Information pushing method and device, electronic equipment and storage medium

Abstract

The invention discloses an information pushing method and device, electronic equipment and a storage medium. The method comprises the following steps: acquiring an information pushing parameter; according to the information pushing parameters, a first feature attribute set is determined, feature attributes of the target object contained in the first feature attribute set are used for reflecting identification information of the target object, and the target object authorizes information used for representing the health condition; under the constraint of a to-be-pushed information theme indicated by the information pushing parameter, for each feature attribute in the first feature attribute set, determining a scene tag corresponding to the feature attribute according to a first type tag and a second type tag which are screened out from a preset tag library and have the matching degree with the feature attribute meeting a preset matching condition; and generating to-be-pushed information according to the scene label corresponding to each feature attribute, and pushing the to-be-pushed information to the target object corresponding to each feature attribute. According to the invention, the accuracy and adaptability of information pushing of the target object can be improved.

Description

Technical Field

[0001] This invention relates to the field of data processing technology, and in particular to an information push method, apparatus, electronic device, and storage medium. Background Technology

[0002] With the accelerating aging of society and the continuous increase in the proportion of retired employees, the health management of this group presents new characteristics and challenges. Some retirees lack access to information and generally lack professional knowledge of personal health management, making it difficult for them to form a clear and accurate understanding of their own health status, which can easily lead to various health risks.

[0003] The existing health management model for retirees in enterprises is mostly a uniform approach, which fails to combine the individual characteristics of each retiree with the common health needs of retiree groups with similar situations to carry out accurate matching and delivery of health information, and thus cannot meet the different health management needs of retirees and the need for accurate delivery of health information. Summary of the Invention

[0004] This invention provides an information push method, device, electronic device, and storage medium to solve the problems of insufficient accuracy and adaptability of information push to target objects.

[0005] According to one aspect of the present invention, an information push method is provided, comprising: Obtain information push parameters. Information push parameters include at least the topic of the information to be pushed, the target push range, and the expected accuracy of the information push. The target push range is used to indicate the set of target objects that the carrier of the information to be pushed can reach. Based on the information push parameters, a first set of feature attributes is determined. The first set of feature attributes contains the feature attributes of all target objects within the target push range indicated by the information push parameters. The feature attributes of the target objects are used to reflect the identification information of the target objects and the information authorized by the target objects to characterize their health status. Under the constraint of the topic of the information to be pushed as indicated by the information push parameters, for each feature attribute in the first feature attribute set, the scene tag corresponding to the feature attribute is determined according to the first type tag and the second type tag selected from the preset tag library that meet the preset matching conditions for the feature attribute matching degree; wherein, the preset tag library includes the first type tag and the second type tag; the first type tag is used to identify the first feature, and the first feature is used to represent the feature information under different information dimensions in different information domains; the second type tag is used to identify the first feature set that matches the target object group, and the target object group is used to indicate the feature attribute set that has at least one common feature in the first feature attribute set, and the second type tag is associated with the common feature of the corresponding target object group; the scene tag corresponding to each feature attribute is used to identify the first feature set consisting of the first type tag and the second type tag under the constraint of the topic of the information to be pushed as indicated by the information push parameters; The information to be pushed is generated based on the scene label corresponding to each feature attribute, and then pushed to the target object corresponding to each feature attribute.

[0006] According to another aspect of the present invention, an information push device is provided, comprising: The information push parameter acquisition module is used to acquire information push parameters. The information push parameters include at least the topic of the information to be pushed, the target push range, and the expected accuracy of the information push. The target push range is used to indicate the set of target objects that the carrier carrying the information to be pushed can reach. The feature attribute set determination module is used to determine a first feature attribute set based on the information push parameters. The first feature attribute set contains feature attributes of all target objects within the target push range indicated by the information push parameters. The feature attributes of the target objects are used to reflect the identification information of the target objects and the information authorized by the target objects to characterize their health status. The scene tag determination module is used, under the constraint of the topic of the information to be pushed as indicated by the information push parameters, to determine the scene tag corresponding to each feature attribute in the first feature attribute set, based on first type tags and second type tags selected from a preset tag library that meet preset matching conditions for the feature attribute; wherein, the preset tag library includes first type tags and second type tags; the first type tag is used to identify a first feature, which is used to represent feature information under different information dimensions in different information domains; the second type tag is used to identify a first feature set that matches a target object group, which is used to indicate a feature attribute set in the first feature attribute set that has at least one common feature, and the second type tag is associated with the common feature of the target object group; the scene tag corresponding to each feature attribute is used to identify the first feature set consisting of the first type tags and the second type tags corresponding to each feature attribute under the constraint of the topic of the information to be pushed as indicated by the information push parameters. The information push module is used to generate push information based on the scene tag corresponding to each feature attribute, and push the push information to the target object corresponding to each feature attribute.

[0007] According to another aspect of the present invention, an electronic device is provided, the electronic device comprising: At least one processor; and A memory communicatively connected to the at least one processor; wherein, The memory stores a computer program that can be executed by the at least one processor, which is then executed by the at least one processor to enable the at least one processor to perform the information push method according to any embodiment of the present invention.

[0008] According to another aspect of the present invention, a computer-readable storage medium is provided, the computer-readable storage medium storing computer instructions, the computer instructions being configured to cause a processor to execute and implement the information push method described in any embodiment of the present invention.

[0009] According to another aspect of this application, a computer program product is provided, which includes a computer program that, when executed by a processor, implements the information push method described in any embodiment of this application.

[0010] The technical solution of this invention, by acquiring information push parameters, can clarify the push direction and scope for subsequent information pushes; extract the identification information and authorized health status information of all target objects within the target push scope indicated by the information push parameters to construct a first feature attribute set, providing data support for differentiated and precise information push; under the constraint of the information push parameters, according to the first type of tags and the second type of tags that match each feature attribute obtained from the preset tag library, a scene tag is determined for each feature attribute. The scene tag can represent both the feature information matching the target object and the group feature information matching the target object group with common features, thereby ensuring that the scene tag corresponding to each feature attribute can comprehensively cover all kinds of feature information related to that feature attribute; generate push information that fits the feature attributes and needs of the target object according to the scene tag, and complete the information push, ensuring the targeting and adaptability of the information push. Based on the above technical solution, it is possible to generate suitable push information content for the target object according to the information push parameters, target object feature attributes and preset tag library, and push it to the corresponding target object. This can improve the accuracy and adaptability of information push to the target object, and thus enable the precision of information push in the scenario of health management for retired employees in enterprises, thereby improving the professionalism and humanistic care of enterprise health management services.

[0011] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of the present invention, nor is it intended to limit the scope of the invention. Other features of the invention will become readily apparent from the following description. Attached Figure Description

[0012] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0013] Figure 1 This is a flowchart of an information push method provided according to an embodiment of the present invention; Figure 2 This is a schematic diagram of the structure of an information push device according to an embodiment of the present invention; Figure 3 This is a schematic diagram of the structure of an electronic device that implements the information push method of this invention. Detailed Implementation

[0014] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0015] It should be noted that the terms "candidate," "target," etc., used in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0016] Figure 1 This is a flowchart illustrating an information push method provided in an embodiment of the present invention. This embodiment is applicable to situations where information is pushed to a target object. The method can be executed by an information push device, which can be implemented in hardware and / or software. This information push device can be configured in any electronic device with network communication capabilities. Figure 1 As shown, the information push method provided in this embodiment of the invention may include: S110. Obtain information push parameters. The information push parameters include at least the topic of the information to be pushed, the target push range, and the expected accuracy of the information push. The target push range is used to indicate the set of target objects that the carrier carrying the information to be pushed can reach.

[0017] Information push parameters can indicate the targeted needs of information push and the expected effect of information push accuracy.

[0018] The subject of the information to be pushed can indicate the scope of content to be covered by the information to be pushed, and can be used to reflect the application scenario of the information push task. For example, the scope of content to be covered by the information to be pushed indicated by the subject of the information to be pushed can refer to content subjects related to the health management needs of retired employees of enterprises, such as daily health management, physical examination reminders, and convalescent service guidance. Each subject of the information to be pushed can reflect the application scenario of the corresponding information push task. For example, if the subject of the information to be pushed is a physical examination reminder, the corresponding information push task is used to push information related to regular physical examinations to retired employees of enterprises; if the subject of the information to be pushed is a convalescent service guidance, the corresponding information push task is used to push information related to convalescent services to retired employees of enterprises.

[0019] The target push scope clearly defines the set of individuals to whom the information is to be pushed. Optionally, the target push scope can be determined based on the subject of the information to be pushed. For example, if the subject of the information to be pushed is "care service guidance," then the target push scope can be set to retired employees within the company who have a history of illness; if the subject of the information to be pushed is "routine health management," then the target push scope can be set to all retired employees within the company.

[0020] The expected accuracy of information push can refer to the degree to which the information push can accurately reach the recipient and the recipient's satisfaction with the push information meets the preset satisfaction requirements.

[0021] S120. Based on the information push parameters, determine the first set of feature attributes. The first set of feature attributes contains the feature attributes of all target objects within the target push range indicated by the information push parameters. The feature attributes of the target objects are used to reflect the identification information of the target objects and the information authorized by the target objects to characterize their health status.

[0022] The first set of characteristic attributes can refer to the set of characteristic attributes of all target objects for which the information to be pushed is determined based on the target push range in the information push parameters. In this embodiment, the target object can refer to the person for whom the information is to be pushed among all retired employees of the enterprise, and the target object has agreed to provide and authorize the use of its own identification information and information used to characterize its own health status.

[0023] The characteristic attributes of the target object are used to reflect the target object's identification information and the information authorized by the target object to characterize its health status, and can serve as a basis for distinguishing different target objects. In this embodiment, the characteristic attributes of the target object can be determined based on the information voluntarily filled in by retired employees of the enterprise and historical push records; wherein, the identification information of the target object includes at least the relevant information in the information voluntarily filled in by retired employees of the enterprise that can ensure that the target object can be uniquely identified, and the identification information of the target object may also include other information related to the identification of the target object, such as gender information, educational background, department, etc.; the information authorized by the target object to characterize its health status may refer to the information voluntarily filled in by retired employees of the enterprise or the information in historical push records that can characterize the target object's health status, and the information authorized by the target object to characterize its health status may also refer to health examination records that the target object agrees to provide and allows to be used within a preset scope.

[0024] By determining the first set of characteristic attributes, we can clearly identify the target object's identification information and authorized health information within the target push range, providing accurate data support for subsequent differentiated information push to target objects with different health conditions.

[0025] As an optional but not limited implementation, the characteristic attributes of the target object are generated in the following way: Acquire first information about multiple target objects, including information reflecting the identification of the target objects and information authorized by the target objects to characterize their health status; Based on the initial information of each target object, construct the characteristic attributes of each target object.

[0026] The first information can refer to a set of information used to construct the characteristic attributes of the target object, including second information that reflects the identification of the target object and third information that can be used to characterize the health status of the target object after authorization by the target object. The second information includes at least one type of information that can ensure the target object can be uniquely identified. For example, the second information may include identification-related information such as the target object's name, affiliated unit, contact information, and information receiving preferences, while the third information may include daily health status, records of participation in rehabilitation services, past medical history, and medication status. In this embodiment, the second and third information may include information about retired employees during their employment and retirement periods. The second and third information can be obtained from information voluntarily filled in by retired employees, historical push records, or relevant data that retired employees agree to provide and authorize for use within a preset scope, and a data source identifier is added to the obtained information. The specific forms of the second and third information may include numbers, text, images, audio and video, etc., and this embodiment does not impose any limitations.

[0027] Optionally, after obtaining the second and third information of each target object, the second and third information are checked for completeness to determine whether they contain preset identification information fields and preset health information fields. These preset identification information fields and preset health information fields are information fields required for constructing feature attributes. If the second and third information of the target object is missing preset identification information fields and / or preset health information fields, the missing fields are filled manually. For different representations of the second and third information, a preset parsing method is used to convert the second and third information into a preset unified data format, and the content of each data field in the second and third information is semantically normalized to ensure that information with the same semantics can be mapped to the same field content identifier.

[0028] Optionally, if information from different data sources for the same field differs in content, a weighted summation method is used to fuse the information from different data sources to obtain the final information field content. For example, if the content corresponding to any field in the information voluntarily submitted by the target object differs from the content corresponding to the same field in historical push records, a weighted fusion is performed on the content corresponding to any field in the obtained information voluntarily submitted by the target object and the content corresponding to the same field in historical push records, based on a preset weight configuration of the voluntarily submitted information and historical push records, to obtain the final information field content.

[0029] The characteristic attributes of a target object can refer to the attribute information that reflects the identity characteristics and authorized health status characteristics of the target object, obtained by feature extraction and processing based on the first information of the target object, and can be used as a basis for distinguishing different target objects.

[0030] By constructing feature attributes for each target object using the first information, not only can the feature attributes of the constructed target objects uniquely identify the corresponding target objects, but the feature attributes of the target objects can also reflect various identification information and health status information of the target objects. The feature attributes of the target objects can be used to distinguish different target objects, and can also be used to analyze the correlation between multiple target objects.

[0031] As an optional but not limited implementation, based on the first information of each target object, the characteristic attributes of each target object are constructed, including: Extract multi-dimensional feature information of each target object from its first information according to preset feature extraction rules; A feature information matrix is ​​established based on the multi-dimensional feature information of each target object. In the feature information matrix, the rows represent the multi-dimensional feature information of a single target object, and the columns represent the different dimensions of the multi-dimensional feature information. Based on the information push parameters and preset feature weight configuration, set the weight values ​​of each feature dimension in the feature information matrix; Based on the feature information matrix and the weight values ​​of each feature information dimension in the feature information matrix, the feature attributes of each target object are constructed.

[0032] The preset feature extraction rules include at least several pre-defined feature dimensions to be selected and extracted from the first information of the target object, as well as the extraction method for the feature values ​​of each dimension. Optionally, the multiple feature dimensions can be determined based on multiple semantic categories obtained by classifying the semantic attributes of each field in the first information of the target object; the extraction method for the feature values ​​of each dimension can refer to standardizing the field content corresponding to each feature dimension in the first information and mapping it to a unified numerical space to obtain the feature values ​​of each dimension.

[0033] Multi-dimensional feature information refers to feature information extracted from the primary information of a target object that covers multiple dimensions of the target object's identity and health status. For example, multi-dimensional feature information may include information on the target object's identity feature dimension, gender feature dimension, and health status dimension. For instance, the identity feature dimension might refer to whether the target object is a cadre, a general staff member, or a contracted employee, while the education feature dimension might refer to high school, undergraduate, postgraduate, or doctoral degrees. Information in the gender characteristic dimension can refer to male or female, while information in the health status dimension can refer to good, sub-healthy, or sick.

[0034] A feature information matrix can refer to a collection that structures the multi-dimensional feature information of each target object in matrix form. Each row of the matrix corresponds to all the multi-dimensional feature information of a single target object, and each column corresponds to the specific dimension category of the multi-dimensional feature information.

[0035] The preset feature weight configuration is a configuration standard used to indicate the importance of different feature information dimensions when constructing the feature attributes of a target object. The preset feature weight configuration includes at least one set of default feature weight recombinations, and may also include multiple sets of feature weight recombinations, each of which is associated with different information push parameters to indicate the selection of the appropriate feature weight recombination under the corresponding information push parameter conditions.

[0036] Based on the information push parameters, a suitable feature weight recombination is selected from the preset feature weight configuration. If no suitable feature weight recombination exists in the preset feature weight configuration, the default feature weight recombination is used. Based on the selected feature weight recombination, corresponding weight values ​​are set for each feature information dimension in the feature information matrix to highlight the different contributions of different feature information to the construction of the target object's feature attributes. Based on the feature information in each row of the feature information matrix and the weight values ​​of each feature information dimension in the feature information matrix, the feature attributes of each target object are constructed.

[0037] By extracting multi-dimensional feature information according to preset feature extraction rules and constructing a feature information matrix, the systematic and structured nature of the feature information can be ensured, and feature omissions can be avoided. By setting the weight values ​​of each feature dimension according to the information push requirements, features that are highly related to the topic of the information to be pushed and the target push scope can be highlighted, thereby ensuring that the feature attributes of the constructed target object can highlight the feature information related to the application scenario indicated by the topic of the information to be pushed, so as to improve the adaptability of the pushed information content to the target object.

[0038] S130. Under the constraint of the topic of the information to be pushed as indicated by the information push parameters, for each feature attribute in the first feature attribute set, the scene tag corresponding to the feature attribute is determined according to the first type tag and the second type tag selected from the preset tag library that meet the preset matching conditions for the feature attribute matching degree; wherein, the preset tag library includes the first type tag and the second type tag; the first type tag is used to identify the first feature, and the first feature is used to represent the feature information under different information dimensions in different information domains; the second type tag is used to identify the first feature set that matches the target object group, and the target object group is used to indicate the feature attribute set that has at least one common feature in the first feature attribute set, and the second type tag is associated with the common feature of the corresponding target object group; the scene tag corresponding to each feature attribute is used to identify the first feature set composed of the first type tag and the second type tag under the constraint of the topic of the information to be pushed as indicated by the information push parameters.

[0039] Preset matching conditions refer to pre-defined conditions used to determine whether there is a match between the first type of tag, the second type of tag, and the feature attribute. Scene tags refer to tags determined by integrating the first type of tag and the second type of tag that match the feature attribute under the constraint of the topic of the information to be pushed. Scene tags can identify the set of first features that are associated with the corresponding feature attribute under the push request indicated by the topic of the information to be pushed.

[0040] Common features can refer to the feature information shared by all target objects in the target object set. The target object set can refer to the set of multiple target objects corresponding to the feature attributes of multiple target objects that possess at least one common feature in the first feature attribute set, such as the set of multiple target objects whose health status is healthy, or the set of multiple target objects that are over 65 years old and male, etc.

[0041] By matching each feature attribute with a corresponding scene tag, the feature attributes of the target object can be accurately associated with the tags in the preset tag library and the push requirements indicated by the topic of the information to be pushed, thereby ensuring that the generated scene tags can provide a basis for generating appropriate push information for the target object.

[0042] As an optional but not limited implementation, under the constraint of the topic of the information to be pushed as indicated by the information push parameters, for each feature attribute in the first feature attribute set, the scene tag corresponding to the feature attribute is determined according to the first type of tags and the second type of tags selected from the preset tag library that meet the preset matching conditions, including: Based on the degree of matching between each feature attribute in the first feature attribute set and the common features of the corresponding target object groups associated with each second type tag in the preset tag library, the second type tag corresponding to each feature attribute in the first feature attribute set is determined; Based on the matching degree between each first type tag in the preset tag library and the information push parameters, multiple third type tags are obtained; the third type tags are the first type tags in the preset tag library whose matching degree with the information push parameters is not lower than a preset threshold. Based on the degree of matching between each feature attribute in the first feature attribute set and each third type label in the multiple third type labels, multiple fourth type labels corresponding to each feature attribute in the first feature attribute set are determined; the fourth type label is the third type label among the multiple third type labels whose degree of matching with the feature attribute is not lower than a preset threshold. The scene label corresponding to each feature attribute is determined based on the multiple fourth-type labels corresponding to each feature attribute and the second-type labels corresponding to each feature attribute.

[0043] The common characteristics of a target group refer to the shared feature information of all target objects within that group. Based on each feature attribute in the first feature attribute set, a matching degree analysis is performed between it and the common characteristics of the target group associated with each second-type tag in the preset tag library. By judging the degree of matching, second-type tags that meet the matching requirements are selected from the preset tag library as the appropriate tags for the corresponding feature attributes. By selecting second-type tags based on the matching degree of common features, it is possible to accurately identify second-type tags that match the target group to which each feature attribute belongs. This provides a foundation for constructing scene tags that aligns with group characteristics, improving the accuracy of group adaptation for scene tags.

[0044] The third type of tag can refer to tags selected from the first type of tags in a preset tag library whose matching degree with the information push parameters is not lower than a preset threshold. In other words, the third type of tag is a first type of tag that is compatible with the information push topic. Optionally, the matching degree between the first type of tag and the information push parameters can be obtained by calculating the similarity between the feature information identified by the first type of tag and the feature information extracted from the topic of the information to be pushed indicated by the information push parameters. By selecting third type of tags that highly match the information push parameters, it is possible to quickly determine tag resources in the preset tag library that match the information push needs represented by the topic of the information to be pushed, and eliminate tags that do not match or have a low degree of matching to reduce redundant calculations in subsequent tag matching. This improves tag matching efficiency and ensures the adaptability of the third type of tag to the information push parameter indication.

[0045] The fourth type of label can refer to a label selected from the third type of label set whose matching degree with any feature attribute in the first feature attribute set is not less than a preset threshold. The fourth type of label is a label that matches the individual feature information of the target object represented by a single feature attribute. Optionally, the matching degree between the feature attribute and the third type of label can be obtained by calculating the similarity between the feature information represented by the feature attribute and the feature information identified by the third type of label. Based on the multiple third type of labels obtained by the aforementioned selection, for each feature attribute in the first feature attribute set, the matching degree with each third type of label is calculated one by one, and the third type of label with the matching degree meeting the preset threshold is selected as the fourth type of label, which can improve the adaptability of the label to the individual features of the target object.

[0046] By integrating the second type of tags that align with the commonalities of the group with the fourth type of tags that align with individual characteristics, a scenario tag is formed that combines group adaptability, individual targeting, and push demand adaptability. This provides a basis for generating accurately adapted push information in the future, thereby improving the accuracy and adaptability of information push.

[0047] As an optional but not limited implementation, the default tag library is generated in the following way: Based on the first preset information, multiple types of information to be pushed are determined. The first preset information is used to characterize the requirements of multiple target objects for pushed information, and the multiple types of information to be pushed are used to indicate multiple fields of information to be pushed. Based on multiple types of information to be pushed, a set of data dictionaries is constructed. The set of data dictionaries contains multiple data dictionaries. Each data dictionary is used to describe the information domain indicated by any type of information to be pushed. Each data element in each data dictionary is used to describe the feature information of any information dimension within the corresponding information domain. Based on the data elements contained in each data dictionary, generate the first type of tag in the preset tag library; Based on the first type of tags in the preset tag library and the characteristic attributes of multiple target objects, generate the second type of tags in the preset tag library.

[0048] The first preset information represents the health management directions or health service needs of multiple target objects. By analyzing or decomposing the first preset information, the areas of push information that multiple target objects expect to receive can be determined, that is, multiple types of information to be pushed can be determined. Based on the multiple types of information to be pushed, a data dictionary set is constructed by pre-setting multiple information contents under each type of information to be pushed. The data dictionary set contains multiple data dictionaries, each data dictionary corresponds to a type of information to be pushed, and each data dictionary contains multiple data elements. Each data element is determined according to the pre-set information contents under the type of information to be pushed corresponding to its data dictionary.

[0049] For example, the multiple types of information to be pushed included in the first preset information can indicate information related to the target object's information domain, information related to health status, information related to recuperation services, and information related to commonly used medicines that multiple target objects are interested in. Among them, information related to the target object's information domain can refer to the target object's age, gender, department, information receiving preferences, etc.; information related to health status can refer to knowledge related to chronic diseases, knowledge related to physical examinations, etc.; information related to recuperation services can refer to information related to recuperation service types, information related to recuperation service participation status, etc.; and information related to commonly used medicines can refer to information related to drug categories, information related to medication management attributes, information related to drug risk warnings, etc. Based on the multiple information types to be pushed contained in the first preset information, a data dictionary set is constructed. This data dictionary set includes a target object data element dictionary, a health data element dictionary, a convalescent data element dictionary, and a drug classification dictionary. The target object data element dictionary describes information related to the target object's information domain. Each data element in the target object data element dictionary can refer to feature information of any information dimension within the target object's information domain. For example, the target object's age, gender, department, and information receiving preferences can be used as data elements in the target object data element dictionary. The health data element dictionary describes information related to the health status domain. Each data element in the health data element dictionary can refer to any information dimension within the health status domain. The data elements in the health data element dictionary include: characteristic information such as hypertension knowledge and physical examination guidelines; and convalescent data element dictionary, which describes information related to the convalescent service field. Each data element in the convalescent data element dictionary can refer to characteristic information of any information dimension in the convalescent service field, such as content of the first type of convalescent service and participation status identification information of the first type of convalescent service. The drug classification dictionary describes information related to the field of commonly used drugs. Each data element in the drug classification dictionary can refer to characteristic information of any information dimension in the field of commonly used drugs, such as risk warnings for commonly used drugs and precautions for the first type of drugs.

[0050] Based on the data elements contained in each data dictionary, a first-type label in a preset label library is generated. The first-type labels in the preset label library correspond one-to-one with the data elements in the data dictionary set, and each data element provides a naming source for its corresponding first-type label. Based on the first-type labels in the preset label library and the feature attributes of multiple target objects, multiple first-type labels that match the common features of multiple target objects are extracted, generating a second-type label in the preset label library.

[0051] By determining the type of information to be pushed based on the first preset information, it is possible to ensure that the preset tag library meets the needs of multiple target objects for pushed information, thereby improving the accuracy of the pushed information content. According to multiple types of information to be pushed, a data dictionary set is constructed, and a first type of tag is generated based on the data elements in the data dictionary set, which enables the first type of tag to identify clear feature information. According to the first type of tag in the preset tag library and the feature attributes of multiple target objects, a second type of tag in the preset tag library is generated, which enables the preset tag library to contain both the first type of tag that meets the needs of multiple target objects and can identify different feature information, and the second type of tag that can identify the feature information corresponding to the group composed of multiple target objects. Thus, the preset tag library can provide comprehensive and high-quality data support for accurate information push, thereby improving the accuracy and feasibility of information push.

[0052] As an optional but not limited implementation, a second type of tag is generated from the preset tag library based on the first type of tags in the preset tag library and the characteristic attributes of multiple target objects, including: According to the preset grouping rules, the feature attributes of multiple target objects are grouped to obtain multiple sets of second feature attributes and common features associated with each set of second feature attributes. Each feature profile in the set of second feature attributes has at least one common feature. The common feature associated with each set of second feature attributes refers to the feature information shared by each feature attribute in each set of second feature attributes. The common features associated with each set of second feature attributes are combined with multiple first-type tags in the preset tag library whose matching degree is not less than a preset threshold to obtain the second-type tags in the preset tag library.

[0053] Preset grouping rules refer to pre-defined rules for classifying and aggregating the feature attributes of multiple target objects, and can be used to clarify the basis for grouping target objects. Preset grouping rules can be determined based on the dimension of common feature information among the feature attributes of multiple target objects. For example, preset grouping rules can refer to rules that classify and aggregate the feature attributes of multiple target objects according to different age ranges based on the age feature dimension; preset grouping rules can also refer to rules that classify and aggregate the feature attributes of multiple target objects according to different health status identifiers based on the health status feature dimension; preset grouping rules can refer to rules that classify and aggregate the feature attributes of multiple target objects jointly determined by different age ranges based on the age feature dimension and different health status identifiers based on the health status feature dimension.

[0054] The second feature attribute set can refer to the feature attribute set obtained after grouping the feature attributes of multiple target objects according to a preset grouping rule. Each second feature attribute set contains at least one common feature among the feature attributes of the multiple target objects. The common feature can refer to the feature information shared by all feature attributes in each second feature attribute set, that is, the feature information corresponding to the common feature dimension used when classifying and aggregating the feature attributes of multiple target objects. For example, the common feature is that the age characteristic represented by the feature attributes of multiple target objects is the same, meaning that the ages of the multiple target objects belong to the same age range.

[0055] In this embodiment, the similarity between the common features associated with the second set of feature attributes and the feature information identified by the first type of tag is calculated. When the calculated similarity is greater than a preset similarity threshold, it is determined that the feature information identified by the first type of tag matches the common features associated with the second set of feature attributes. The proportion of target objects included in the second set of feature attributes among all target objects indicated by the push information parameters is calculated, and this proportion is used as the degree of matching between the common features associated with the second set of feature attributes and the first type of tag. Multiple first type tags in the preset tag library whose degree of matching with the common features associated with the second set of feature attributes is not less than a preset threshold are combined to obtain the second type of tag in the preset tag library.

[0056] By dividing feature attribute groups according to preset group division rules, the rationality and relevance of the second feature attribute set can be ensured, and the target object group with common features can be accurately aggregated. Based on the degree of matching between common features and first type tags, multiple first type tags are selected from the preset tag library to generate second type tags. This allows the second type tags to represent the common needs of the corresponding target object group, thereby improving the group relevance and accuracy of information push.

[0057] S140. Generate push information based on the scene label corresponding to each feature attribute, and push the push information to the target object corresponding to each feature attribute.

[0058] The information to be pushed can refer to health management-related information generated based on the scene tags corresponding to the characteristic attributes of each target object, and is intended to be pushed to the target object. For example, the information to be pushed could refer to daily dietary precautions for hypertensive patients, reminders for diabetes medication, annual physical examination appointment notices, or introductions to rehabilitation and convalescent service institutions. For example, for the scene tag "65 years and older - hypertensive patients - long-term medication - daily medication reminders", the information to be pushed could be "Please pay attention to taking your antihypertensive medication on time every day, avoid arbitrarily increasing or decreasing the dosage, and monitor and record your blood pressure regularly."

[0059] The generated push notification is delivered to the target object corresponding to the scene tag. For example, the push notification can be delivered to the target object through authorized contact information, service terminals, or other channels. Alternatively, the push notification can be delivered to the target object using a corresponding information receiving method based on the target object's information receiving preferences.

[0060] By generating and pushing information based on scene tags, it is possible to ensure that the pushed information is highly matched with the characteristics and attributes of the target audience and the health management scenario. This enables precise and tailored health management information to the target audience, such as pushing targeted prevention and control knowledge to people with chronic diseases and physical examination reminders to the elderly. This can improve the target audience's attention to and acceptance of the pushed information.

[0061] Optionally, the feedback information of each target object after receiving the push information is analyzed to determine the target object's satisfaction level with the push information. When the satisfaction level is lower than the preset satisfaction level threshold, the preset threshold for matching the target object with each tag in the preset tag library is adjusted to improve the accuracy of the push information.

[0062] The technical solution of this invention, by acquiring information push parameters, can clarify the push direction and scope for subsequent information pushes; extract the identification information and authorized health status information of all target objects within the target push scope indicated by the information push parameters to construct a first feature attribute set, providing data support for differentiated and precise information push; under the constraint of the information push parameters, according to the first type of tags and the second type of tags that match each feature attribute obtained from the preset tag library, a scene tag is determined for each feature attribute. The scene tag can represent both the feature information matching the target object and the group feature information matching the target object group with common features, thereby ensuring that the scene tag corresponding to each feature attribute can comprehensively cover all kinds of feature information related to that feature attribute; generate push information that fits the feature attributes and needs of the target object according to the scene tag, and complete the information push, ensuring the targeting and adaptability of the information push. Based on the above technical solution, it is possible to generate suitable push information content for the target object according to the information push parameters, target object feature attributes and preset tag library, and push it to the corresponding target object. This can improve the accuracy and adaptability of information push to the target object, and thus enable the precision of information push in the scenario of health management for retired employees in enterprises, thereby improving the professionalism and humanistic care of enterprise health management services.

[0063] Figure 2 This is a schematic diagram of the structure of an information push device provided in an embodiment of the present invention. Figure 2 As shown, the information push device provided in this embodiment of the invention may include: The information push parameter acquisition module 210 is used to acquire information push parameters. The information push parameters include at least the topic of the information to be pushed, the target push range, and the expected information push accuracy. The target push range is used to indicate the set of target objects that the carrier carrying the information to be pushed can reach. The feature attribute set determination module 220 is used to determine a first feature attribute set according to the information push parameters. The first feature attribute set contains the feature attributes of all target objects within the target push range indicated by the information push parameters. The feature attributes of the target objects are used to reflect the identification information of the target objects and the information authorized by the target objects to characterize their health status. The scene tag determination module 230 is used, under the constraint of the topic of the information to be pushed as indicated by the information push parameters, to determine the scene tag corresponding to each feature attribute in the first feature attribute set, based on a first type tag and a second type tag selected from a preset tag library that meet preset matching conditions for the feature attribute; wherein, the preset tag library includes a first type tag and a second type tag; the first type tag is used to identify a first feature, which is used to characterize feature information under different information dimensions in different information domains; the second type tag is used to identify a first feature set that matches a target object group, which is used to indicate a feature attribute set in the first feature attribute set that has at least one common feature, and the second type tag is associated with the common feature of the target object group; the scene tag corresponding to each feature attribute is used to identify the first feature set consisting of the first type tag and the second type tag corresponding to each feature attribute under the constraint of the topic of the information to be pushed as indicated by the information push parameters. The information push module 240 is used to generate push information based on the scene tag corresponding to each feature attribute, and push the push information to the target object corresponding to each feature attribute.

[0064] Based on the above embodiments, optionally, the scene label determination module is specifically used for: Based on the degree of matching between each feature attribute in the first feature attribute set and the common features of the corresponding target object groups associated with each second type tag in the preset tag library, the second type tag corresponding to each feature attribute in the first feature attribute set is determined; Based on the degree of matching between each first type tag in the preset tag library and the information push parameters, multiple third type tags are obtained; the third type tags are first type tags in the preset tag library whose degree of matching with the information push parameters is not lower than a preset threshold. Based on the degree of matching between each feature attribute in the first feature attribute set and each third type label in the plurality of third type labels, a plurality of fourth type labels corresponding to each feature attribute in the first feature attribute set are determined; the fourth type label is a third type label among the plurality of third type labels whose degree of matching with the feature attribute is not lower than a preset threshold; The scene label corresponding to each feature attribute is determined based on the multiple fourth-type labels corresponding to each feature attribute and the second-type labels corresponding to each feature attribute.

[0065] Based on the above embodiments, optionally, the feature attributes of the target object are generated in the following manner: Acquire first information about multiple target objects, the first information including information reflecting the identification of the target objects and information authorized by the target objects to characterize their health status; Based on the first information of each target object, the feature attributes of each target object are constructed.

[0066] Based on the above embodiments, optionally, feature attributes of each target object are constructed according to the first information of each target object, including: Extract multi-dimensional feature information of each target object from the first information of each target object according to a preset feature extraction rule; A feature information matrix is ​​established based on the multi-dimensional feature information of each target object. In the feature information matrix, rows represent the multi-dimensional feature information of a single target object, and columns represent the different dimensions of the multi-dimensional feature information. Based on the information push parameters and the preset feature weight configuration, set the weight value of each feature information dimension in the feature information matrix; Based on the feature information matrix and the weight values ​​of each feature information dimension in the feature information matrix, the feature attributes of each target object are constructed.

[0067] Based on the above embodiments, optionally, the preset tag library is generated in the following manner: Based on the first preset information, multiple types of information to be pushed are determined. The first preset information is used to characterize the requirements of the multiple target objects for pushed information, and the multiple types of information to be pushed are used to indicate multiple fields of information to be pushed. Based on the multiple types of information to be pushed, a set of data dictionaries is constructed. The set of data dictionaries contains multiple data dictionaries. Each data dictionary is used to describe the information domain indicated by any type of information to be pushed. Each data element in each data dictionary is used to describe the feature information of any information dimension within the corresponding information domain. Based on the data elements contained in each data dictionary, a first type of tag in the preset tag library is generated; based on the first type of tag in the preset tag library and the feature attributes of multiple target objects, a second type of tag in the preset tag library is generated.

[0068] Based on the above embodiments, optionally, a second type of tag in the preset tag library is generated according to a first type of tag in the preset tag library and the feature attributes of multiple target objects, including: According to the preset grouping rules, the feature attributes of multiple target objects are grouped to obtain multiple sets of second feature attributes and common features associated with each set of second feature attributes. Each feature profile in the second set of second feature attributes has at least one common feature. The common feature associated with each set of second feature attributes refers to the feature information shared by each feature attribute in each set of second feature attributes. The common features associated with each set of second feature attributes are combined with multiple first type tags in the preset tag library whose matching degree is not less than a preset threshold to obtain the second type tags in the preset tag library.

[0069] The technical solution of this invention, by acquiring information push parameters, can clarify the push direction and scope for subsequent information pushes; extract the identification information and authorized health status information of all target objects within the target push scope indicated by the information push parameters to construct a first feature attribute set, providing data support for differentiated and precise information push; under the constraint of the information push parameters, according to the first type of tags and the second type of tags that match each feature attribute obtained from the preset tag library, a scene tag is determined for each feature attribute. The scene tag can represent both the feature information matching the target object and the group feature information matching the target object group with common features, thereby ensuring that the scene tag corresponding to each feature attribute can comprehensively cover all kinds of feature information related to that feature attribute; generate push information that fits the feature attributes and needs of the target object according to the scene tag, and complete the information push, ensuring the targeting and adaptability of the information push. Based on the above technical solution, it is possible to generate suitable push information content for the target object according to the information push parameters, target object feature attributes and preset tag library, and push it to the corresponding target object. This can improve the accuracy and adaptability of information push to the target object, and thus enable the precision of information push in the scenario of health management for retired employees in enterprises, thereby improving the professionalism and humanistic care of enterprise health management services.

[0070] The information push device provided in the embodiments of the present invention can execute the information push method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the method execution.

[0071] The acquisition, storage, use, and processing of data in this application comply with relevant national laws and regulations and do not violate public order and good morals.

[0072] According to embodiments of this disclosure, this disclosure also provides an electronic device, a readable storage medium, and a computer program product.

[0073] Figure 3 A schematic diagram of an electronic device 10, which can be used to implement embodiments of the present invention, is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices (e.g., helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the invention described and / or claimed herein.

[0074] like Figure 3 As shown, the electronic device 10 includes at least one processor 11 and a memory, such as a read-only memory (ROM) 12 or a random access memory (RAM) 13, communicatively connected to the at least one processor 11. The memory stores computer programs executable by the at least one processor. The processor 11 can perform various appropriate actions and processes based on the computer program stored in the ROM 12 or loaded from storage unit 18 into the RAM 13. The RAM 13 can also store various programs and data required for the operation of the electronic device 10. The processor 11, ROM 12, and RAM 13 are interconnected via a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0075] Multiple components in electronic device 10 are connected to I / O interface 15, including: input unit 16, such as keyboard, mouse, etc.; output unit 17, such as various types of displays, speakers, etc.; storage unit 18, such as disk, optical disk, etc.; and communication unit 19, such as network card, modem, wireless transceiver, etc. Communication unit 19 allows electronic device 10 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0076] Processor 11 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. Processor 11 executes the various methods described above, such as the information push method.

[0077] In some embodiments, the information push method may be implemented as a computer program tangibly contained in a computer-readable storage medium, such as storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or installed on electronic device 10 via ROM 12 and / or communication unit 19. When the computer program is loaded into RAM 13 and executed by processor 11, one or more steps of the information push method described above may be performed. Alternatively, in other embodiments, processor 11 may be configured to perform the information push method by any other suitable means (e.g., by means of firmware).

[0078] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific reference products (ASSPs), systems-on-a-chip (SoCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0079] Computer programs used to implement the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when executed by the processor, the computer programs cause the functions / operations specified in the flowcharts and / or block diagrams to be performed. The computer programs may be executed entirely on a machine, partially on a machine, or as a standalone software package, partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0080] In the context of this invention, a computer-readable storage medium can be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, apparatus, or device. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination thereof. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0081] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the electronic device. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0082] The systems and technologies described herein can be implemented in computing systems that include back-end components (e.g., as data servers), or computing systems that include switching components (e.g., application servers), or computing systems that include front-end components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such back-end, switching, or front-end components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., communication networks). Examples of communication networks include local area networks (LANs), wide area networks (WANs), blockchain networks, and the Internet.

[0083] A computing system can include clients and servers. Clients and servers are generally located far apart and typically interact through communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or cloud host, which is a hosting product within the cloud computing service system to address the shortcomings of traditional physical hosts and VPS services, such as high management difficulty and weak business scalability.

[0084] In particular, according to embodiments of the present invention, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments of the present invention include a computer program product comprising a computer program carried on a non-transitory computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via communication unit 19, or installed from storage unit 18, or installed from ROM 12. When the computer program is executed by processor 11, it performs the functions defined in the methods of the embodiments of the present invention.

[0085] This invention also provides a computer program product, including a computer program that, when executed by a processor, implements the information push method provided in any embodiment of this application.

[0086] In implementing the computer program product, computer program code for performing the operations of this invention can be written in one or more programming languages ​​or a combination thereof. Programming languages ​​include object-oriented programming languages ​​such as Java, Smalltalk, and C++, as well as conventional procedural programming languages ​​such as C or similar languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network, including a local area network (LAN) or a wide area network (WAN), or it can be connected to an external computer (e.g., via the Internet using an Internet service provider). It should be understood that the various forms of processes shown above can be used, with steps reordered, added, or deleted. For example, the steps described in this invention can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution of this invention can be achieved, and this is not limited herein.

[0087] The specific embodiments described above do not constitute a limitation on the scope of protection of this invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this invention should be included within the scope of protection of this invention.

Claims

1. An information push method, characterized in that, The method includes: Obtain information push parameters, which include at least the topic of the information to be pushed, the target push range, and the expected accuracy of the information push. The target push range is used to indicate the set of target objects that the carrier carrying the information to be pushed can reach. Based on the information push parameters, a first set of feature attributes is determined. The first set of feature attributes contains the feature attributes of all target objects within the target push range indicated by the information push parameters. The feature attributes of the target objects are used to reflect the identification information of the target objects and the information authorized by the target objects to characterize their health status. Under the constraint of the topic of the information to be pushed as indicated by the information push parameters, for each feature attribute in the first feature attribute set, a scene tag corresponding to the feature attribute is determined according to a first type tag and a second type tag selected from a preset tag library that meet the preset matching conditions for the feature attribute; wherein, the preset tag library includes a first type tag and a second type tag; the first type tag is used to identify a first feature, which is used to characterize feature information under different information dimensions in different information domains; the second type tag is used to identify a first feature set that matches a target object group, which is used to indicate a feature attribute set in the first feature attribute set that has at least one common feature, and the second type tag is associated with the common feature of the target object group; the scene tag corresponding to each feature attribute is used to identify the first feature set consisting of the first type tag and the second type tag corresponding to each feature attribute under the constraint of the topic of the information to be pushed as indicated by the information push parameters; The information to be pushed is generated based on the scene label corresponding to each feature attribute, and the information to be pushed is pushed to the target object corresponding to each feature attribute.

2. The method according to claim 1, characterized in that, Under the constraint of the topic of the information to be pushed as indicated by the information push parameters, for each feature attribute in the first feature attribute set, the scene tag corresponding to the feature attribute is determined according to the first type of tag and the second type of tag selected from the preset tag library that meet the preset matching conditions, including: Based on the degree of matching between each feature attribute in the first feature attribute set and the common features of the corresponding target object groups associated with each second type tag in the preset tag library, the second type tag corresponding to each feature attribute in the first feature attribute set is determined; Based on the degree of matching between each first type tag in the preset tag library and the information push parameters, multiple third type tags are obtained; the third type tags are first type tags in the preset tag library whose degree of matching with the information push parameters is not lower than a preset threshold. Based on the degree of matching between each feature attribute in the first feature attribute set and each third type label in the plurality of third type labels, a plurality of fourth type labels corresponding to each feature attribute in the first feature attribute set are determined; the fourth type label is a third type label among the plurality of third type labels whose degree of matching with the feature attribute is not lower than a preset threshold; The scene label corresponding to each feature attribute is determined based on the multiple fourth-type labels corresponding to each feature attribute and the second-type labels corresponding to each feature attribute.

3. The method according to claim 1, characterized in that, The characteristic attributes of the target object are generated in the following way: Acquire first information about multiple target objects, the first information including information reflecting the identification of the target objects and information authorized by the target objects to characterize their health status; Based on the first information of each target object, the feature attributes of each target object are constructed.

4. The method according to claim 3, characterized in that, Based on the first information of each target object, the feature attributes of each target object are constructed, including: Extract multi-dimensional feature information of each target object from the first information of each target object according to a preset feature extraction rule; A feature information matrix is ​​established based on the multi-dimensional feature information of each target object. In the feature information matrix, rows represent the multi-dimensional feature information of a single target object, and columns represent the different dimensions of the multi-dimensional feature information. Based on the information push parameters and the preset feature weight configuration, set the weight value of each feature information dimension in the feature information matrix; Based on the feature information matrix and the weight values ​​of each feature information dimension in the feature information matrix, the feature attributes of each target object are constructed.

5. The method according to claim 1, characterized in that, The preset tag library is generated in the following way: Based on the first preset information, multiple types of information to be pushed are determined. The first preset information is used to characterize the requirements of the multiple target objects for pushed information, and the multiple types of information to be pushed are used to indicate multiple fields of information to be pushed. Based on the multiple types of information to be pushed, a set of data dictionaries is constructed. The set of data dictionaries contains multiple data dictionaries. Each data dictionary is used to describe the information domain indicated by any type of information to be pushed. Each data element in each data dictionary is used to describe the feature information of any information dimension within the corresponding information domain. Based on the data elements contained in each data dictionary, generate the first type of tag in the preset tag library; Based on the first type of tags in the preset tag library and the feature attributes of multiple target objects, a second type of tag in the preset tag library is generated.

6. The method according to claim 5, characterized in that, Based on the first type of tags in the preset tag library and the feature attributes of multiple target objects, generate the second type of tags in the preset tag library, including: According to the preset grouping rules, the feature attributes of multiple target objects are grouped to obtain multiple sets of second feature attributes and common features associated with each set of second feature attributes. Each feature profile in the second set of second feature attributes has at least one common feature. The common feature associated with each set of second feature attributes refers to the feature information shared by each feature attribute in each set of second feature attributes. The common features associated with each set of second feature attributes are combined with multiple first type tags in the preset tag library whose matching degree is not less than a preset threshold to obtain the second type tags in the preset tag library.

7. An information push device, characterized in that, The device includes: The information push parameter acquisition module is used to acquire information push parameters. The information push parameters include at least the topic of the information to be pushed, the target push range, and the expected accuracy of the information push. The target push range is used to indicate the set of target objects that the carrier carrying the information to be pushed can reach. The feature attribute set determination module is used to determine a first feature attribute set based on the information push parameters. The first feature attribute set contains feature attributes of all target objects within the target push range indicated by the information push parameters. The feature attributes of the target objects are used to reflect the identification information of the target objects and the information authorized by the target objects to characterize their health status. The scene tag determination module is used, under the constraint of the topic of the information to be pushed as indicated by the information push parameters, to determine the scene tag corresponding to each feature attribute in the first feature attribute set, based on first type tags and second type tags selected from a preset tag library that meet preset matching conditions for the feature attribute; wherein, the preset tag library includes first type tags and second type tags; the first type tag is used to identify a first feature, which is used to represent feature information under different information dimensions in different information domains; the second type tag is used to identify a first feature set that matches a target object group, which is used to indicate a feature attribute set in the first feature attribute set that has at least one common feature, and the second type tag is associated with the common feature of the target object group; the scene tag corresponding to each feature attribute is used to identify the first feature set consisting of the first type tags and the second type tags corresponding to each feature attribute under the constraint of the topic of the information to be pushed as indicated by the information push parameters. The information push module is used to generate push information based on the scene tag corresponding to each feature attribute, and push the push information to the target object corresponding to each feature attribute.

8. The apparatus according to claim 7, characterized in that, The scene label determination module is specifically used for: Based on the degree of matching between each feature attribute in the first feature attribute set and the common features of the corresponding target object groups associated with each second type tag in the preset tag library, the second type tag corresponding to each feature attribute in the first feature attribute set is determined; Based on the degree of matching between each first type tag in the preset tag library and the information push parameters, multiple third type tags are obtained; the third type tags are first type tags in the preset tag library whose degree of matching with the information push parameters is not lower than a preset threshold. Based on the degree of matching between each feature attribute in the first feature attribute set and each third type label in the plurality of third type labels, a plurality of fourth type labels corresponding to each feature attribute in the first feature attribute set are determined; the fourth type label is a third type label among the plurality of third type labels whose degree of matching with the feature attribute is not lower than a preset threshold; The scene label corresponding to each feature attribute is determined based on the multiple fourth-type labels corresponding to each feature attribute and the second-type labels corresponding to each feature attribute.

9. An electronic device, characterized in that, The electronic device includes: At least one processor; and A memory communicatively connected to the at least one processor; wherein, The memory stores a computer program that can be executed by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to perform the information push method according to any one of claims 1-6.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions that are used to cause a processor to execute the information push method according to any one of claims 1-6.

Images