Information pushing method, electronic equipment and computer program product

Abstract

The invention provides an information pushing method, electronic equipment and a computer program product. The information pushing method comprises the steps that a feature tag of a subject is determined according to interaction data of the subject, and the feature tag represents demand features and emotional features of the subject; generating target information corresponding to the feature tag; and pushing the target information to the subject.

Description

Technical Field

[0001] The present disclosure relates to the technical field of information processing and the like, and particularly to an information push method, an electronic device, and a computer program product. Background Art

[0002] In today's digital age, online social platforms have become an important way for various industries to maintain customer relationships. Through diverse social platforms, enterprises and customers can conduct efficient consultations, feedback, and exchanges. In addition, these platforms also provide a channel for enterprises to push relevant information to target customers, which helps to enhance customer stickiness and satisfaction, while ensuring that customers can obtain the information they truly need.

[0003] However, in traditional information push methods, enterprises often rely on the personal understanding and judgment of service personnel to selectively push information. This method not only consumes a large amount of labor costs, but also easily leads to the omission of important information. Even worse, sometimes service personnel will adopt an undifferentiated information push strategy, sending the same content to all customers, which may not only disturb customers who do not need this information, but also lead to customer dissatisfaction or even complaints, instead reducing customer stickiness to the enterprise. Summary of the Invention

[0004] The present disclosure provides an information push method, an electronic device, and a computer program product.

[0005] According to one aspect of the present disclosure, there is provided an information push method, including: determining a feature tag of the subject according to the interaction data of the subject, the feature tag characterizing the demand feature and emotional feature of the subject; generating target information corresponding to the feature tag; and pushing the target information to the subject.

[0006] In some embodiments, determining the feature tag of the subject according to the interaction data of the subject includes: determining a first feature tag of the subject according to the conversation data and / or behavior data in the interaction data, the first feature tag characterizing the demand feature of the subject for information; and determining a second feature tag of the subject according to the conversation data and / or behavior data in the interaction data, the second feature tag characterizing the emotional feature of the subject when obtaining information.

[0007] In some embodiments, generating target information corresponding to the feature tag includes: determining a target theme according to the feature tag; and controlling an information generation model to generate target information describing the target theme, where the target information is in the form of text, picture, or video.

[0008] In some embodiments, determining the target topic includes: determining the subject category of each subject according to the feature tags of each subject, where subjects belonging to the same subject category have feature tags with the same attributes; and determining the number of subjects corresponding to each subject category, and using the subject category with the number of subjects exceeding the number threshold as the target topic.

[0009] In some embodiments, pushing the target information to the subject includes: pushing the target information to the subjects belonging to the subject category.

[0010] In some embodiments, after determining the feature tags of the subject, it further includes: using the topic with the number of triggers exceeding the trigger threshold as the target topic according to the number of times each topic is triggered by an external platform in the first period; and controlling an information generation model to generate target information describing the target topic.

[0011] In some embodiments, pushing the target information to the subject includes: determining a plurality of first feature tags of the target information and the weights of the target information for each first feature tag, where the weights represent the degree of correlation between the first feature tag and the topic described by the target information; determining the same first feature tags between the target information and the subject; adding the weights of each same first feature tag to obtain the association score of the subject; and pushing the target information to the subjects with the association score greater than the score threshold.

[0012] In some embodiments, pushing the target information to the subject includes: determining whether the content of the target information is consistent with the reference data of the target topic; in the case where the content is consistent with the reference data, determining whether there are any prohibited words in the target information, where the prohibited words are words that cannot exist in the target information; and in the case where there are no prohibited words in the target information, determining that the verification of the target information passes and pushing the target information with passed verification to the subject.

[0013] In some embodiments, pushing the target information with passed verification to the subject includes: determining a push strategy for the target information according to the second feature tag of the subject; and pushing the target information to the corresponding subject according to the push strategy.

[0014] In some embodiments, after pushing the target information to the subject, it includes: adjusting the feature tags of the subject according to the feedback data of the subject on the target information.

[0015] According to one aspect of the present disclosure, there is provided an electronic device, including: a memory that stores execution instructions; and a processor that executes the execution instructions stored in the memory, such that the processor executes the information push method of any embodiment of the present disclosure.

[0016] According to one aspect of the present disclosure, a readable storage medium stores execution instructions, and when the execution instructions are executed by a processor, they are used to implement the information push method of any embodiment of the present disclosure.

[0017] According to one aspect of the present disclosure, a computer program product includes a computer program, and when the computer program is executed by a processor, it implements the information push method of any embodiment of the present disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] The drawings illustrate exemplary embodiments of the present disclosure and, together with the description thereof, are used to explain the principles of the present disclosure. These drawings are included to provide a further understanding of the present disclosure and are included in this specification and form a part of this specification.

[0019] Figure 1 is an application scenario diagram of the information push method according to an embodiment of the present disclosure.

[0020] Figure 2 is a flowchart of an interaction process according to an embodiment of the present disclosure.

[0021] Figure 3 is a flowchart of the information push method according to an embodiment of the present disclosure.

[0022] Figure 4 is a flowchart of a push process according to an embodiment of the present disclosure.

[0023] Figure 5 is another flowchart of a push process according to an embodiment of the present disclosure.

[0024] Figure 6 is a schematic block diagram of the structure of an information push device according to an embodiment of the present disclosure.

[0025] Figure 7 is a schematic block diagram of the structure of an electronic device according to an embodiment of the present disclosure. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0026] The present disclosure will be further described in detail below with reference to the drawings and examples. It can be understood that the specific examples described herein are only used to explain the relevant content and do not limit the present disclosure. Additionally, it should be noted that for the sake of convenience of description, only the parts related to the present disclosure are shown in the drawings.

[0027] It should be noted that, without conflict, the embodiments in the present disclosure and the features in the embodiments may be combined with each other. The technical solutions of the present disclosure will be described in detail below with reference to the drawings and in conjunction with the embodiments.

[0028] In today's digital age, online social platforms have become an important way for various industries to maintain customer relationships. Especially in the real estate transaction scenario, real estate enterprises communicate and push information to customers efficiently through diverse social platforms. However, traditional information push methods usually adopt an undifferentiated strategy, that is, sending the same content to all customers. This "one-size-fits-all" approach may not only disturb customers who do not need this information but also easily trigger customer dissatisfaction and even complaints, which instead weakens the customer's stickiness to the enterprise. To avoid this problem, some real estate enterprises attempt to push targeted information based on the understanding of customers by service personnel. For example, through interaction with customers, service personnel judge that a customer is more concerned about rental information and thus push relevant content to this customer. However, this method has obvious limitations: if a customer subsequently browses an article about housing purchase policies and the service personnel fail to monitor this change in a timely manner, then when pushing information related to housing purchase policies, this customer may be missed. Obviously, this push method relies too much on the subjective judgment of service personnel, not only consuming a large amount of human resources but also easily resulting in the omission of important information and being difficult to meet the dynamically changing needs of customers.

[0029] Therefore, the present disclosure proposes an information push method.

[0030] Figure 1 It is a schematic diagram of the application scenario of the information push method according to the embodiments of the present disclosure. As Figure 1 shown, in this application scenario, it may include a server 100 and a terminal device 200. The server 100 and the terminal device 200 can be connected through a network or Bluetooth to perform data interaction. The server 100 can be a cloud server or a physical server, and the terminal device 200 can be an intelligent device such as a computer, a mobile phone, or a tablet. The server 100 is used to provide the basic data required to run the information push method, and the terminal device 200 executes the information push method of the present disclosure based on the basic data provided by the server 100, and the server side interacting with the client can run on the terminal device 200.

[0031] For the convenience of description and to make the technical solutions of the specific embodiments of the present disclosure easier to understand, before describing the information push method implemented in the present disclosure, the technical terms involved in the specific embodiments of the present disclosure are explained as follows: Subject: For example, a customer with information needs. In the real estate field, a customer can be a house owner or a buyer.

[0032] Interactive data: It can be the conversation data generated by the subject through the client interacting with the server, or the behavioral data generated by the subject through the client performing actions such as clicking, liking, and commenting on the information published by the server, or the feedback data such as the satisfaction level and information demand level of the subject with respect to the server.

[0033] Feature tags: Represent the demand characteristics and emotional characteristics of the subject, where the first feature tag expresses the demand characteristics and the second feature expression expresses the emotional characteristics. Each subject can have one or more first feature tags and one or more second feature tags.

[0034] Target information: It can be information such as articles, pictures, videos, etc. that can describe the target topic.

[0035] Target topic: For example, a certain popular topic in a certain industry.

[0036] Figure 2 It is a flowchart of the interaction process according to the embodiments of the present disclosure. As Figure 2 shown, it shows the data flow process between the client and the server when executing the information push method. Among them, the server can run on Figure 1 the terminal device 200 and is operated by an enterprise; the client can run on the mobile device of the subject, such as a mobile phone, etc., for interacting with the server and receiving the information pushed by the server.

[0037] The client executes step 201 to generate conversation data, behavioral data, feedback data, etc. These data are the interaction data between the subject and the server and can reflect the demand characteristics and emotional characteristics of the subject.

[0038] The server executes steps 202 to 206, captures various interaction data generated by the client via step 201, and then analyzes these interaction data to determine the feature tags of the subject served by the client. The feature tags include the first feature tag and the second feature tag. The first feature tag represents the demand characteristics of the subject, and the second feature tag represents the emotional characteristics of the subject. Then, according to the feature tags of all the subjects served by the server, the topic with the highest discussion degree among all the served subjects can be determined and used as the target topic to generate the target information. Of course, it is also possible to crawl the hot topics on the external platform regarding the industry where the enterprise is located and use them as the target topic to generate the target information. Then, the feature tags of each subject are matched with the target information to determine the subjects who have a demand for this information. Then, the target information is pushed to the corresponding subjects.

[0039] The client executes step 207 to generate feedback data regarding the target information. The feedback data includes: the service satisfaction evaluation of the server, the interaction data received for the target information, etc. If the subject believes that the target information is relatively well-matched with their needs, they can rate the push action, such as "10 points". Alternatively, if the subject indicates their interest in the information through behaviors such as clicking, viewing, or commenting, then the feedback data can record the total number of clicks, total number of shares, total number of likes, etc. obtained by the target information.

[0040] Furthermore, the server executes step 209 to update the subject's feature tags and the target information generation strategy based on the subject's feedback data.

[0041] If the feedback data shows that for information on the same topic, the information in video form has higher click-through and like counts than the information in text form, indicating that the topic is more easily spread and effectively presented in video form, then in subsequent generation of information on this topic, the proportion of video form is increased.

[0042] Through the interaction between the client and the server, richer subject interaction data is provided to the server. When the terminal device where the server is located executes the information push method, it can generate information that meets the needs of most subjects through this subject interaction data, and perform precise push, improving the effectiveness of information output and increasing the stickiness of the subject to the enterprise.

[0043] Figure 3 is a flowchart of the information push method according to an embodiment of the present disclosure. As Figure 3 shown, an information push method M300 is provided. Through step S310 and step S330, target information adapted to the subject's feature tags is generated and the target information is pushed specifically, enabling the effective output of information and increasing the trust and stickiness of the subject to the enterprise. The basic data required for the operation of the information push method M300 can be stored on Figure 1 server 100 and run by the terminal device 200; the server can be installed on the terminal device 200 for interaction with the client (i.e., the subject).

[0044] In step S310, according to the subject's interaction data, the subject's feature tags are determined.

[0045] The interaction data includes conversation data, behavior data, and feedback data.

[0046] The subject sends a consultation question to the server through the client, and this process generates conversation data. The conversation data contains the content that the subject is concerned about, and these contents reflect the demand characteristics of the subject. The conversation data can be in text form, or in voice or other forms, which are not restricted here. If the conversation data is in voice form, it will be converted into text form during the subsequent analysis process.

[0047] The subject reads the information published by the server through the client. For example, after the server publishes an article, if the subject is interested in the article title and clicks on the link to the article content and then reads it. Then the "click" is the behavior of the subject, and at least the "number of clicks" and the "click object" can be used as a set of behavior data. Other examples of behavior data include: the subject's reaction to the pushed information. For example, the subject actively blocks the information published by the enterprise, the subject pins the enterprise account, or the subject views most of the information published by the server, etc., all of which will generate certain behavior data. Similarly, when the subject is a house owner, actions such as "rent adjustment" can be generated, and corresponding behavior data will be generated accordingly, which will not be elaborated here one by one. Different behaviors will generate different behavior data, which are not restricted here. Behavior data can show the topics that the subject is interested in and reflect the demand characteristics of the subject.

[0048] In addition, the conversation data and behavior data can also reflect the emotional characteristics of the subject, including the subject's satisfaction with the enterprise service, the subject's satisfaction with the information pushed by the server, the urgency of obtaining the enterprise service, etc.

[0049] After the subject receives the service from the server, the subject will evaluate the service, and then a service satisfaction evaluation will be generated. Then this service satisfaction evaluation is a form of conversation data. For example, after the subject sends "What is the current housing purchase policy?" to the server through the client, the server quickly pushes information related to "housing purchase policy" to the client. The subject believes that the server's feedback can solve its problem, and the response is quick and the attitude is good, and the subject will give a service satisfaction evaluation of "10 points".

[0050] Feature tags are the demand characteristics and emotional characteristics of the subject reflected in the interaction data. The demand characteristics are presented in the form of the first feature tag, and the emotional characteristics are presented in the form of the second feature tag. The first feature tag can be tags expressing demands such as "concerned about price cuts", "concerned about housing purchase policies in City A", etc., and the second tag can be tags expressing emotional states such as "positive", "negative", "urgently want to sell", "responsive", etc. The foregoing are only examples of feature tags, and in actual applications, they can be set to other tag contents, which are not restricted here.

[0051] It should be noted that according to the interaction data of the entities, each entity can have multiple first feature tags and multiple non - contradictory second feature tags. The number of feature tags for each entity is not limited.

[0052] It should be noted that in the embodiments of the present disclosure, the methods for pushing target information to an entity include: publishing the target information, setting the visible range of the target information to include the entity, or sending the target information to the entity by means of sending a message reminder. Thus, the user can receive the target information by means of active pulling or by means of passive notification. In practical applications, there can be multiple pushing methods, which are not limited herein.

[0053] In step 320, generate target information corresponding to the feature tags.

[0054] In some embodiments, the target topic can be determined according to the feature tags; then, control the information generation model to generate target information describing the target topic, where the target information is in the form of text, picture or video.

[0055] That is to say, the target topic of the target information can be determined by the tag popularity. Specifically, the method for determining the target topic by the tag popularity is: according to the feature tags of each entity, determine the entity category of each entity, where the entities belonging to the same entity category have feature tags with the same attributes; and determine the number of entities corresponding to each entity category, and use the entity category with the number of entities exceeding the number threshold as the target topic.

[0056] For example, determine the entity category of "housing purchase and sale policies" for entities such as "pay attention to the housing purchase and sale policies in City A", "pay attention to the housing purchase and sale policies in City B", and "pay attention to the housing purchase and sale policies in City C". If the number of entities corresponding to this entity category exceeds the number threshold, for example, 60 entities have feature tags with the attribute of "housing purchase and sale policies", exceeding the number threshold of 50, then use "housing purchase and sale policies" as the target topic to generate target information.

[0057] Of course, the target topic of the target information can also be determined by the topic popularity of an external platform. Specifically, the method for determining the target topic by the topic popularity of an external platform is: according to the number of times each topic is triggered on the external platform in the first period, use the topic with the number of trigger times exceeding the number threshold as the target topic. The first period can be a natural month, etc., which is not limited herein; the external platform can be one or more network platforms (such as Weibo), or an offline discussion environment, which is not limited herein. It should be noted that the topics concerned in the present disclosure are all related topics in the industry where the enterprise is located, and different enterprises can pay attention to different topics.

[0058] It should be noted that the target topic can also be specified by the service staff of the server according to the expansion of the enterprise's business. Determining the target topic through the topic popularity of the external platform is one of the ways to specify the target topic. Specifying the target topic can overcome the time lag of subject classification and ensure that each subject can quickly obtain the latest information.

[0059] In step S330, the target information is pushed to the subject.

[0060] If the target topic of the target information is determined by the label popularity of the subject, then the target information is pushed to each subject belonging to the subject category associated with the target topic.

[0061] If the target topic of the target information is determined by the topic popularity of the external platform, then the method of pushing the target information can be: determining multiple first feature tags of the target information and the weights of the target information for each first feature tag, where the weight represents the degree of relevance between the first feature tag and the topic described by the target information; determining the same first feature tags between the target information and the subject; adding the weights of each same first feature tag to obtain the association score of the subject; and pushing the target information to the subject whose association score is greater than the score threshold.

[0062] After generating the target information, each target information will have one or more first feature tags according to the content it describes. The first feature tags configured for the subject are also selected from the first feature tags of all the information published by the enterprise. As the content of the target information iterates, the types and dimensions of the first feature tags also increase, and the new first feature tags are recorded in the tag set. After the server establishes a friendship relationship with a new subject, it will find the first feature tags suitable for the subject in the tag set and use them as the feature tags of the subject.

[0063] In addition, according to the emphasis of the topic described by the target information, weights can be configured for each of the first feature tags. The weight represents the degree of relevance between the first feature tag and the topic described by the target information. The weights configured for the first feature tags of different target information are different.

[0064] For example, the target theme described by a certain target information is "decrease in deed tax", which mainly describes the deed tax policy in the housing purchase and sale policies of cities A and B, and secondarily describes the housing price situation. Then the first feature tags of this target information can be "concerned about the housing purchase and sale policy of city A", "concerned about the housing purchase and sale policy of city B", and "concerned about housing prices"; since the description of housing prices has a relatively small length, a weight of 0.35 is configured for "concerned about the housing purchase and sale policy of city A", a weight of 0.35 is configured for "concerned about the housing purchase and sale policy of city B", and a weight of 0.3 is configured for "concerned about housing prices". In this way, when the first feature tags of a certain subject are "concerned about the housing purchase and sale policy of city A" and "concerned about housing prices", then its association score can be the sum of 0.35 and 0.3, that is, 0.75. If 0.75 is greater than the score threshold of 0.35, then this subject is taken as the audience of this information.

[0065] During the pushing process, it also includes a process of verifying the target information to ensure the authenticity of the information content and the compliance of the information content. Specifically, it is determined whether the content of the target information is consistent with the reference data of the target theme; in the case where the content is consistent with the reference data, it is determined whether there are any prohibited words in the target information, and prohibited words are words that cannot exist in the target information; and in the case where there are no prohibited words in the target information, it is determined that the verification of the target information passes, and the target information that passes the verification is pushed to each subject.

[0066] It should be noted that the target information of the present disclosure can be generated by an information generation model, and the information generation model includes GPT (Generative Pre-trained Transformer) and BERT (Bidirectional Encoder Representations from Transformers), etc. After inputting the target theme into the information generation model, the model can combine the data related to this theme on the external platform to generate information describing this theme. In addition, it will also combine the rules of the platform to which the target information is transmitted to control the content generated by the information generation model not to contain prohibited words of the relevant platform, so as to achieve unobstructed dissemination of information.

[0067] Therefore, the reference data mentioned above is the relevant data of the external platform that the information generation model draws on when generating the target information. Moreover, when the data of the external platform is used as the reference data for the target generation model, its authenticity should have been verified. After generating the target information, by determining the consistency between the reference data and the target information, it is determined whether the content expressed by the target information is true and conforms to the actual situation of the relevant industry. The prohibited words are the words prohibited in the word usage rules of the platform where the target information is disseminated. The dissemination platform of the target information should be the platforms where the client and the server are located. The word usage rules of different platforms are different, and the prohibited words are not listed here.

[0068] Of course, in order to consider the feelings of the subject, after the target information passes the verification, the state of the subject should also be considered. That is, according to the second characteristic label of the subject, determine the push strategy for the target information; and push the target information to the corresponding subject according to the push strategy. For example, if the second characteristic label of the subject shows "complaint", it means that the subject is in an unsatisfied state at this time. Then the push strategy formulated for this subject should be "push non-advertising information". At this time, if the target information is of the "non-advertising" attribute, then this target information can be pushed to this subject; otherwise, the relevant information will not be pushed to it to avoid causing customer complaints from the subject and reducing the subject's favorability towards the enterprise.

[0069] The information push method proposed in this disclosure combines the interaction data of the subject to determine characteristic labels for each subject. And according to the characteristic labels of the subject or social hotspots, determine the description subject of the target information, so as to meet the information acquisition needs of the subject as much as possible and reduce the output and dissemination of invalid information. Moreover, after generating the target information, according to the degree of fit between the target information and the characteristic label of the theme, push the target information to the corresponding subject, reducing the interference to the subjects who are not interested in this information, maximizing the effective dissemination of information, and enhancing the trust and stickiness of the subject to the enterprise.

[0070] The following describes the complete process of implementing the information push method.

[0071] After the server establishes an interaction relationship with the personal account of the subject through the enterprise account, the subject can send information such as inquiries and consultations to the server through the client. The enterprise can also push information or respond to the subject through the server. At this time, the subject will generate conversation data on the client. The conversation data can be in the forms of text, pictures, and voices. If the conversation data is in the form of voice, the conversation content can be converted into text through voice recognition technology.

[0072] In addition, when the subject clicks on the information published by the server, likes, comments, or forwards the information, or makes a service satisfaction evaluation of the service, or when the subject makes a rent adjustment as the landlord, the generated behavior data will also be recorded.

[0073] After the present disclosure obtains these conversation data and behavior data in a preset period, it will also store them in the same JSON (JavaScript Object Notation) structure for subsequent analysis. It should be noted that when obtaining data, these data will be classified according to the content of the data, and only after classification can the category of the data be determined, that is, behavior data or conversation data. Store the data belonging to the same category in the corresponding database, such as the relational database MySQL.

[0074] It should be noted that when the server generates information, each piece of information will have a first feature label to indicate the content described by the information. These first feature labels will be stored in the first feature label set. At the same time, some second feature labels describing emotional characteristics will also be preset and stored in the second feature label set.

[0075] Figure 4 It is a flowchart of a push process according to an embodiment of the present disclosure. The following combines Figure 4 , to show one of the ways to push target information.

[0076] In step 401, according to the interaction data of the subject, determine the feature label of the subject.

[0077] The interaction data includes conversation data, behavior data, and feedback data. The subject sends a consultation question to the server through the client, and this process will generate conversation data. The conversation data contains the content that the subject is concerned about, and these contents reflect the demand characteristics of the subject. The conversation data can be in text form or in voice form, etc., and there is no limitation here. If the conversation data is in voice form, it will be converted into text form in the subsequent analysis process.

[0078] The subject reads the information published by the server through the client. For example, when the server publishes an article, if the subject is interested in the article title, clicks on the link to the article content and then reads it. Then "clicking" is the behavior of the subject, and at least "the number of clicks" and "the clicked object" can be used as a group of behavior data. Behavior data also includes, for example, the reaction of the subject to the pushed information. For example, the subject actively blocks the information published by the enterprise, the subject pins the enterprise account, or the subject views most of the information published by the server, etc., will all generate certain behavior data. Similarly, when the subject is a house owner, actions such as "rent adjustment" can be generated and corresponding behavior data can be generated accordingly, which will not be elaborated here one by one. Different behaviors will generate different behavior data, and there is no limitation here. Behavior data can show the topics that the subject is interested in and reflect the demand characteristics of the subject.

[0079] In addition, the dialogue data and behavior data can also reflect the emotional characteristics of the subject, including the subject's satisfaction with the enterprise service, the subject's satisfaction with the information pushed by the server, the urgency of obtaining the enterprise service, etc.

[0080] After the subject receives the service from the server, the subject will evaluate the service, and then a service satisfaction evaluation will be generated. This service satisfaction evaluation is a form of dialogue data. For example, after the subject sends "What is the current housing policy?" to the server through the client, the server quickly pushes information related to "housing policy" to the client. If the subject believes that the server's feedback can solve its problem, and the response is rapid and the attitude is good, the subject will give a service satisfaction evaluation of "10 points".

[0081] Feature tags are the demand characteristics and emotional characteristics of the subject reflected in the interaction data. The demand characteristics are presented in the form of the first feature tag, and the emotional characteristics are presented in the form of the second feature tag. The first feature tag can be tags expressing demands such as "concerned about price cuts", "concerned about housing purchase and sale policies in City A", etc., and the second tag can be tags expressing emotional states such as "positive", "negative", "urgent to sell", "responsive", etc. The foregoing are only examples of feature tags, and in actual applications, they can be set to other tag contents, which are not limited here.

[0082] It should be noted that according to the interaction data of the subject, each subject can have multiple first feature tags and multiple non-contradictory second feature tags. The number of feature tags for each subject is not limited.

[0083] Furthermore, in step 402, according to the feature tags of each subject, a subject category is determined for the subject. Substantially, it is to classify the feature tags with the same attributes into one category and use it as the subject category. For example, both "concerned about housing purchase and sale policies in City A" and "concerned about housing purchase and sale policies in City B" have the attribute of "housing purchase and sale policies" and can be classified into the "housing purchase and sale policies" subject category.

[0084] Furthermore, in step 403, the number of subjects in each subject category is counted. For example, there are 10 subjects belonging to the "housing purchase and sale policies" subject category and 60 subjects belonging to the "housing price" subject category. Obviously, the topic related to "housing price" has a higher popularity. If more information related to housing price is generated and pushed, it may receive more attention from subjects and improve the stickiness of subjects to the enterprise.

[0085] Further, in step 404, it is determined whether the number of entities is greater than a quantity threshold. The quantity threshold can be determined according to the number of entities bound to the server. For example, if there are 100 entities that have established an interaction relationship with the server, the quantity threshold can be set to 20; if there are 1000 entities that have established an interaction relationship with the server, the quantity threshold can be set to 100, and there is no limitation here.

[0086] Further, if the number of entities in a certain entity category is greater than the quantity threshold, step 405 is executed, and with this entity category as the target theme, target information is generated. When generating the target information, an information generation model can be used, which will not be elaborated here.

[0087] Further, in step 406, the target information is pushed to all entities belonging to this entity category.

[0088] Figure 5 It is another flowchart of the push process according to an embodiment of the present disclosure. In combination with Figure 5 to show another way of pushing target information.

[0089] In step 501, according to the interaction data of the entity, the characteristic label of the entity is determined. This step can refer to Figure 3 the description of step S310 therein, which will not be elaborated here. Step 501 is the same as step 401.

[0090] In step 502, the trigger times of each theme on the external platform in the first period are obtained.

[0091] The trigger times include the situation where the published remarks contain relevant themes, the search, click and forward times of relevant themes, the number of discussions under the topic of relevant themes, etc. The external platform can be any platform in the network or in reality, and there is no limitation here. The first period can be a natural day, an hour, etc., and there is no limitation here.

[0092] Further, in step 503, it is determined whether the trigger times are greater than a times threshold. If the trigger times of a certain theme on the external platform are greater than the times threshold, it means that the attention degree to this entity in the current social environment is relatively high. At this time, the social hotspots can be focused on in a timely manner, and step 504 is executed, and with this theme as the target theme, target information is generated. The previous way of pushing target information is more based on the active interaction of the entity, and it takes a certain period to determine the theme. Compared with determining the theme through social hotspots, it has a certain lag. Figure 5 The method shown in

[0093] Further, perform step 505 to determine the first feature tags of the target information and their weights. Then, perform step 506 to determine the same first feature tags of the subject and the target information. Further, perform step 507 to add up the weights of each same first feature tag to determine the association score of the subject.

[0094] It should be noted that the method for determining the association score of the subject is not limited to adding up the weights of the same first features. Any other method that can represent the degree of association between the subject and the target information falls within the protection scope of the present disclosure.

[0095] Further, perform step 508 to determine whether the association score is greater than the score threshold. If the association score of the subject is greater than the score threshold, it proves that the subject matches the target information, and step 509 should be performed to push the target information to the corresponding subject whose association score is greater than the score threshold.

[0096] Among them, step 406 and step 509 are the same. During the implementation process, the authenticity and compliance of the target information should be verified. That is, determine whether the content of the target information is consistent with the reference data of the target theme; in the case where the content is consistent with the reference data, determine whether there are prohibited words in the target information, and prohibited words are words that cannot exist in the target information; and in the case where there are no prohibited words in the target information, determine that the verification of the target information passes, and push the verified target information to each subject.

[0097] Further, in order to consider the feelings of the subject, after the target information passes the verification, the state of the subject should also be considered. That is, according to the second feature tag of the subject, determine the push strategy for the target information; and push the target information to the corresponding subject according to the push strategy. For example, if the second feature tag of the subject shows "complaint", indicating that the subject is in an unsatisfied state at this time, then the push strategy formulated for this subject should be "push non-advertising information". At this time, if the target information is of the "non-advertising" attribute, then the target information can be pushed to the corresponding subject; otherwise, stop pushing the relevant information to it to avoid causing customer complaints from the subject and reducing the subject's favorability towards the enterprise.

[0098] After pushing the target information to each entity, the feedback data of each entity on the target information should be monitored. For example, count the total number of comments, total number of likes, etc. obtained for the target information, and determine the number of likes of entities in different regions for this information. It is also possible to compare the total number of likes obtained for different forms of information on the same topic. Then, based on this feedback data, adjust the generation strategy and push strategy for the target information. For example, if region D has a high degree of attention to the topic of "admission policy", then when generating information on the topic of "admission policy", focus on pushing it to entities in region D. Another example is that for the same topic, information in video form has a higher number of clicks than information in text form, so in subsequent generation of information on this topic, control the video form to have a larger proportion.

[0099] Of course, when publishing the target information, scheduled publishing can be set. For example, if the number of clicks is high at 8 pm every night, then push the target information to the corresponding entities at 8 pm every night. Batch publishing can also be set. For example, if multiple target information are generated at one time, then these target information can be pushed simultaneously. In addition, precise publishing can be carried out according to regions. For example, if the subject of a piece of information is "housing purchase policy in city A", usually entities in other cities will not pay attention to the policy of city A, so this information can be precisely published to all entities in city A.

[0100] The information push method proposed in this disclosure combines the interaction data of entities to determine feature tags for each entity. And based on the feature tags of the entities or social hotspots, determine the description subject of the target information, as much as possible to meet the information acquisition needs of the entities, and reduce the output and dissemination of invalid information. And after generating the target information, push the target information to the corresponding entities according to the degree of fit between the target information and the feature tags of the topic, reducing the interference to entities that do not pay attention to this information, maximizing the effective dissemination of information, and enhancing the trust and stickiness of entities to the enterprise.

[0101] Figure 6 It is a structural schematic diagram of an information push device according to an embodiment of this disclosure. Refer to Figure 6 As shown in, the information push device 600 proposed in this disclosure includes: a tag determination module 610, configured to determine the feature tags of an entity according to the interaction data of the entity, where the feature tags characterize the demand characteristics and emotional characteristics of the entity; an information generation module 620, configured to generate target information corresponding to the feature tags; and a push module 630, configured to push the target information to the entity.

[0102] The information push device 600 of this disclosure may be in the form of computer software, and each module of the information push device 600 may be in the form of computer software modules.

[0103] Each module of the information push device 600 of the present disclosure is provided to implement each step of the information push method. Its execution principle and steps can be referred to the foregoing, and will not be elaborated herein.

[0104] Figure 7 It is a schematic block diagram of the structure of an electronic device according to an embodiment of the present disclosure. As Figure 7 shown, the present disclosure further provides an electronic device 1000, including: a processor 1200 and a memory 1300, the memory 1300 stores execution instructions; the processor 1200 executes the execution instructions stored in the memory 1300, so that the processor 1200 executes the information push method.

[0105] The hardware structure of the electronic device 1000 can be implemented by using a bus architecture. The bus architecture can include any number of interconnected buses and bridges, depending on the specific application of the hardware and the overall design constraints. The bus 1100 connects various circuits including one or more processors 1200, a memory 1300, and / or hardware modules together. The bus 1100 can also connect various other circuits 1400 such as peripheral devices, voltage regulators, power management circuits, external antennas, etc.

[0106] The bus 1100 can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Component (EISA) bus, etc. The bus can be divided into an address bus, a data bus, a control bus, etc. For the sake of convenience of representation, only one connecting line is used in this figure, but it does not mean that there is only one bus or one type of bus.

[0107] The present disclosure further provides a readable storage medium, in which a computer program is stored, and the computer program is used to implement the above method when executed by a processor. The "readable storage medium" can be any device that can contain, store, communicate, propagate, or transmit a program for use by or in connection with an instruction execution system, apparatus, or device. More specific examples of the readable storage medium include the following: an electrical connection part (electronic device) having one or more wirings, a portable computer disk cartridge (magnetic device), a random access memory (RAM), a read only memory (ROM), an erasable programmable read only memory (EPROM or flash memory), an optical fiber device, and a portable read only memory (CDROM), etc.

[0108] The present disclosure also provides a computer program product. The method of the present disclosure can be implemented in whole or in part by software, hardware, firmware, or any combination thereof. When implemented using software, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer programs or instructions. When the computer program or instructions are loaded and executed, the processes or functions of the present disclosure are executed in whole or in part.

[0109] The computer program or instructions can be stored in a readable storage medium, or transmitted from one readable storage medium to another. For example, the computer program or instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center in a wired or wireless manner. The readable storage medium can be any available medium that can be accessed, or a data storage device such as a server or data center that integrates one or more available media. The available medium can be a magnetic medium, such as a floppy disk, hard disk, or magnetic tape; it can also be an optical medium, such as a digital video disc; or it can be a semiconductor medium, such as a solid-state drive. The computer-readable storage medium can be a volatile or non-volatile storage medium, or can include both volatile and non-volatile types of storage media.

[0110] Those skilled in the art should understand that the embodiments of the present disclosure can be provided as a method, an electronic device, a readable storage medium, or a computer program product. Therefore, the present disclosure can take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present disclosure can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk memory, CD-ROM, optical memory, etc.) that contain computer-usable program code.

[0111] The present disclosure is described with reference to the flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to the present disclosure. It should be understood that each process and / or block in the flowchart and / or block diagram, and the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, such that the instructions executed by the processor of the computer or other programmable data processing device generate means for implementing the specified functions in Figure 1 one process or multiple processes and / or blocks Figure 1 one block or multiple blocks.

[0112] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to operate in a particular manner, such that the instructions stored in the computer-readable memory produce a manufacture including an instruction device that implements the functions specified in one or more of the processes Figure 1 or blocks of one or more of the processes and / or Figure 1 blocks.

[0113] These computer program instructions can also be loaded onto a computer or other programmable data processing apparatus, such that a series of operational steps are performed on the computer or other programmable apparatus to produce a computer-implemented process, thereby providing steps for implementing the functions specified in one or more of the processes Figure 1 or blocks of one or more of the processes and / or Figure 1 blocks.

[0114] In the description of this specification, the descriptions with reference to the terms "one embodiment / way", "some embodiments / ways", "example", "specific example", or "some examples", etc. mean that the specific features, structures, or characteristics described in connection with the embodiment / way or example are included in at least one embodiment / way or example of the present disclosure. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment / way or example. Moreover, the specific features, structures, or characteristics described may be combined in any one or more embodiments / ways or examples in a suitable manner. In addition, without contradiction, those skilled in the art can combine and combine the different embodiments / ways or examples described in this specification and the features of different embodiments / ways or examples.

[0115] In addition, the terms "first" and "second" are used for descriptive purposes only and cannot be construed as indicating or implying relative importance or implicitly specifying the quantity of the indicated technical features. Thus, the features defined with "first" and "second" may explicitly or implicitly include at least one of the features. In the description of the present disclosure, "a plurality of" means at least two, such as two, three, etc., unless otherwise specifically defined.

[0116] Those skilled in the art should understand that the above embodiments are merely for clearly explaining the present disclosure and are not intended to limit the scope of the present disclosure. For those skilled in the art, other changes or modifications can be made on the basis of the above disclosure, and these changes or modifications are still within the scope of the present disclosure.

[0117] It is understandable that before using the technical solutions disclosed in the embodiments of the present disclosure, the types, usage scopes, usage scenarios, etc. of the personal information involved in the present disclosure should be informed to the user and the user's authorization should be obtained in an appropriate manner in accordance with relevant laws and regulations.

[0118] For example, when responding to receiving an active request from a user, a prompt message is sent to the user to clearly prompt the user that the operation requested by the user will require obtaining and using the user's personal information. Thus, the user can autonomously choose whether to provide personal information to software or hardware such as an electronic device, an application program, a server, or a storage medium that performs the operations of the technical solutions of the present disclosure according to the prompt message.

[0119] As an optional but non-limiting implementation manner, the manner of sending a prompt message to the user in response to receiving an active request from the user can be, for example, in the form of a pop-up window, and the prompt message can be presented in text in the pop-up window. In addition, the pop-up window can also carry a selection control for the user to choose "agree" or "disagree" to provide personal information to the electronic device.

[0120] It is understandable that the above process of notifying and obtaining the user's authorization is only illustrative and does not constitute a limitation on the implementation manner of the present disclosure, and other manners that meet relevant laws and regulations can also be applied to the implementation manner of the present disclosure.

[0121] Meanwhile, it is understandable that the data involved in the technical solutions of the present disclosure (including but not limited to the data itself, the acquisition or use of the data) should comply with the requirements of the corresponding laws, regulations and related provisions.

Claims

1. An information push method, characterized in that: include: Determine, based on the subject's interaction data, a feature label of the subject, wherein the feature label represents a demand feature and an emotional feature of the subject; generating target information corresponding to the feature tag; and The target information is pushed to the subject.

2. The information push method according to claim 1, characterized in that: Determining a feature tag of the subject according to the subject's interaction data includes: Determining a first characteristic tag of the subject according to the conversation data and / or behavior data in the interaction data, wherein the first characteristic tag represents a characteristic of the subject's demand for information; and A second feature tag of the subject is determined according to the conversation data and / or behavior data in the interaction data, wherein the second feature tag represents an emotional feature of the subject when acquiring information.

3. The information push method according to claim 1, characterized in that: Generating target information corresponding to the feature tag, including: Determining a target topic based on the feature tags; and The control information generation model generates target information describing the target subject, wherein the target information is in text form, picture form or video form.

4. The information push method according to claim 3, characterized in that: Identify target topics, including: Determining the subject category of each of the subjects according to the feature labels of each of the subjects, wherein subjects belonging to the same subject category have feature labels of the same attributes; and The number of subjects corresponding to each of the subject categories is determined, and the subject category whose number of subjects exceeds a quantity threshold is taken as the target subject.

5. The information push method according to claim 4, characterized in that: Pushing the target information to the subject includes: The target information is pushed to subjects belonging to the subject category.

6. The information push method according to claim 3, characterized in that: After determining the characteristic tag of the subject, the method further includes: According to the number of times each topic is triggered by the external platform in the first cycle, the topic whose number of triggering exceeds the number threshold is used as the target topic; and The control information generation model generates target information describing the target subject.

7. The information push method according to claim 6, characterized in that: Pushing the target information to the subject includes: Determine a plurality of first feature tags of the target information and a weight of the target information to each first feature tag, wherein the weight represents a degree of relevance between the first feature tag and a subject described by the target information; Determining a common first feature tag between the target information and the subject; Adding the weights of the same first feature tags to obtain a relevance score of the subject; and The target information is pushed to entities whose association scores are greater than a score threshold.

8. The information push method according to claim 1, characterized in that: Pushing the target information to the subject includes: Determining whether the content of the target information is consistent with the reference data of the target subject; In the case where the content is consistent with the reference data, determining whether there is a prohibited word in the target information, wherein the prohibited word is a word that cannot exist in the target information; and In the case that the prohibited words do not exist in the target information, it is determined that the verification of the target information has passed, and the target information that has passed the verification is pushed to the subject.

9. An electronic device, characterized in that: include: A memory storing execution instructions; as well as A processor, wherein the processor executes the execution instruction stored in the memory, so that the processor executes the information push method according to any one of claims 1 to 8.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the information pushing method according to any one of claims 1 to 8 is implemented.

Images