scope of the present disclosure. Many modifications and variations will be apparent to those of ordinary skill in the art in light of the description of the present disclosure. However, such modifications and variations do not depart from the scope of the present disclosure.

While the basic concepts have been described above, it will be apparent to those of ordinary skill in the art in view of this disclosure that the above disclosure is intended to be exemplary only and is not intended to limit the disclosure. Various modifications, improvements and adaptations to the present disclosure may occur to those skilled in the art, although not explicitly described herein. Such alterations, modifications, and improvements are intended to be suggested in this disclosure, and are intended to be within the spirit and scope of the exemplary embodiments of this disclosure.

Also, this disclosure uses specific words to describe embodiments of the disclosure. For example, "one embodiment," "an embodiment," and/or "some embodiments" means that a particular feature, structure, or characteristic described in connection with at least one embodiment of the disclosure is included. Therefore, it is emphasized and should be appreciated that two or more references to "an embodiment" or "one embodiment" or "an alternative embodiment" in various places throughout this specification are not necessarily all referring to the same embodiment. Furthermore, certain features, structures, or characteristics of one or more embodiments of the disclosure may be combined as appropriate.

Further, those of ordinary skill in the art will understand that aspects of the present disclosure may be illustrated and described as embodied in several patentable categories or contexts, including any new and useful combination of processes, machines, articles, or materials, or any new and useful modification thereof. Accordingly, various aspects of the present disclosure may be carried out entirely by hardware, entirely by software (including firmware, resident software, micro-code, etc.), or by a combination of hardware and software. The above hardware or software may be referred to as a "unit", "module", or "system". Furthermore, aspects of the present disclosure may take the form of a computer program product embodied in one or more computer-readable media, with computer-readable program code embodied therein.

A computer readable signal medium may comprise a propagated data signal with computer program code embodied therein, for example, on a baseband or as part of a carrier wave. Such a propagated signal may take any of a variety of forms, including electro-magnetic, optical, and the like, or any suitable combination. A computer readable signal medium may be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. Program code on a computer readable signal medium may be propagated over any suitable medium, including radio, electrical cable, fiber optic cable, RF, or the like, or any combination thereof.

Computer program code required for operation of portions of the present disclosure may be written in any one or more programming languages, including a subject oriented programming language such as Java, Scala, Smalltalk, Eiffel, JADE, Emerald, C + +, C #, VB.NET, Python, and the like, a conventional programming language such as C, Visual Basic, Fortran 2003, Perl, COBOL 2002, PHP, ABAP, a dynamic programming language such as Python, Ruby, and Groovy, or other programming languages, and the like. The program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the latter scenario, the remote computer may be connected to the user's computer through any network format, such as a Local Area Network (LAN) or a Wide Area Network (WAN), or the connection may be made to an external computer (for example, through the Internet), or in a cloud computing environment, or as a service, such as a software as a service (SaaS).

Additionally, the order in which the elements and sequences of the present disclosure are processed, the use of numerical letters, or the use of other names are not intended to limit the order of the processes and methods of the present disclosure, unless explicitly recited in the claims. While various presently contemplated embodiments of the invention have been discussed in the foregoing disclosure by way of example, it is to be understood that such detail is solely for that purpose and that the appended claims are not limited to the disclosed embodiments, but, on the contrary, are intended to cover all modifications and equivalent arrangements that are within the spirit and scope of the disclosed embodiments. For example, although the system components described above may be implemented by hardware devices, they may also be implemented by software-only solutions, such as installing the described system on an existing server or mobile device.

Similarly, it should be noted that in the preceding description of embodiments of the disclosure, various features are sometimes grouped together in a single embodiment, figure, or description thereof for the purpose of streamlining the disclosure aiding in the understanding of one or more of the embodiments. Similarly, it should be noted that in the preceding description of embodiments of the disclosure, various features are sometimes grouped together in a single embodiment, figure, or description thereof for the purpose of streamlining the disclosure aiding in the understanding of one or more of the embodiments.

Claims

1. An intelligent child care knowledge point information pushing method is applied to an intelligent child care cloud platform, the intelligent child care cloud platform is in communication connection with a plurality of intelligent child care service terminals, and the method comprises the following steps:

2. The intelligent child-care knowledge point information pushing method according to claim 1, further comprising a step of determining frequent item description data of the reference frequent question-and-answer item, the step including:

and extracting description components of the reference frequent question and answer items to obtain a description component set corresponding to the reference frequent question and answer items in a child-rearing test hotspot putting scene, and taking the obtained description component set of the reference frequent question and answer items as frequent item description data of the reference frequent question and answer items in the at least one child-rearing session behavior data.

3. The intelligent child-care knowledge point information pushing method according to claim 2, wherein the step of determining interest parameters of the community child-care conversation group and the reference frequent question and answer item in the at least one child-care conversation behavior data based on conversation collaboration data of the community child-care conversation group in the at least one child-care conversation behavior data and frequent item description data of the reference frequent question and answer item in the at least one child-care conversation behavior data to obtain an interest parameter cluster corresponding to the reference frequent question and answer item comprises the steps of:

for each piece of session behavior data in the at least one piece of childbearing session behavior data, determining a frequent question-answer feature as a candidate question-answer feature in the currently traversed child-bearing session behavior data based on a description component set corresponding to frequent question-answer content of the reference frequent question-answer item;

determining candidate childbearing session behavior data matched with a latest session group image tag of the community childbearing session group in the currently traversed childbearing session behavior data based on the candidate question-answer feature, and taking an intersection session behavior feature of the candidate childbearing session behavior data and the latest session group image tag as an image matching behavior feature, wherein the latest session group image tag is obtained based on session collaboration data of the community childbearing session group in the currently traversed childbearing session behavior data in a preset product stage before a current session product stage, and indicates a current session image tag of the community childbearing session group in the currently traversed childbearing session behavior data;

determining interest parameters of the community childbearing session group and the reference frequent question-answer item in the currently traversed childbearing session behavior data based on the candidate question-answer features and the portrait matching behavior features;

and obtaining an interest parameter cluster corresponding to the reference frequent question-answering item based on the interest parameters respectively corresponding to the at least one piece of childbearing session behavior data.

4. The intelligent child-care knowledge point information pushing method according to claim 3, wherein determining interest parameters of the community child-care conversation group and the reference frequent question-answer item in the currently traversed child-care conversation behavior data based on the candidate question-answer features and the portrait matching behavior features comprises:

determining a characteristic interest probability variation trend between the candidate question answering characteristics and the portrait matching behavior characteristics, performing characteristic regularization processing on the characteristic interest probability variation trend according to a preset characteristic regularization template, and taking characteristic regularization data obtained after the characteristic regularization processing as interest parameters of the community nursery conversation group and the reference frequent question answering item, wherein the preset characteristic regularization template is determined based on model weight data of a historical interest evaluation model; or

And respectively mapping the candidate question-answer characteristics and the portrait matching behavior characteristics into corresponding reference frequent question-answer characteristics and target portrait matching behavior characteristics under portrait dimensions of the child bearing conversation group based on model weight data of the historical interest evaluation model, and determining interest parameters of the community child bearing conversation group and the reference frequent question-answer items based on the reference frequent question-answer characteristics and the target portrait matching behavior characteristics.

5. The intelligent child-care knowledge point information pushing method according to claim 2, wherein the step of determining interest parameters of the community child-care conversation group and the reference frequent question and answer item in the at least one child-care conversation behavior data based on conversation collaboration data of the community child-care conversation group in the at least one child-care conversation behavior data and frequent item description data of the reference frequent question and answer item in the at least one child-care conversation behavior data to obtain an interest parameter cluster corresponding to the reference frequent question and answer item comprises the steps of:

sequentially traversing each piece of session behavior data in the at least one piece of childbearing session behavior data, mapping a plurality of frequent question-answer features in a description component set corresponding to frequent question-answer contents of the reference frequent question-answer project to an image dimension of a childbearing session group based on model weight data of a historical interest evaluation model in the currently traversed childbearing session behavior data to obtain a corresponding reference frequent question-answer feature set, and mapping session collaboration data of the community childbearing session group to the image dimension of the childbearing session group to obtain a corresponding session image collaboration feature;

analyzing the item content of the reference frequent question-answering item based on the reference frequent question-answering feature set, and determining the frequent question-answering content of the reference frequent question-answering item in the currently traversed child-rearing conversation behavior data under the portrait dimension of the child-rearing conversation group;

determining interest parameters of the community nursery conversation group and the reference frequent question and answer item based on the frequent question and answer content and the conversation portrait collaborative feature;

and obtaining an interest parameter cluster corresponding to the reference frequent question-answering item based on the interest parameters corresponding to the at least one childbearing session behavior data.

6. The intelligent child-care knowledge point information pushing method according to any one of claims 1 to 5, wherein the determining of the interest knowledge point data of the community child-care session group according to the interest parameter clusters corresponding to the plurality of reference frequent question and answer items, respectively, comprises:

determining a target interest parameter cluster in a plurality of interest parameter clusters;

for any target interest parameter cluster, when the interest probability variation trend between the community nursery conversation group and the reference frequent question-answer item corresponding to the any target interest parameter cluster is determined to be increased according to a preset increase amplitude based on the interest probability of the target number of interest parameters corresponding to the any target interest parameter cluster, judging that the community nursery conversation group has an interest knowledge point of the reference frequent question-answer item corresponding to the any target interest parameter cluster; or

For any target interest parameter cluster, when the interest probability variation trend between the community childbearing session group and the reference frequent question-answer item corresponding to the any target interest parameter cluster is determined to be reduced according to a preset reduction amplitude based on the interest probability of the target number of interest parameters corresponding to the any target interest parameter cluster, it is determined that the community childbearing session group has no interest knowledge point of the reference frequent question-answer item corresponding to the any target interest parameter cluster.

7. The intelligent child-care knowledge point information pushing method according to any one of claims 1 to 5, wherein the determining of the interest knowledge point data of the community child-care session group according to the interest parameter clusters corresponding to the plurality of reference frequent question and answer items, respectively, comprises:

determining interest tracing service node clusters corresponding to the reference frequent question and answer items based on the interest parameter clusters corresponding to the reference frequent question and answer items, wherein each interest tracing service node cluster comprises a plurality of interest tracing service nodes, and each interest tracing service node indicates an interest attention object and an interest operation object of the community nursery conversation group;

and determining the interest knowledge point data of the community nursery conversation group based on the interest tracing service node cluster corresponding to the plurality of reference frequent question and answer items.

8. The method for pushing intelligent knowledge point information for infant care according to claim 7, wherein the determining a plurality of interest tracing service node clusters corresponding to the reference frequent question and answer items based on the plurality of interest parameter clusters corresponding to the reference frequent question and answer items comprises:

performing interest label binding on interest parameter clusters corresponding to the reference frequent question and answer items to obtain interest tracing service node clusters corresponding to the reference frequent question and answer items;

the determining the interest knowledge point data of the community nursery conversation group based on the interest tracing service node cluster corresponding to the plurality of reference frequent question and answer items comprises:

determining a plurality of interest tracing service node clusters as target interest tracing service node clusters in the interest tracing service node clusters corresponding to the reference frequent question-answering items;

for any target interest tracing service node cluster in a plurality of target interest tracing service node clusters, when a target number of interest tracing service nodes in the target interest tracing service node cluster indicate that interest attention objects of the community nursery session group are inconsistent and the service operation duration of any interest tracing service node in the target number of interest tracing service nodes is less than a first preset duration, determining that the community nursery session group does not have the service operation interest of a matched reference frequent question and answer item matched with the interest attention object;

for any target interest tracing service node cluster in the target interest tracing service node clusters, when a target number of interest tracing service nodes contained in the target interest tracing service node cluster indicate that interest attention objects of the community nursery session group are consistent, and the service operation duration of the target number of interest tracing service nodes is longer than a second preset duration, determining that the community nursery session group has the service operation interest of a matched reference frequent question and answer item matched with the interest attention objects;

collecting the interest knowledge points corresponding to the determined business operation interests of the community nursery conversation group as the interest knowledge point data of the community nursery conversation group;

wherein, the step of obtaining the application page push data of the related child bearing knowledge points matched with the interest knowledge point data from the pre-subscribed child bearing knowledge point data source according to the interest knowledge point data and recommending the page to the community child bearing session group comprises the following steps:

acquiring target reference application page push data matched with the interest knowledge point data, past content feedback data corresponding to the target reference application page push data and page function data to be online corresponding to the target reference application page push data from a pre-subscribed child-care knowledge point data source, wherein the page function data to be online is determined based on push state data of related online services of the interest knowledge point data in the target reference application page push data;

calling a preset AI model, and acquiring priority probability distribution of page recommendation behaviors corresponding to the target reference application page push data based on the past content feedback data and the page function data to be online, wherein the priority probability distribution of the page recommendation behaviors is used for expressing page recommendation tags of all the page recommendation behaviors in the target reference application page push data, and the page recommendation tag of any page recommendation behavior is used for expressing the probability distribution that any page recommendation behavior is matched with each page plate of the current reference application page;

based on the priority probability distribution of the page recommendation behavior, page plate data is quoted to the interest knowledge point data in the target reference application page push data, and quote page plate data of the interest knowledge point data in the target reference application page push data is obtained;

and carrying out page recommendation to the community nursery conversation group based on the reference page plate data of the interest knowledge point data in the target reference application page push data.

9. An intelligent child-care knowledge point information pushing system is characterized by comprising an intelligent child-care cloud platform and a plurality of intelligent child-care service terminals in communication connection with the intelligent child-care cloud platform;

the intelligent child-rearing cloud platform is used for:

10. An intelligent nursing cloud platform, comprising a processor and a machine-readable storage medium, wherein the machine-readable storage medium stores at least one instruction, at least one program, a code set, or a set of instructions, and the at least one instruction, the at least one program, the code set, or the set of instructions is loaded and executed by the processor to realize the intelligent nursing knowledge point information pushing method according to any one of claims 1 to 8.