Targeted message pushing method and apparatus for cultural tourism system, and medium and device

Abstract

Disclosed in the present application are a targeted message pushing method and apparatus for a cultural tourism system, and a medium and a device. The targeted message pushing method for a cultural tourism system may comprise: acquiring, from a base station, base station information and user equipment information of currently accessing user equipments; querying whether the user equipment information is in a cultural tourism system, and if the user equipment information is in the cultural tourism system, setting tags for the user equipment information; constructing a target device set on the basis of the user equipment information having the set tags, and corresponding base station information; for each user equipment in the target device set, constructing a message body to be sent, wherein a method for constructing said message body comprises: acquiring a common attribute tag of a user profile of each user equipment in the target device set, and on the basis of the common attribute tag, acquiring service data corresponding to said message body; and pushing said message body to the user equipments in the target device set on the basis of the common attribute tag. Therefore, targeted message pushing is realized, so that message content is pushed, in an accurate, effective and targeted manner, to the possible public having corresponding requirements.

Description

Method, device, medium and equipment for targeted message push in cultural tourism system Technical Field

[0001] The present application relates to the field of communication technology, and more specifically, to a method, apparatus, medium, and equipment for targeted message push in a cultural tourism system. Background Art

[0002] With the advancement of communication technology, push messaging to specific user groups is becoming an increasingly common method of delivering messages, particularly in areas such as product promotion, marketing, and announcements. In real-world applications, there's an objective need for push messaging between business systems and clients. For example, in an internet hospital scenario, a medical record system needs to push messages to a doctor's workstation. Another example is providing messaging services to users in the cultural and tourism industry. These messages can be carrier-provided and include, but are not limited to, text messages, multimedia messages, rich media messages, and 5G messages.

[0003] In existing technology, operators compile various messages by obtaining mobile phone user information. At a specific time, the cultural and tourism system pushes these messages uniformly; users passively receive these messages. This approach fails to target push notifications to groups likely to have such requests, causing frustration among some users who prefer not to receive these messages, and even leading to complaints, reports, and public suggestions. In short, the effectiveness of push notifications is far from ideal. Therefore, there is an urgent need to improve the effectiveness of push notifications; specifically, how to accurately and effectively target pre-set message content to the public likely to have such requests, or to pre-selected specific groups.

[0004] Summary of the Invention

[0005] The main purpose of this application is to provide a method for targeted message push in a cultural and tourism system, so that messages can be accurately and effectively pushed to the public who are likely to have corresponding needs, thereby improving the user experience of message push as a whole.

[0006] In order to achieve the above-mentioned objectives, in the first aspect, the present application provides a method for targeted message push in a cultural and tourism system, including: obtaining base station information and currently connected user device information from a base station; querying whether the user device information is in the cultural and tourism system, and if the user device information is in the cultural and tourism system, setting a label for the user device information; constructing a target device set based on the user device information with set labels and the corresponding base station information; constructing a message body to be sent for each user device in the target device set, and the method of constructing the message body to be sent includes: obtaining the common attribute label of the user portrait of each user device in the target device set; obtaining the service data corresponding to the message body to be sent based on the common attribute label; and pushing the message body to be sent to the user devices in the target device set based on the common attribute label.

[0007] In some embodiments, users in the target device set are classified to form a user sample label data set; a semi-supervised support vector machine (TSVM) algorithm is used to obtain common attribute labels of the user sample label data set; the semi-supervised support vector machine (TSVM) algorithm is:

[0008] Among them, Loss represents the loss value, ω represents the normal vector on the plane, b represents the distance from the hyperplane to the origin, l is the number of label sample sets, (ω, b) determines a partitioning hyperplane, Represents the attribute tag, C l and C u They represent the compromise parameters specified by the user for balancing the importance of labeled samples and unlabeled samples in order to balance the complexity of the model, m represents the total number of users, and i is a positive integer; some of the user portraits are cleaned.

[0009] In some embodiments, the user sample label dataset includes: a labeled dataset and an unlabeled dataset.

[0010] In some embodiments, based on the user device information and the corresponding base station information of the user, when the user enters and leaves the base station, the attribute value of the user is calculated; the attribute value is compared with a predetermined threshold to determine the user classification.

[0011] In some embodiments, the user device in the target device set is selected using a decision tree rule; and the message body to be sent is pushed to the selected user device.

[0012] In some embodiments, the decision tree rule adopts a greedy search strategy, and the attribute entropy algorithm is:

[0013] Where V represents a random variable, P(V k ) represents V k The probability of k is a positive integer.

[0014] On the second aspect, the present application also provides a device for targeted message push in a cultural and tourism system, including: an information capture unit, used to obtain base station information and currently connected user device information from a base station; a query unit, used to query whether the user device information is in the cultural and tourism system, and if the user device information is in the cultural and tourism system, set a label for the user device information; a message body generation unit, used to construct a target device set based on the user device information with set labels and the corresponding base station information; construct a message body to be sent for each user device in the target device set, and the method of constructing the message body to be sent includes: obtaining the common attribute label of the user portrait of each user device in the target device set; obtaining the service data corresponding to the message body to be sent according to the common attribute label; a message push unit, used to push the message body to be sent to the user devices in the target device set according to the common attribute label.

[0015] In the third aspect, the present application also provides a communication terminal device, including a memory, a processor, and a computer program stored in the memory and runnable on the processor, characterized in that when the processor executes the computer program, the steps of the above-mentioned cultural and tourism system targeted message push method are implemented.

[0016] In a fourth aspect, the present application also provides a computer-readable storage medium, which stores a computer program, and is characterized in that when the computer program is executed by a processor, the steps of the above-mentioned cultural and tourism system targeted message push method are implemented.

[0017] In the fifth aspect, the present application also provides an electronic device, comprising: a memory for storing a computer program product; a processor for executing the computer program product stored in the memory, and when the computer program product is executed, the steps of the above-mentioned cultural and tourism system targeted message push method are implemented.

[0018] Compared with the prior art, this application has the following advantages:

[0019] This application provides a method, apparatus, medium, and device for targeted message push in a cultural and tourism system. By matching the common attribute tags of a user's device's user profile with the service data in the message body to be sent, the message is sent based on these common attribute tags. This enables targeted message push within the cultural and tourism system, enabling accurate and effective push of message content to the public likely to have corresponding needs, or to pre-selected specific groups. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] The drawings that constitute part of this application are used to provide a further understanding of this application and make other features, objects and advantages of this application more apparent. The illustrative embodiment drawings of this application and their descriptions are used to explain this application and do not constitute an improper limitation of this application. In the drawings:

[0021] FIG1 shows a flow chart of a method for targeted message push in a cultural tourism system according to an exemplary embodiment of the present application;

[0022] FIG2 shows a schematic diagram of a decision tree sample of an exemplary embodiment of the present application;

[0023] FIG3 shows a schematic diagram of a device for targeted message push in a cultural tourism system according to an exemplary embodiment of the present application;

[0024] FIG4 shows a schematic diagram of a communication terminal device according to an exemplary embodiment of the present application. DETAILED DESCRIPTION

[0025] In order to enable those skilled in the art to better understand the present invention, the following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments in the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts should fall within the scope of protection of this application.

[0026] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or sequential order. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present application described here. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0027] In this application, terms such as "upper," "lower," "left," "right," "front," "back," "top," "bottom," "inner," "outer," "center," "vertical," "horizontal," "transverse," and "longitudinal" indicate positions or locations based on the positions or locations shown in the accompanying drawings. These terms are primarily intended to better describe this application and its embodiments and are not intended to limit the devices, elements, or components indicated to having a specific orientation, or to being constructed or operated in a specific orientation.

[0028] Furthermore, some of the above terms may be used to express other meanings besides indicating a position or location. For example, the term "on" may also be used to express a dependency or connection in certain circumstances. Those skilled in the art will understand the specific meanings of these terms in this application based on the specific circumstances.

[0029] Additionally, the term "plurality" shall mean two or more.

[0030] It should be noted that, in the absence of conflict, the embodiments and features of the embodiments in this application can be combined with each other. The present application will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

[0031] Users accessing base stations are classified according to rules. These users are used as samples and AI-powered machine learning is used to identify user groups that meet the requirements. Combining base station information with information about connected user devices, machine learning is performed through sample induction to create user profiles. Finally, messages are pushed to user devices based on common attribute tags.

[0032] Figure 1 shows a flow chart of a method 100 for targeted message push in a cultural tourism system according to an exemplary embodiment of the present application. As shown in step 102, base station information and currently connected user equipment information are obtained from a base station.

[0033] In some embodiments, telecom operators obtain the IMSI / IMEI and phone number of connected mobile phones through base stations at specific locations and submit this information to cultural and tourism systems, such as cultural and tourism systems and internet medical systems. Optionally, user device information includes, but is not limited to, base station switching information and time information caused by the movement of the mobile phone.

[0034] As shown in step 104, the user device information is queried, that is, whether the user device information is in the cultural and tourism system. If the user device information is in the cultural and tourism system, a tag is set for the user device information. For example, in the cultural and tourism system, the user device information may include historical data. Based on the monitoring and processing of historical data, the user can be tagged with empirical tags, such as: travel enthusiast / non-travel enthusiast, nature enthusiast, culture enthusiast, historical site enthusiast, self-driving enthusiast, leisure walking enthusiast, sports enthusiast, etc.

[0035] As shown in step 106, a target device set is constructed, that is, a target device set is constructed based on the user device information with tags and the corresponding base station information. Generally, the target device set includes user devices that may need to push messages, but further screening is required.

[0036] As shown in step 108, a message body to be sent is constructed, that is, a message body to be sent is constructed for each user device in the target device set. The method of constructing the message body to be sent includes: obtaining common attribute tags of the user portrait of each user device in the target device set; and obtaining service data corresponding to the message body to be sent based on the common attribute tags.

[0037] In some embodiments, the users in the target device set can be classified to form a user sample label dataset. The following describes the method of user classification using the cultural tourism system as an example:

[0038] For users who have accessed the base station through monitoring, after obtaining the mobile phone number of the base station access user and the user whose data is retained in the cultural and tourism system, the base station information is used to classify the user in the following way, and the data is used as the label sample data for semi-supervised learning of machine learning. The base station information may include: base station number, base station location, etc. The specific operation is as follows:

[0039] ① Based on the base station information, establish the base station information set U (a large set of all tourism industry base stations), (where i = 1, 2...m) represents the base stations for tourist attractions classification, for example: U1 represents natural attractions, U2 represents cultural attractions, U3 represents historical sites, etc., and m represents the total number of classifications of attractions; assuming that the attractions are scattered and the base station sets of each attraction do not have intersections, then (a≠b, and a <m,b<m)。

[0040] ②For a certain category of attractions U i (U i Indicates a complete collection of a specific category of attractions) (where j = 1, 2...n) represents the classification of scenic spot base station set for specific location scenic spots, for example: S1 represents Huangshan, S2 represents Taishan, S3 represents Wuyishan, etc. It can be expressed as the Taishan scenic spot base station set is a subset of natural scenic spots, n represents the total number of specific scenic spots under a certain scenic spot classification, assuming that the scenic spots are dispersed, then (a≠b, and a <n,b<n)。

[0041] ③For S j ={x1, x2, ..x p} represents a specific scenic spot base station set, element x k ∈S j Indicates the specific base station of the scenic spot, and p indicates the number of base stations associated with the specific scenic spot. It can be represented as x2 base stations in the Taishan Tourist Area under the natural attractions of the tourism industry.

[0042] According to the above data structure, the data can be constructed into a three-dimensional array, U[][][] (U[0][1][1] represents natural attractions, Mount Tai tourist area, x2 base station data). If you need to calculate the total travel time of a person in a certain time interval, you can use a certain time interval condition to filter the travel base station set. and (There is no intersection time between scenic spot base stations), then the calculation can be done as follows:

[0043] (1) Total travel time .time (here T represents the calculated total travel time of the user in a certain time interval, and U[i][j][k].time represents the specific base station access time).

[0044] (2) Attraction type and travel time time (i=1,2,...m) T1: time spent on natural attractions, T2: time spent on cultural attractions, T3: time spent on historical sites, m represents the total number of scenic spots classified; U i [j][k].time indicates the total time of the tourist attraction type.

[0045] (3) Find the short-term switching time of tourist users to adjacent attractions, and roughly calculate the user's travel speed. Specifically, the base station distance Dis(x i ,x j )(represents x i Base station to x j distance between base stations), calculate the time interval Tim (t i ,t j )(indicates t i Leave x i Base station time, t j Enter x j ), based on the above data, we can roughly calculate the user speed V = Dis (x i ,x j ) / Tim(t i ,t j ).

[0046] (4) Entering and leaving In(x) through the base station i ) calculates the time, obtains the attribute value; compares the attribute value with the threshold, and obtains the label

[0047] Through the above calculations, we set the relevant labels based on the total travel time threshold θ(t), set the preference labels based on the travel type ratio θ(p), set the labels based on the speed thresholds θ(v1) and θ(v2), and set the labels based on v1>v2. We also set the group labels based on the time threshold θ(ts) from the time a scenic spot connects to the base station to the time it leaves. The labels are set as follows:

[0048] In this way, the attribute value of the user is calculated based on the user equipment information and the corresponding base station information of the user; the attribute value is compared with a predetermined threshold to determine the user classification.

[0049] In some embodiments, a semi-supervised support vector machine (TSVM) algorithm can be used to obtain common attribute labels of the user sample label data set. For example, by accessing the cultural tourism system, selecting given labels obtained from base station rule data (preference type: natural scenery, cultural tourism, rest and vacation; mode of transportation: self-driving, group tour; hiking; age structure: elderly, middle-aged, young), the network is trained for the labeled data divided by the above small amount of data and the large amount of unlabeled user data of the cultural tourism system. First, a Teacher model is trained with (smaller-scale) labeled data, and then this model is used to predict pseudo-labels for (larger-scale) unlabeled data as training data for the Student model; the advantage of this method is that it can greatly reduce the training work.

[0050] The model is trained by minimizing an objective function between labeled and unlabeled data. The semi-supervised support vector machine (TSVM) algorithm is used. The core idea of ​​TSVM is to train an initial SVM using a labeled sample set. This learner is then used to label unlabeled samples, so that all samples are labeled. The SVM is then retrained based on these labeled samples, and then error-prone samples are identified for continuous adjustment. This can be expressed as the following formula (1):

[0051] Among them, Loss represents the loss value, ω represents the normal vector on the plane, b represents the distance from the hyperplane to the origin, l is the number of label sample sets, (ω, b) determines a partitioning hyperplane, Represents the attribute tag, C l and C u Respectively represent the trade-off parameters specified by the user for balancing the importance of labeled samples and unlabeled samples in the model complexity, m represents the total number of users, and i is a positive integer. The following mathematical formulas ② and ③ are given a labeled sample set D l and the unlabeled sample set D u : D l ={(x1,y1),(x2,y2),...(x l ,y l )} ② Du ={x l+1 ,x l+2 ,...x l+U} ③

[0052] Where l<<u means that the labeled sample set contains very few examples relative to the number of unlabeled samples. l is the number of labeled sample sets, u is the number of unlabeled sample sets, x represents user information, y represents attribute labels, and l+u is the total number of users.

[0053] In particular, semi-supervised learning of user profiles using a small number of labeled examples provided by base stations can produce user profiles that do not conform to actual conditions. For example, tour guides may be labeled as travel enthusiasts, scenic area staff may be labeled with various labels, and drivers working in scenic areas may be labeled as self-driving. Here, we use example-based inductive learning to cleanse user profile data.

[0054] As shown in step 110 , the message body to be sent is pushed to the user device, that is, according to the common attribute tag, the message body to be sent is pushed to the user devices in the target device set.

[0055] In some embodiments, a message push decision tree is generated. Therefore, using the decision tree rules, a portion of user devices in the target device set is selected; the to-be-sent message body is pushed to these user devices, enabling the message content to be more accurately and effectively pushed to the public who are likely to have corresponding needs, or to a pre-selected specific group.

[0056] The specific implementation steps are: obtain the sample table through the data of the cultural and tourism system, and define the attribute values. The attributes here include weather attributes, time attributes, scenic spot attributes, etc., with whether to travel as the goal. The sample table can be as follows (a simple example, not a real business attribute).

[0057] The decision tree learning strategy is designed as a greedy search strategy (used to minimize the depth of the tree); in other words, it determines which attributes in the channel model need to be learned by taking the entropy value of the attribute.

[0058] Entropy is a measure of the uncertainty of a random variable. The entropy value can be used to determine whether an attribute should be used as a learning attribute. See the attribute entropy formula ④:

[0059] Variable Description: Random variable V has value V k , V k The probability of P(V k ), k is a positive integer. The smaller the value calculated by this definition, the more certain the information is. For example learning, certain transactions do not need to be learned.

[0060] At the same time, the information gain is calculated by the attributes defined by the sample, as well as the calculated entropy value and information entropy (attribute entropy and positive example information entropy are obtained according to the entropy formula). The calculation formula ⑤ is: IG(Y|X)=H(Y)-H(Y|X) ⑤

[0061] Where IG(Y|X) is the information gain, H(Y) is the entropy of attribute Y, and H(Y|X) is the entropy of attribute X (positive example) of attribute Y. The node with the highest information gain is selected as the priority node in the decision tree. Through example-based learning of the decision tree, a decision tree is ultimately generated, as shown in Figure 2. When a user accesses a scenic spot base station, the generated decision tree rules determine whether to send a message based on the current weather and the scenic spot's operating status. If the decision tree reaches the "invalid" leaf node according to the rules, the message will not be sent to the user who accessed the base station. If the decision tree reaches the "valid" leaf node according to the rules, the message will be sent.

[0062] FIG3 shows a schematic diagram of an apparatus 200 for targeted message push in a cultural and tourism system according to an exemplary embodiment of the present application. The apparatus 200 for targeted message push in a cultural and tourism system comprises an information capture unit 202 for acquiring base station information and currently connected user device information from a base station; a query unit 204 for querying whether the user device information is in the cultural and tourism system, and if so, setting a tag for the user device information; a message body generation unit 206 for constructing a target device set based on the user device information with the tag set and the corresponding base station information; and constructing a message body to be sent for each user device in the target device set. The construction method of the message body to be sent includes: obtaining a common attribute tag of the user portrait of each user device in the target device set; obtaining service data corresponding to the message body to be sent based on the common attribute tag; and a message push unit 208 for pushing the message body to be sent to the user devices in the target device set based on the common attribute tag.

[0063] Figure 4 shows a schematic diagram of a communication terminal device 300 according to an exemplary embodiment of the present application. Communication terminal device 300 may include: at least one processor 302; and at least one memory 304 including computer program code. The at least one memory 304 and computer program code 306 are configured to utilize the at least one processor 302 to cause communication terminal device 300 to execute: The communication terminal device may implement the steps of the method for targeted message push in a cultural tourism system according to the aforementioned embodiment of the present application.

[0064] The present application also discloses a computer-readable storage medium, which stores a computer program. The computer program can implement the steps of the method for targeted message push of the cultural and tourism system in the above embodiment of the present application.

[0065] The present application also discloses an electronic device, comprising: a memory for storing a computer program product; a processor for executing the computer program product stored in the memory, and when the computer program product is executed, the electronic device can implement the steps of the method for targeted message push of the cultural and tourism system in the above embodiment of the present application.

[0066] The processor may be a central processing unit (CPU) or other forms of processing units having data processing capabilities and / or instruction execution capabilities, and may control other components in the electronic device to perform desired functions.

[0067] The memory may include one or more computer program products, which may include various forms of computer-readable storage media, such as volatile memory and / or non-volatile memory. The volatile memory may include, for example, random access memory (RAM) and / or cache memory. The non-volatile memory may include, for example, read-only memory (ROM), a hard disk, a flash memory, etc. One or more computer program instructions may be stored on the computer-readable storage medium, and the processor may execute the program instructions to implement the task generation method of each embodiment of the present application described above and / or other desired functions.

[0068] In one example, the electronic device may further include an input device and an output device, and these components are interconnected via a bus system and / or other forms of connection mechanisms (not shown).

[0069] In addition, the input device may also include, for example, a keyboard, a mouse, and the like.

[0070] The output device can output various information to the outside, including determined distance information, direction information, etc. The output device can include, for example, a display, a speaker, a printer, a communication network and a remote output device connected thereto, and the like.

[0071] Of course, for the sake of simplicity, this application only shows some of the components in the electronic device that are relevant to this application, omitting components such as buses, input / output interfaces, etc. In addition, the electronic device may further include any other appropriate components depending on the specific application.

[0072] In addition to the above-mentioned methods and devices, an embodiment of the present application may also be a computer program product, which includes computer program instructions, which, when executed by a processor, enable the processor to execute the steps of the task generation method according to various embodiments of the present application described in the above part of this specification.

[0073] The computer program product may be written in any combination of one or more programming languages ​​to implement the program code for performing the operations of the embodiments of the present application, including object-oriented programming languages ​​such as Java, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user's computing device, partially on the user's computing device, as a standalone software package, partially on the user's computing device and partially on a remote computing device, or entirely on a remote computing device or server.

[0074] In addition, an embodiment of the present application may also be a computer-readable storage medium having computer program instructions stored thereon, which, when executed by a processor, enables the processor to execute the steps of the task generation method according to various embodiments of the present application described in the above part of this specification.

[0075] The computer-readable storage medium can adopt any combination of one or more readable media. The readable medium can be a readable signal medium or a readable storage medium. The readable storage medium can, for example, include but is not limited to a system, device or component of electricity, magnetism, light, electromagnetic, infrared, or semiconductor, or any combination thereof. More specific examples (non-exhaustive list) of readable storage media include: an electrical connection with one or more wires, a portable disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof.

[0076] Those skilled in the art will understand that all or part of the steps of implementing the above-mentioned method embodiment can be completed by hardware related to program instructions, and the aforementioned program can be stored in a computer-readable storage medium. When the program is executed, it executes the steps of the above-mentioned method embodiment; and the aforementioned storage medium includes: ROM, RAM, disk or optical disk, etc. Various media that can store program codes.

[0077] The basic principles of the present application have been described above in conjunction with specific embodiments. However, it should be noted that the advantages, strengths, and effects mentioned in this application are merely illustrative and not restrictive, and it should not be assumed that these advantages, strengths, and effects are required of each embodiment of this application. In addition, the specific details disclosed above are merely illustrative and facilitating understanding, and are not restrictive. The above details do not limit this application to necessarily being implemented using the above specific details.

[0078] The above description is merely a preferred embodiment of the present application and is not intended to limit the present application. Various modifications and variations are possible for those skilled in the art. Any modifications, equivalent substitutions, or improvements made within the spirit and principles of the present application shall be included within the scope of protection of the present application.

Claims

1. A method for targeted message push in a cultural tourism system, characterized in that: include: Acquire base station information and currently connected user equipment information from the base station; querying whether the user device information is in the cultural and travel system, and if the user device information is in the cultural and travel system, setting a tag for the user device information; Constructing a target device set according to the user device information with set tags and the corresponding base station information; A message body to be sent is constructed for each user device in the target device set. The construction method of the message body to be sent includes: obtaining a common attribute tag of a user portrait of each user device in the target device set, including: Classifying users in the target device set to form a user sample label data set; A semi-supervised support vector machine (TSVM) algorithm is used to obtain common attribute labels of the user sample label data set; The semi-supervised support vector machine TSVM algorithm is: Among them, Loss represents the loss value, ω represents the normal vector on the plane, b represents the distance from the hyperplane to the origin, l is the number of label sample sets, (ω, b) determines a partitioning hyperplane, Represents the attribute tag, C l and C u They represent the trade-off parameters of the importance of labeled samples and unlabeled samples specified by the user to balance the complexity of the model, m represents the total number of users, and i is a positive integer; Cleaning some of the user portraits; According to the common attribute tag, obtaining service data corresponding to the message body to be sent; According to the common attribute tag, the message body to be sent is pushed to user devices in the target device set.

2. The method for targeted message push in a cultural tourism system according to claim 1, characterized in that: The user sample label data set includes: a labeled data set and an unlabeled data set.

3. The method for targeted message push in a cultural tourism system according to claim 1, characterized in that: Classifying users in the target device set further includes: Calculating the attribute value of the user according to the user equipment information of the user and the corresponding base station information when the user enters and leaves the base station; The attribute value is compared with a predetermined threshold to determine the user classification.

4. The method for targeted message push in a cultural tourism system according to claim 1, characterized in that: Pushing the message body to be sent to the user equipment in the target equipment set further includes: Selecting the user device in the target device set by using a decision tree rule; Push the message body to be sent to the selected user equipment.

5. The method for targeted message push in a cultural tourism system according to claim 4, characterized in that: The decision tree rule adopts a greedy search strategy, and the attribute entropy algorithm is: Where V represents a random variable, P(V k ) indicates V k The probability of k is a positive integer.

6. A device for directional message push in a cultural tourism system, characterized in that: include: An information acquisition unit, used to acquire base station information and currently connected user equipment information from the base station; A query unit, used for querying whether the user equipment information is in the cultural travel system, and if the user equipment information is in the cultural travel system, setting a tag for the user equipment information; A message body generating unit, used for executing the construction of a target device set according to the user equipment information with set tags and the corresponding base station information; A message body to be sent is constructed for each user device in the target device set. The construction method of the message body to be sent includes: obtaining a common attribute tag of a user portrait of each user device in the target device set, including: Classifying users in the target device set to form a user sample label data set; A semi-supervised support vector machine (TSVM) algorithm is used to obtain common attribute labels of the user sample label data set; The semi-supervised support vector machine TSVM algorithm is: Among them, Loss represents the loss value, ω represents the normal vector on the plane, b represents the distance from the hyperplane to the origin, l is the number of label sample sets, (ω, b) determines a partitioning hyperplane, Represents the attribute tag, C l and C u They represent the trade-off parameters of the importance of labeled samples and unlabeled samples specified by the user to balance the complexity of the model, m represents the total number of users, and i is a positive integer; Cleaning some of the user portraits; According to the common attribute tag, obtaining service data corresponding to the message body to be sent; A message pushing unit is used to push the message body to be sent to user devices in the target device set according to the common attribute tag.

7. A communication terminal device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the steps of the method for targeted message push of a cultural and tourism system as described in any one of claims 1 to 5 are implemented.

8. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of the method for targeted message push of a cultural and tourism system as described in any one of claims 1 to 5 are implemented.

9. An electronic device, characterized in that: include: a memory for storing a computer program product; The processor is used to execute the computer program product stored in the memory, and when the computer program product is executed, the steps of the method for targeted message push of the cultural and tourism system described in any one of claims 1 to 5 are implemented.

Images