Recognition method and device for visit of recreational and sports facilities and electronic equipment

Abstract

The embodiment of the invention discloses a recognition method and device for visit of a recreational and sports facility and electronic equipment, belongs to the technical field of data analysis, and can improve the recognition accuracy of the visit of the recreational and sports facility. Comprising the following steps: acquiring user signaling data provided by an operator, the user signaling data comprising user position information of a user connected with a base station through a mobile device and time information of a user moving track; determining a target recreation and sports facility according to user position information in the user signaling data; based on the user signaling data and the target literary and sports facility, a multi-dimensional feature set is determined, and the multi-dimensional feature set comprises spatial features of position association between the user and the target literary and sports facility, time sequence features of the user visiting the target literary and sports facility, user attribute features of user behavior preferences, and facility attribute features of construction conditions of the target literary and sports facility; and inputting a feature map formed by the multi-dimensional feature set into the trained space-time prediction model, and outputting a visiting result of the user to the target literary and sports facility through the space-time prediction model.

Description

Technical Field

[0001] This application relates to the technical field of data analysis, and in particular, to a method, apparatus, and electronic device for identifying visits to cultural and sports facilities. Background Art

[0002] With the promotion and upgrade of life service industries such as health, elderly care, culture, tourism, and sports towards high quality and diversification, the deployment of cultural and sports service facilities closely related to them is crucial.

[0003] In the related art, for the detection of cultural and sports facilities, the usage situation of cultural and sports facilities is usually determined by collecting mobile phone signaling data of users. However, mobile phone signaling data only obtains the location information of users when connecting to the base station, and the obtained data is relatively one-sided, and cannot accurately identify the visits of users to cultural and sports facilities, resulting in a problem of low accuracy in identifying visits to cultural and sports facilities, and unable to accurately optimize the deployment of cultural and sports facilities. Summary of the Invention

[0004] The purpose of the embodiments of this application is to provide a method, apparatus, and electronic device for identifying visits to cultural and sports facilities, so as to solve the problem of low accuracy in identifying visits to cultural and sports facilities.

[0005] To solve the above technical problems, the embodiments of this application are implemented as follows:

[0006] In a first aspect, the embodiments of this application provide a method for identifying visits to cultural and sports facilities, including: obtaining user signaling data provided by an operator, where the user signaling data includes: user location information and time information of the user's movement trajectory when the user is connected to a base station through a mobile device; determining a target cultural and sports facility according to the user location information in the user signaling data; determining a multi-dimensional feature set based on the user signaling data and the target cultural and sports facility, where the multi-dimensional feature set includes: spatial features of the location association between the user and the target cultural and sports facility, temporal features of the user's visit to the target cultural and sports facility, user attribute features of the user's behavior preferences, and facility attribute features of the construction situation of the target cultural and sports facility; inputting a feature map formed by the multi-dimensional feature set into a trained spatio-temporal prediction model, and outputting, through the spatio-temporal prediction model, the visit result of the user to the target cultural and sports facility, where the visit result is used to optimize the deployment of the target cultural and sports facility.

[0007] Second aspect, an embodiment of the present application provides a recognition device for the visit to a cultural and sports facility, including: an acquisition module, configured to acquire user signaling data provided by an operator, where the user signaling data includes: user location information and time information of the user's movement trajectory connected by a mobile device and a base station; a positioning module, configured to determine a target cultural and sports facility according to the user location information in the user signaling data; a determination module, configured to determine a multi-dimensional feature set based on the user signaling data and the target cultural and sports facility, where the multi-dimensional feature set includes: a spatial feature of the location association between the user and the target cultural and sports facility, a timing feature of the user's visit to the target cultural and sports facility, a user attribute feature of the user's behavior preference, and a facility attribute feature of the construction status of the target cultural and sports facility. A prediction module, configured to input a feature map formed by the multi-dimensional feature set into a trained spatio-temporal prediction model, and output, through the spatio-temporal prediction model, a visit result of the user to the target cultural and sports facility, where the visit result is used to optimize the deployment of the target cultural and sports facility.

[0008] Third aspect, an embodiment of the present application provides an electronic device, including a processor and a memory electrically connected to the processor, where the memory stores a computer program, and the processor is configured to call and execute the computer program from the memory to implement the above-mentioned recognition method for the visit to a cultural and sports facility.

[0009] Fourth aspect, an embodiment of the present application provides a computer-readable storage medium for storing a computer program, where the computer program can be executed by a processor to implement the above-mentioned recognition method for the visit to a cultural and sports facility.

[0010] Fifth aspect, an embodiment of the present application provides a chip, where the chip includes a processor and a communication interface, the communication interface is coupled to the processor, and the processor is configured to run a program or an instruction to implement the above-mentioned recognition method for the visit to a cultural and sports facility.

[0011] Sixth aspect, an embodiment of the present application provides a computer program product, where the computer program product includes a computer program, and when the computer program is executed by a processor, it implements the above-mentioned recognition method for the visit to a cultural and sports facility.

[0012] Adopt the technical solution of the embodiment of the present application to obtain the user signaling data provided by the operator. The user signaling data includes: the user location information where the user is connected to the base station through the mobile device and the time information of the user's movement trajectory; determine the target cultural and sports facilities according to the user location information in the user signaling data; based on the user signaling data and the target cultural and sports facilities, determine the multi-dimensional feature set. The multi-dimensional feature set includes: the spatial feature of the location association between the user and the target cultural and sports facilities, the temporal feature of the user's visit to the target cultural and sports facilities, the user attribute feature of the user's behavior preference, and the facility attribute feature of the construction situation of the target cultural and sports facilities; input the feature map formed by the multi-dimensional feature set into the trained spatio-temporal prediction model, and through the spatio-temporal prediction model, output the visit result of the user to the target cultural and sports facilities. The visit result is used to optimize the deployment of the target cultural and sports facilities. It can be seen that through the user signaling data, the user location information can be obtained, and then the target cultural and sports facilities can be determined. According to the user signaling data and the target cultural and sports facilities, the spatial feature of the location association between the user and the target cultural and sports facilities, the temporal feature of the user's visit to the target cultural and sports facilities, the user attribute feature with the user's personal preference, and the facility attribute feature of the construction situation of the target cultural and sports facilities are combined as the multi-dimensional feature set. The feature map of the multi-dimensional feature set is input into the trained spatio-temporal prediction model, and the visit result of the user to the target cultural and sports facilities is output. Through the enhanced processing of the user signaling data, combined with the features of the user and the target cultural and sports facilities, the situation of the user's visit to the target cultural and sports facilities is analyzed in multiple dimensions, making the visit result identified by the spatio-temporal prediction model more accurate, and accurately optimizing the deployment of the target cultural and sports facilities according to the identified visit result, so as to solve the problem of low accuracy in identifying the visit to cultural and sports facilities. Brief Description of the Drawings

[0013] In order to more clearly illustrate the technical solutions in one or more embodiments of the present application or the prior art, the following will briefly introduce the drawings required for the description of the embodiments or the prior art. Obviously, the drawings in the following description are only some embodiments recorded in one or more embodiments of the present application. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained according to these drawings.

[0014] Figure 1 It is a schematic flowchart of a method for identifying the visit to cultural and sports facilities according to an embodiment of the present application;

[0015] Figure 2 It is a schematic structural diagram of the feature map of the multi-dimensional feature set according to an embodiment of the present application;

[0016] Figure 3 It is a schematic diagram of the spatio-temporal prediction model to be trained according to an embodiment of the present application;

[0017] Figure 4It is a schematic flowchart of a method for identifying visits to cultural and sports facilities according to another embodiment of the present application;

[0018] Figure 5 It is a schematic block diagram of a device for identifying visits to cultural and sports facilities according to an embodiment of the present application;

[0019] Figure 6 It is a schematic diagram of the hardware structure of a device for identifying visits to cultural and sports facilities according to an embodiment of the present application. Detailed implementation manners

[0020] Embodiments of the present application provide a method, a device, an electronic device, and a storage medium for identifying visits to cultural and sports facilities, so as to solve the problem of low accuracy in identifying visits to cultural and sports facilities.

[0021] In order to enable those skilled in the art to better understand the technical solutions in the present application, the following will clearly and completely describe the technical solutions in the embodiments of the present application with reference to the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present application.

[0022] The method for identifying visits to cultural and sports facilities provided by the embodiments of the present application can be executed by an electronic device or by software installed in the electronic device. Specifically, the electronic device can be a terminal device or a server device. Among them, the terminal device can include a smart phone, a laptop computer, a smart wearable device, a vehicle-mounted terminal, etc., and the server device can include an independent physical server, a server cluster composed of multiple servers, or a cloud server capable of performing cloud computing.

[0023] The following will, with reference to the accompanying drawings, describe in detail a method for identifying visits to cultural and sports facilities provided by the embodiments of the present application through specific embodiments and their application scenarios.

[0024] Figure 1 A schematic flowchart of a method for identifying visits to cultural and sports facilities provided by an embodiment of the present invention is shown. The method includes the following steps:

[0025] S102, Obtain user signaling data provided by an operator.

[0026] The user signaling data includes: user location information where the user is connected to a base station through a mobile device and time information of the user's movement trajectory.

[0027] The mobile device can be a device such as a mobile phone or a computer that a user can carry with them. Among them, the corresponding user signaling data can be the user's mobile phone signaling data, and the operator is the provider of network services.

[0028] User location information refers to the location information of the user determined by the user's connection with the base station through the mobile device, such as the user's place of residence, the user's place of work, and the location where the user moves.

[0029] The time information of the user's movement trajectory refers to the movement trajectory generated by the user when moving after establishing a network connection with the base station, which will change over time. The user signaling data can record the user's movement trajectory and the corresponding time information.

[0030] S104, determine the target cultural and sports facility according to the user location information in the user signaling data.

[0031] Cultural and sports facilities include public service facilities for culture and sports. The target cultural and sports facility is the cultural and sports facility to judge whether the user has visited, such as a library, a stadium, or outdoor sports facilities.

[0032] Specifically, according to the user location information in the user signaling data, the user's current location information can be determined. When determining the target cultural and sports facility, generally, the user will choose a cultural and sports facility that is closer to the user's place of residence or work, or a facility that is far away but has a good reputation as the target cultural and sports facility to be visited.

[0033] S106, determine the multi-dimensional feature set based on the user signaling data and the target cultural and sports facility. The multi-dimensional feature set includes: the spatial feature of the location association between the user and the target cultural and sports facility, the temporal feature of the user's visit to the target cultural and sports facility, the user attribute feature of the user's behavior preference, and the facility attribute feature of the construction situation of the target cultural and sports facility.

[0034] The multi-dimensional feature set contains data with multiple features or variables, and each feature can describe an aspect of the data object.

[0035] Through the user signaling data, the user's location information can be determined. By determining the target cultural and sports facility, the location of the target cultural and sports facility can be obtained. According to the location relationship between the user and the target cultural and sports facility, the spatial feature can be determined. For example, the range and stay time of the user's visit to the target cultural and sports facility, etc.; through the user signaling data, the time rule of the user's visit to the target cultural and sports facility can also be determined, and this time rule is determined as the temporal feature; according to the user's behavior preference, the user attribute feature can be determined; by determining the target cultural and sports facility, the corresponding construction situation of the target cultural and sports facility can be obtained as the facility attribute feature, such as the venue type and venue area of the target cultural and sports facility.

[0036] By taking a set of multiple features as a multi-dimensional feature set, it is possible to enhance the acquisition of the content of user signaling data, and combine the user's personal characteristics and the uniqueness of the target sports and cultural facilities to improve the accuracy of subsequent identification of the user's visit to the target sports and cultural facilities.

[0037] S108. Input the feature map formed by the multi-dimensional feature set into the trained spatio-temporal prediction model. Through the spatio-temporal prediction model, output the visit result of the user to the target sports and cultural facilities, and the visit result is used to optimize the deployment of the target sports and cultural facilities.

[0038] The feature map refers to the important features extracted from the multi-dimensional feature set through a neural network.

[0039] The spatio-temporal prediction model includes a model of a channel convolutional neural network and a recurrent neural network with an attention mechanism, and is used to identify the feature map corresponding to the input user.

[0040] Convert the multi-dimensional feature set into a feature map, input the feature map into the trained spatio-temporal prediction model, and through the attention mechanism in the spatio-temporal prediction model, output the visit result of the user to the target sports and cultural facilities.

[0041] The visit result includes: the access situation of the user to the target sports and cultural facilities, which can also be the number of times the user visits the target sports and cultural facilities, and can also include outputting the construction characteristics of the target sports and cultural facilities based on the access situation of the user to the target sports and cultural facilities, etc., without specific limitation. According to the visit result, optimize the deployment of the target sports and cultural facilities.

[0042] Adopt the technical solution of the embodiment of the present application to obtain user signaling data provided by an operator. The user signaling data includes: user location information where the user is connected to a base station through a mobile device and time information of the user's movement trajectory; determine a target cultural and sports facility according to the user location information in the user signaling data; based on the user signaling data and the target cultural and sports facility, determine a multi-dimensional feature set. The multi-dimensional feature set includes: spatial features of the location association between the user and the target cultural and sports facility, temporal features of the user's visit to the target cultural and sports facility, user attribute features of the user's behavior preferences, and facility attribute features of the construction situation of the target cultural and sports facility; input the feature map formed by the multi-dimensional feature set into a trained spatio-temporal prediction model, and through the spatio-temporal prediction model, output the user's visit result to the target cultural and sports facility. The visit result is used to optimize the deployment of the target cultural and sports facility. It can be seen that user location information can be obtained through user signaling data, and then the target cultural and sports facility can be determined. According to the user signaling data and the target cultural and sports facility, combine the spatial features of the location association between the user and the target cultural and sports facility, the temporal features of the user's visit to the target cultural and sports facility, the user attribute features with the user's personal preferences, and the facility attribute features of the construction situation of the target cultural and sports facility as a multi-dimensional feature set. Input the feature map of the multi-dimensional feature set into a trained spatio-temporal prediction model, output the user's visit result to the target cultural and sports facility. Through the enhanced processing of user signaling data, combined with the features of the user and the target cultural and sports facility, analyze the user's visit to the target cultural and sports facility in multiple dimensions, make the visit result identified by the spatio-temporal prediction model more accurate, and accurately optimize the deployment of the target cultural and sports facility according to the identified visit result, so as to solve the problem of low accuracy in identifying the visit to cultural and sports facilities.

[0043] In one embodiment, the multi-dimensional feature set includes spatial features of the location association between the user and the target cultural and sports facility; according to the user signaling data and the target cultural and sports facility, determine the multi-dimensional feature set (i.e., S106), and the following steps A1 - A6 can be executed:

[0044] Step A1, calculate the distance between the user and the target cultural and sports facility according to the user location information in the user signaling data.

[0045] For the use of cultural and sports facilities, users usually choose facilities that are closer to their permanent residence or facilities with a certain reputation and word-of-mouth within their activity range. The user location information can be the user's place of residence or work, or the user's location on the way to play, etc. The distance between the user location information and the cultural and sports facility largely reflects the user's play intention.

[0046] Determine the longitude and latitude of the user's location based on the user location information in the user signaling data. Calculate the longitude and latitude of the target cultural and sports facility according to the determined target cultural and sports facility. Determine the distance from the user to the target cultural and sports facility based on the longitude and latitude information of the user and the target cultural and sports facility. The calculation formula for the distance is as shown in Formula 1:

[0047]

[0048] Among them, is the distance from the user to the target cultural and sports facility, R is the radius of the earth, lat and lng are the central longitude and latitude within the range of the target cultural and sports facility, and are the longitude and latitude of the location where user i is located. The distance from the user to the target cultural and sports facility is the distance from the user's usual location to the target cultural and sports facility. The usual location includes the place of residence or work, and can also be the location where the user often passes by, etc.

[0049] Step A2: Determine the extended distance from the user to outside the target cultural and sports facility according to the distance from the user to the target cultural and sports facility.

[0050] When counting the spatial feature information between the user and the target cultural and sports facility, it is also necessary to process the original user signaling data.

[0051] According to the distance from the user to the target cultural and sports facility determined in Step A1, filter the trajectory data of the user within the range between the user's usual location and the target cultural and sports facility in the user signaling data, and determine the trajectory data of the user outside the distance from the user to the target cultural and sports facility. Determine the extended range outside the distance from the user to the target cultural and sports facility as the extended distance from the user to outside the target cultural and sports facility.

[0052] Step A3: Determine the preset range around the target cultural and sports facility according to the distance from the user to the target cultural and sports facility and the extended distance.

[0053] According to Step A2, it can be determined that the distance from the user to the target cultural and sports facility is the distance from the user's place of residence or work to the target cultural and sports facility, and the extended distance is the extended range outside the distance from the user to the target cultural and sports facility. Determine the range of part of the distance from the user to the target cultural and sports facility that is relatively close to the target cultural and sports facility, and the extended distance from the user outside the target cultural and sports facility as the preset range around the target cultural and sports facility. Among them, the preset range can also be the total range of the distance from the user to the target cultural and sports facility and the extended distance from the user outside the target cultural and sports facility.

[0054] The trajectory of the user within the extended distance outside the target cultural and sports facility can be expressed by Formula 2:

[0055] Tra i ={tra i ∈D j∧ (!S j )} Formula 2

[0056] where Tra i represents the user's trajectory within the extended distance, and tra i is all the trajectory data of user i during time period t, D j is the surrounding area within a certain extended distance from the target cultural and sports facility j, and S j is the size of the target cultural and sports facility j. ∧ is the operator of logical symbols, and! represents not belonging to, meaning negation. It can be seen that the user's trajectory within the extended distance includes: among all the user's trajectories, the user's trajectories that belong to the extended range of the target cultural and sports facility but do not belong to the location of the target cultural and sports facility itself.

[0057] Step A4: Based on the user location information and the time information of the user location movement in the user signaling data, determine the moving distance and total staying duration of the user within the preset range.

[0058] The preset range refers to the surrounding area of the target cultural and sports facility. According to the user location information and the time information of the user's movement trajectory in the user signaling data, the specific location of the user at a specific time can be determined. Therefore, the moving distance and total staying duration of the user within the surrounding area of the target cultural and sports facility can be determined.

[0059] Step A5: Based on the moving distance and the corresponding moving time, determine the average roaming speed of the user.

[0060] According to the user's moving distance, determine the moving time corresponding to the moving distance, and perform a division operation on the moving distance and the moving time to obtain the user's average roaming speed.

[0061] Step A6: Determine the spatial features of the location association between the user and the target cultural and sports facility based on the total staying duration and the average roaming speed.

[0062] According to the total staying duration of the user within the preset range determined in step A4 and the average roaming speed of the user determined in step A5, convert the data of the total staying duration and the average roaming speed into corresponding feature vectors, and determine the feature vectors corresponding to the total staying duration and the average roaming speed as the spatial features of the location association between the user and the target cultural and sports facility.

[0063] Among them, the construction of spatial features also includes the user's movement trajectory, the user's workplace, the user's place of residence, the distance between the target cultural and sports facility and the workplace, the distance between the target text facility and the place of residence, the roaming time of the user within the target cultural and sports facility, the roaming distance of the user within the target cultural and sports facility, the roaming speed of the user within the target cultural and sports facility, etc., which are not specifically limited.

[0064] The constructed spatial features can reflect the user's activity range and habits. For example, when the total stay time of the user around the target sports and cultural facility is relatively long, it indicates that the user likes the target sports and cultural facility. When the total stay time of the user around the target sports and cultural facility is relatively short, it can indicate that the user doesn't like the target sports and cultural facility very much. Or, according to the distance between the target text facility and the place of residence, if the distance is far and the user still stays within the preset range of the target sports and cultural facility for a long time and visits the target sports and cultural facility frequently, it can prove that the user likes the target sports and cultural facility more, etc.

[0065] In this embodiment, through the user signaling data and the target sports and cultural facility, the preset range around the target sports and cultural facility where the user is located can be determined, and the activity information data of the user within the preset range can be determined, such as the total stay time and average roaming speed of the user within the preset range, etc. Taking the activity information data as the spatial features of the location association between the user and the target sports and cultural facility can reflect the user's activity range and activity habits.

[0066] In one embodiment, the multi-dimensional feature set further includes the temporal features of the user's visit to the target sports and cultural facility, the user attribute features of the user's behavior preferences, and the facility attribute features of the construction situation of the target sports and cultural facility. According to the user signaling data and the target sports and cultural facility, to determine the multi-dimensional feature set (i.e., S106), the following steps B1 - B3 can be executed:

[0067] Step B1, based on the user signaling data, determine the date type and time period attribute of the user's visit to the target sports and cultural facility, and determine the date type and time period attribute as the temporal features of the user. The date type includes: working days and non-working days, and the time period attribute includes: working hours and non-working hours.

[0068] According to the user's signaling data, determine the user's location information, and according to the time information of the user's movement trajectory, determine the time when the user visits the target sports and cultural facility. Since the personal activity ranges of the user on working days and non-working days, and during working hours and non-working hours on working days are different, therefore, working days and non-working days can be used as the date type, working hours and non-working hours can be used as the time period attribute, and the time when the user visits the target sports and cultural facility can be divided according to the date type and time period attribute to more accurately capture the dynamic changes of the user's behavior pattern.

[0069] Specifically, given the significantly different usage habits of users for the target cultural and sports facilities between weekdays and non-working days, especially on weekends and legal holidays, the public often has more leisure time and tends to participate in physical exercises or enjoy entertainment and leisure activities. In addition, the impact of different time periods within a day on users' access to the target cultural and sports facilities cannot be ignored. During weekdays, due to the limitation of work responsibilities, the personal activity range is usually concentrated in the area between their place of residence and workplace; while during non-working hours, such as in the morning, evening and night, users have greater freedom to plan their daily activities. At this time, people may be more willing to go to cultural and sports venues that are farther away but have more complete facilities or are more attractive.

[0070] Therefore, by performing refined time feature modeling on the date type and time period attributes of users' visits to the target cultural and sports facilities to obtain users' time series features, the arrival tendency of users can be predicted more accurately, thereby optimizing the resource allocation and service supply of the target cultural and sports facilities and enhancing the user experience.

[0071] Step B2: Obtain the user's Internet access information, and based on the Internet access information, determine the user's behavior preferences, and determine the user behavior preferences as the user attribute characteristics.

[0072] The operator can provide user signaling data and can also obtain the corresponding Internet access information of the user. The Internet access information includes: the user's age, gender, occupation, Internet browsing records, family composition, etc. Based on the Internet access information, the user's behavior preferences can be determined, and the personalized user behavior preferences of the user are determined as the user attribute characteristics.

[0073] For example, the user's age can reflect their physical strength level, interests and hobbies, and disposable time; gender differences may lead to different sports and leisure preferences; the type of occupation affects the working hours and locations, and thus affects the time arrangement of leisure activities; by analyzing the user's Internet browsing records and determining the usage of different software, the degree of interest of the user in specific activities can be inferred. For example, users who often use fitness software are more likely to visit fitness venues or outdoor sports venues more frequently. Family composition includes: single, couple, family with children, etc., and will also affect the considerations of users when choosing cultural and sports facility activities.

[0074] The user attribute characteristics can reflect the interests, hobbies and needs of the user, have certain reference value for identifying users' visits to the target cultural and sports facilities, and the personalized behavior patterns can also significantly enhance the prediction ability of the subsequent spatio-temporal prediction model.

[0075] Step B3: According to the target cultural and sports facilities, obtain the construction situation of the target cultural and sports facilities, and determine the construction situation of the target cultural and sports facilities as the facility attribute characteristics of the target cultural and sports facilities.

[0076] The construction status of the target cultural and sports facilities includes information such as the venue type, venue area, and venue development time corresponding to the target cultural and sports facilities. Different types of cultural and sports facilities attract different users. The construction status of the target cultural and sports facilities is determined as the facility attribute characteristics of the target cultural and sports facilities.

[0077] For example, libraries mainly serve reading enthusiasts, while sports fields attract sports enthusiasts. By clarifying the construction status of the target cultural and sports facilities, the type of the target cultural and sports facilities can be determined, which helps to match the interests of users with the functions of the facilities, thereby improving the accuracy of prediction. Larger facilities can usually provide more programs and services, and may also have better equipment and environment, which can attract more users. The area information in the construction status of the target cultural and sports facilities can also evaluate the carrying capacity and attractiveness of the facilities.

[0078] It should be noted that in addition to spatial features, temporal features, user attribute features, and facility attribute features, the multi-dimensional feature set can also include various features. For example, it can also include features such as the influence of users on the people around the target cultural and sports facilities and the charging setting features of the target cultural and sports facilities, which are not specifically limited.

[0079] In this embodiment, the date type and time period attribute of the user's visit to the target cultural and sports facilities are obtained to determine the temporal features of the user. By obtaining the user's Internet information, the user's behavior preferences are determined, and then the user attribute features are determined. The facility attribute features of the target cultural and sports facilities are determined through the construction status of the target cultural and sports facilities. Adding the temporal features, user attribute features, and facility attribute features of the target cultural and sports facilities to the multi-dimensional feature set and considering the personalized features of the user and the uniqueness of the target cultural and sports facilities in multiple dimensions can significantly enhance the prediction ability of the subsequent spatio-temporal prediction model.

[0080] In one embodiment, the feature map formed by the multi-dimensional feature set is input into the trained spatio-temporal prediction model, and through the spatio-temporal prediction model, the arrival result of the user at the target cultural and sports facilities (i.e., S108) is output. The following steps C1 - C2 can be executed:

[0081] Step C1, the multi-dimensional feature set is processed by splicing through a feed-forward artificial neural network to obtain the feature map corresponding to the multi-dimensional feature set.

[0082] In order to make full use of the multi-dimensional feature set, the multi-dimensional feature set is input into a feed-forward artificial neural network. The features in the multi-dimensional feature set are processed by the feed-forward artificial neural network to obtain the personalized feature map of each feature, and the personalized feature maps of each feature are spliced to obtain the feature map corresponding to the multi-dimensional feature set.

[0083] As an example, in order to make full use of the correlation between spatial features, temporal features, user attribute features, and facility attribute features under distance constraints, the spatial features, temporal features, user attribute features, and facility attribute features are respectively processed through a feedforward artificial neural network, such as a Multilayer Perceptron (MLP), to obtain personalized feature maps for each processed feature. The processed personalized feature maps are concatenated to form a feature map corresponding to a multi-dimensional feature set. Specifically, at time t, the feature map G corresponding to the constructed multi-dimensional feature set t can be expressed by the following formula 3:

[0084] G t ={T t ||S t ||P t ||F t} Formula 3

[0085] where T t is the temporal feature at time t, S t is the spatial feature under distance constraints at time t, P t is the user attribute feature, and F t is the facility attribute feature at time t.

[0086] As Figure 2 shown, it is a schematic structural diagram of the feature map of the multi-dimensional feature set. The temporal features include: holidays and working hours; the spatial features under distance constraints include: spatial features determined according to user signaling data; the user attribute features include: user age, preferences, etc.; the facility attribute features include: venue type, venue area, etc. The multi-dimensional feature set is respectively concatenated through the MLP to obtain the feature map of the multi-dimensional feature set.

[0087] Step C2: Input the feature map into the trained spatio-temporal prediction model, and through the attention mechanism of the spatio-temporal prediction model, output the arrival result of the user at the target sports facility.

[0088] Input the feature map into the trained spatio-temporal prediction model. Through the convolutional layer and pooling layer in the channel convolutional neural network of the spatio-temporal prediction model, the input feature map is processed to obtain high-order features. The high-order features are input into the recurrent neural network of the attention mechanism to select and focus on important partial features while ignoring unimportant partial features, and finally output the arrival result of the user at the target sports facility.

[0089] The arrival result can be the user's access situation to the target cultural and sports facility, such as arriving at the target cultural and sports facility or not arriving at the target cultural and sports facility; it can also output the user attribute characteristics and facility attribute characteristics when the user arrives at the target cultural and sports facility, or the user attribute characteristics and facility attribute characteristics of the user when the user does not arrive at the target cultural and sports facility.

[0090] According to the arrival results, summarize the access situations of multiple users to the target cultural and sports facility within a period of time. Based on the access situations, it can be determined whether the established target cultural and sports facility meets the ideal state of the masses, and the target cultural and sports facility can be optimized according to the access results of the users to the target cultural and sports facility, or a new target cultural and sports facility can be established at a suitable location, etc.

[0091] In this embodiment, by converting the multi-dimensional feature set of the user into a feature map and inputting the feature map into the trained spatio-temporal prediction model to predict the arrival result of the user to the target cultural and sports facility, it is possible to identify whether the user arrives at the target cultural and sports facility in multiple dimensions. By improving the accuracy of identifying the user's arrival at the target cultural and sports facility, it is possible to make a clearer judgment on the subsequent deployment of the target cultural and sports facility.

[0092] In one embodiment, the training of the spatio-temporal prediction model can perform the following steps D1-D4:

[0093] Step D1, obtain the sample feature map after splicing the sample multi-dimensional feature sets of multiple sample users, and the arrival situation of the sample users to the sample target cultural and sports facility.

[0094] The sample multi-dimensional feature set includes: the sample spatial feature of the position association between the sample user and the sample target cultural and sports facility, the temporal feature of the sample user arriving at the sample target cultural and sports facility, the sample user attribute feature of the sample user's behavior preference, and the sample facility attribute feature of the construction situation of the sample target cultural and sports facility.

[0095] Specifically, obtain the sample multi-dimensional feature set of the sample user within a historical time period, perform splicing processing on the sample multi-dimensional feature set to obtain a sample feature map. Obtain the arrival situation of the sample user to the sample target cultural and sports facility at the current time, that is, whether the sample user arrives at the sample target cultural and sports facility within the current time period.

[0096] As an example, when identifying the sample target cultural and sports facility visited by the sample user based on the sample user signaling data of the mobile phone, obtain the feature matrix within the historical time period, that is, from time t-T to time t-1, and the feature matrix is the sample feature map.

[0097] Step D2, input the sample feature map into the spatio-temporal prediction model to be trained, and process the sample feature map through the convolutional layer and pooling layer of the spatio-temporal prediction model to be trained to obtain high-order features.

[0098] High-order features are used to capture the complex non-linear relationships between the features of each dimension in the multi-dimensional feature set of samples, improving the prediction ability of the spatio-temporal prediction model.

[0099] Following the example in step D1, after inputting the sample feature map into the spatio-temporal prediction model to be trained, the high-order features of the sample feature map are calculated through the convolutional layer and pooling layer of the spatio-temporal prediction model to be trained. The high-order feature T at time t t is calculated as shown in Equation 4:

[0100] T t = σ(W * G t + b) Equation 4

[0101] where W represents the learnable parameter, * represents the convolutional operator, σ(*) is the ReLU activation function, and G t represents the sample feature map at time t, and b represents a hyperparameter.

[0102] Step D3: Input the high-order features into the attention mechanism of the spatio-temporal prediction model to be trained, and through the attention mechanism, output the sample visit result of the sample user to the sample target cultural and sports facility.

[0103] Input the high-order features processed by the channel convolutional neural network in step D2 into the attention mechanism. Through the recurrent neural network of the attention mechanism, it can select and focus on the important partial features in the input sequence while ignoring the unimportant partial features, effectively capturing important patterns and trends from the time series, and improving the accuracy of the spatio-temporal prediction model to be trained.

[0104] Following the example in step D2, input the obtained high-order features into the attention mechanism for calculation, and output the sample visit result of the sample user to the sample target cultural and sports facility. The sample visit result y at time t t is calculated as shown in Equation 5:

[0105] y t = Sigmoid(W a T t ) Equation 5

[0106] where W a is a trainable weight matrix, Sigmoid represents the activation function, and T t represents the high-order feature of user i at the current time t.

[0107] Following the example in step D1, such as Figure 3As shown in the figure, it is a schematic diagram of the spatio-temporal prediction model to be trained. The feature matrix from time t - T to time t - 1 is obtained to form a feature map, which is input into the spatio-temporal prediction model to be trained. After convolution processing through the convolutional layer, pooling processing through the pooling layer, and the ReLU activation function, high-order features are obtained after processing the feature map. The high-order features are input into the attention mechanism, and finally, the sample arrival result at time t is output through the spatio-temporal prediction model to be trained.

[0108] Step D4: According to the arrival situation and the sample arrival result, train the spatio-temporal prediction model to be trained to obtain the trained spatio-temporal prediction model.

[0109] Continuing with the example in step D3, the loss function of the spatio-temporal prediction model to be trained is defined as shown in Equation 6:

[0110]

[0111] where y is the true label (0 or 1), that is, the true label of the arrival result y t of the arrival result y, that is, if the situation of the sample user arriving at the sample target cultural and sports facility is true, then the label of y is 1; if it is false, that is, the sample user does not arrive at the sample target cultural and sports facility, then the label of y is 0. is the predicted value (usually a probability value), that is, the probability value of whether the sample user of the arrival result y t arrives at the sample target cultural and sports facility is true or false.

[0112] According to the arrival situation and the sample arrival result, through the loss function and using the optimization algorithm (Adaptive Moment Estimation, Adam) optimizer to perform iterative update of the parameters, train the spatio-temporal prediction model to be trained to make the arrival situation and the sample arrival result close or consistent, gradually improve the accuracy of model training, and obtain the trained spatio-temporal prediction model.

[0113] In this embodiment, by obtaining the sample feature maps of multiple sample users and the arrival situations of the sample target cultural and sports facilities corresponding to the multiple sample users, by inputting the sample feature maps into the spatio-temporal prediction model to be trained, through the convolutional layer and the pooling layer in the spatio-temporal prediction model to be trained, high-order features corresponding to the sample feature maps are obtained, and after being processed by the attention mechanism, the sample arrival result is output. Using the loss function and the Adam optimizer, train the spatio-temporal prediction model to be trained to obtain the trained spatio-temporal prediction model, which can use the trained spatio-temporal prediction model to predict the arrival situation of users at the target cultural and sports facilities and improve the accuracy of user arrival recognition at the target cultural and sports facilities.

[0114] In one embodiment, after obtaining the trained spatio-temporal prediction model (i.e., step D4), the following steps E1 - E2 can be executed:

[0115] Step E1: Determine the evaluation metrics for the sample visit results based on the visit situations and sample visit results of multiple sample users. The evaluation metrics include one or more of the accuracy rate, hit rate, recall rate, and mean square error of the sample users accessing the sample target cultural and sports facilities.

[0116] Using the trained spatio-temporal prediction model, take the visit situations of multiple sample users as the true values, and take the sample visit results output by the trained spatio-temporal prediction model as the predicted values, and calculate the evaluation metrics for the sample visit results. The evaluation metrics are used to evaluate the accuracy of the output results of the trained spatio-temporal prediction model.

[0117] Specifically, TP represents the number of correctly predicted positive classes, that is, the situation where the sample visit result output by the trained spatio-temporal prediction model is a visit and the prediction is correct; TN represents the number of correctly predicted negative classes, that is, the situation where the sample visit result output by the trained spatio-temporal prediction model is not a visit and the prediction is correct; FP represents the number of incorrectly predicted positive classes, that is, the situation where the sample visit result output by the trained spatio-temporal prediction model is a visit and the prediction is incorrect; FN represents the number of incorrectly predicted negative classes, that is, the situation where the sample visit result output by the trained spatio-temporal prediction model is not a visit and the prediction is incorrect.

[0118] Then, the calculation method of the accuracy rate of the sample users accessing the sample target cultural and sports facilities in the evaluation metrics is shown in Formula 7:

[0119]

[0120] The calculation method of the hit rate of the sample users accessing the sample target cultural and sports facilities in the evaluation metrics is as follows

[0121] shown in Formula 8:

[0122]

[0123] The calculation method of the recall rate of the sample users accessing the sample target cultural and sports facilities in the evaluation metrics is as follows

[0124] shown in Formula 9:

[0125]

[0126] The above accuracy rate, hit rate, and recall rate are particularly applicable to the evaluation of binary classification problems and can improve the effectiveness of the trained spatio-temporal prediction model in identifying positive class cases (that is, users actually accessing the target cultural and sports facilities).

[0127] The mean square error is used to quantify the difference between the predicted values and the observed values, and is particularly suitable for situations where it is necessary to evaluate the accuracy of total quantity or frequency predictions. The predicted data is the sample arrival result output by the trained spatio-temporal prediction model, and the observed value is the actual arrival situation of the sample users at the sample target cultural and sports facilities.

[0128] The calculation method of the accuracy rate of sample users accessing the sample target cultural and sports facilities in the evaluation index is as shown in

[0129] Equation 10:

[0130]

[0131] where n is the number of sample target cultural and sports facilities, and y t is the true value of the i-th sample user's arrival at the sample target cultural and sports facilities; is the predicted value of the i-th sample user's arrival at the sample target cultural and sports facilities. The sample users include one or more, and the sample target cultural and sports facilities also include one or more. The sample users can be the users who train the spatio-temporal prediction model. When using the evaluation index, the sample users can also be the users who use the trained spatio-temporal prediction model. Relatively speaking, the sample target cultural and sports facilities can also be the sample target cultural and sports facilities that use the trained spatio-temporal prediction model, and no specific limitation is made.

[0132] Step E2, evaluate and monitor the trained spatio-temporal prediction model according to the evaluation index.

[0133] Through the evaluation index, the prediction accuracy of the trained spatio-temporal prediction model can be evaluated, and the subsequent use of the trained spatio-temporal prediction model can also be detected. When the situation of the evaluation index is poor, it is necessary to retrain the trained spatio-temporal prediction model to make the evaluation index stable.

[0134] In this embodiment, during the evaluation of the trained spatio-temporal prediction model, the classification prediction performance of whether the sample users access the sample target cultural and sports facilities is measured by using the accuracy rate, hit rate, and recall rate in the evaluation index, and the mean square error is used to evaluate the deviation degree between the total amount of sample users predicted to access the sample target cultural and sports facilities and the actual total amount of sample users accessing the sample target cultural and sports facilities. The performance of the trained spatio-temporal prediction model is evaluated and monitored at all times through the evaluation index.

[0135] Figure 4 is a schematic flowchart of a method for identifying the arrival of cultural and sports facilities according to another embodiment of the present application. As Figure 4 shown, the method includes the following steps:

[0136] S401. Obtain the user signaling data provided by the operator, and determine the target cultural and sports facilities that are closer to the user's location or farther from the user's location but meet the user's needs according to the user location information in the user signaling data.

[0137] The user signaling data includes: the user location information of the connection between the user's mobile device and the base station and the time information of the user's movement trajectory.

[0138] S402. Calculate the distance from the user to the target cultural and sports facilities according to the user location information in the user signaling data, and determine the extended distance outside the target cultural and sports facilities according to the distance from the user to the target cultural and sports facilities.

[0139] S403. Determine the preset range around the target cultural and sports facilities according to the distance from the user to the target cultural and sports facilities and the extended distance, and obtain the total stay duration of the user and the average roaming speed of the user within the preset range.

[0140] S404. Determine the total stay duration and the average roaming speed as the spatial characteristics of the location association between the user and the target cultural and sports facilities.

[0141] S405. Based on the user signaling data, determine the date type and time period attribute of the user's visit to the target cultural and sports facilities, and determine the date type and time period attribute as the temporal characteristics of the user.

[0142] S406. Obtain the user's Internet access information, determine the user's behavior preferences according to the Internet access information, and determine the user's behavior preferences as the user attribute characteristics.

[0143] S407. According to the target cultural and sports facilities, obtain the construction situation of the target cultural and sports facilities, and determine the construction situation of the target cultural and sports facilities as the facility attribute characteristics of the target cultural and sports facilities.

[0144] S408. Take the spatial characteristics of the location association between the user and the target cultural and sports facilities, the temporal characteristics of the user, the user attribute characteristics, and the facility attribute characteristics as a multi-dimensional feature set.

[0145] S409. Perform splicing processing on the multi-dimensional feature set through a feedforward artificial neural network to obtain the feature map corresponding to the multi-dimensional feature set.

[0146] S410. Input the feature map into the trained spatio-temporal prediction model, and output the user's visit result to the target cultural and sports facilities through the attention mechanism of the spatio-temporal prediction model.

[0147] The training process of the spatio-temporal prediction model will not be elaborated here too much.

[0148] S411. Optimize the deployment of the target cultural and sports facilities according to the visit result.

[0149] S412. Use the evaluation metrics to evaluate the performance of the trained spatio-temporal prediction model within a preset time period. If the evaluation metrics do not meet the standards, retrain and adjust the trained spatio-temporal prediction model.

[0150] The specific processes of S401 to S412 above have been described in detail in the above embodiments and will not be repeated here.

[0151] Adopt the technical solution of the embodiment of the present application to obtain the user signaling data provided by the operator. The user signaling data includes: the user location information of the user connected to the base station through the mobile device and the time information of the user's movement trajectory; determine the target cultural and sports facility according to the user location information in the user signaling data; based on the user signaling data and the target cultural and sports facility, determine a multi-dimensional feature set, and the multi-dimensional feature set includes: the spatial feature of the location association between the user and the target cultural and sports facility, the temporal feature of the user's visit to the target cultural and sports facility, the user attribute feature of the user's behavior preference, and the facility attribute feature of the construction situation of the target cultural and sports facility; input the feature map formed by the multi-dimensional feature set into the trained spatio-temporal prediction model, and through the spatio-temporal prediction model, output the user's visit result to the target cultural and sports facility, and the visit result is used to optimize the deployment of the target cultural and sports facility. It can be seen that the user location information can be obtained through the user signaling data, and then the target cultural and sports facility can be determined. According to the user signaling data and the target cultural and sports facility, the spatial feature of the location association between the user and the target cultural and sports facility, the temporal feature of the user's visit to the target cultural and sports facility, the user attribute feature with the user's personal preference, and the facility attribute feature of the construction situation of the target cultural and sports facility are combined as a multi-dimensional feature set. The feature map of the multi-dimensional feature set is input into the trained spatio-temporal prediction model, and the user's visit result to the target cultural and sports facility is output. Through the enhanced processing of the user signaling data and the combination with the features of the user and the target cultural and sports facility, the situation of the user's visit to the target cultural and sports facility is analyzed in multiple dimensions, making the visit result identified by the spatio-temporal prediction model more accurate, and accurately optimizing the deployment of the target cultural and sports facility according to the identified visit result, so as to solve the problem of low accuracy in identifying the visit to the cultural and sports facility.

[0152] In summary, specific embodiments of the present subject matter have been described. Other embodiments are within the scope of the appended claims. In some cases, the actions recited in the claims may be performed in a different order and still achieve the desired result. Additionally, the processes depicted in the figures do not necessarily require the particular order or sequential order shown to achieve the desired result. In certain implementations, multitasking and parallel processing may be advantageous.

[0153] The above is a method for identifying the visit to a cultural and sports facility provided by an embodiment of the present application. Based on the same idea, an embodiment of the present application also provides a device for identifying the visit to a cultural and sports facility.

[0154] Figure 5 It is a schematic structural diagram of an identification device for the visit of a cultural and sports facility according to an embodiment of the present invention. As Figure 5 shown, the identification device for the visit of a cultural and sports facility includes: an acquisition module 51, a positioning module 52, a determination module 53, and a prediction module 54:

[0155] The acquisition module 51 is used to acquire user signaling data provided by an operator, and the user signaling data includes: user location information where the user is connected to a base station through a mobile device and time information of the user's movement trajectory;

[0156] The positioning module 52 is used to determine a target cultural and sports facility according to the user location information in the user signaling data;

[0157] The determination module 53 is used to determine a multi-dimensional feature set based on the user signaling data and the target cultural and sports facility. The multi-dimensional feature set includes: spatial features of the location association between the user and the target cultural and sports facility, temporal features of the user's visit to the target cultural and sports facility, user attribute features of the user's behavior preferences, and facility attribute features of the construction situation of the target cultural and sports facility.

[0158] The prediction module 54 is used to input the feature map formed by the multi-dimensional feature set into a trained spatio-temporal prediction model, and through the spatio-temporal prediction model, output the visit result of the user to the target cultural and sports facility. The visit result is used to optimize the deployment of the target cultural and sports facility.

[0159] In one embodiment, the determination module 53 is used to calculate the distance between the user and the target cultural and sports facility according to the user location information in the user signaling data; determine the extended distance outside the target cultural and sports facility according to the distance between the user and the target cultural and sports facility; determine a preset range around the target cultural and sports facility according to the distance between the user and the target cultural and sports facility and the extended distance; determine the moving distance and total stay duration of the user within the preset range based on the user location information and the time information of the user's location movement in the user signaling data; determine the average roaming speed of the user based on the moving distance and the corresponding moving time; and determine the spatial features of the location association between the user and the target cultural and sports facility by the total stay duration and the average roaming speed.

[0160] In one embodiment, the determination module 53 is specifically further used to determine the date type and time period attribute of the user's visit to the target cultural and sports facility based on the user signaling data, and determine the date type and time period attribute as the temporal features of the user; the date type includes: working days and non-working days, and the time period attribute includes: working hours and non-working hours; obtain the user's Internet access information, and determine the user's behavior preferences according to the Internet access information, and determine the user's behavior preferences as the user attribute features; obtain the construction situation of the target cultural and sports facility according to the target cultural and sports facility, and determine the construction situation of the target cultural and sports facility as the facility attribute features of the target cultural and sports facility.

[0161] In one embodiment, the prediction module 54 is configured to splice the multi-dimensional feature set through a feedforward artificial neural network to obtain a feature map corresponding to the multi-dimensional feature set; input the feature map into the trained spatio-temporal prediction model, and output the arrival result of the user at the target sports facility through the attention mechanism of the spatio-temporal prediction model.

[0162] In one embodiment, the device further includes a training module for training the spatio-temporal prediction model. Specifically, it is configured to obtain the sample feature map after splicing the sample multi-dimensional feature sets of multiple sample users, and the arrival situations of the sample users at the sample target sports facilities; input the sample feature map into the spatio-temporal prediction model to be trained, and process the sample feature map through the convolutional layer and pooling layer of the spatio-temporal prediction model to be trained to obtain high-order features; input the high-order features into the attention mechanism of the spatio-temporal prediction model to be trained, and output the sample arrival results of the sample users at the sample target sports facilities through the attention mechanism; train the spatio-temporal prediction model to be trained according to the arrival situations and the sample arrival results to obtain the trained spatio-temporal prediction model.

[0163] In one embodiment, the training module is further configured to determine the evaluation indicators of the sample arrival results according to the arrival situations and the sample arrival results of multiple sample users. The evaluation indicators include one or more of the accuracy rate, hit rate, recall rate, and mean square error of the sample users accessing the sample target sports facilities; evaluate and monitor the trained spatio-temporal prediction model according to the evaluation indicators.

[0164] Adopting the technical solution of the embodiment of the present application, user signaling data provided by an operator is obtained. The user signaling data includes: user location information where the user is connected to a base station through a mobile device and time information of the user's movement trajectory. Based on the user location information in the user signaling data, a target cultural and sports facility is determined. Based on the user signaling data and the target cultural and sports facility, a multi-dimensional feature set is determined. The multi-dimensional feature set includes: a spatial feature of the location association between the user and the target cultural and sports facility, a temporal feature of the user's visit to the target cultural and sports facility, a user attribute feature of the user's behavior preference, and a facility attribute feature of the construction situation of the target cultural and sports facility. The feature map formed by the multi-dimensional feature set is input into a trained spatio-temporal prediction model, and through the spatio-temporal prediction model, the visit result of the user to the target cultural and sports facility is output. The visit result is used to optimize the deployment of the target cultural and sports facility. It can be seen that through the user signaling data, the user location information can be obtained, and then the target cultural and sports facility can be determined. Based on the user signaling data and the target cultural and sports facility, the spatial feature of the location association between the user and the target cultural and sports facility, the temporal feature of the user's visit to the target cultural and sports facility, the user attribute feature with the user's personal preference, and the facility attribute feature of the construction situation of the target cultural and sports facility are combined as a multi-dimensional feature set. The feature map of the multi-dimensional feature set is input into the trained spatio-temporal prediction model, and the visit result of the user to the target cultural and sports facility is output. Through the enhanced processing of the user signaling data and the combination with the features of the user and the target cultural and sports facility, the situation of the user's visit to the target cultural and sports facility is analyzed multi-dimensionally, making the visit result recognized by the spatio-temporal prediction model more accurate. According to the recognized visit result, the target cultural and sports facility is accurately optimized and deployed, solving the problem of low accuracy in recognizing the visit to the cultural and sports facility.

[0165] Those skilled in the art should understand that Figure 5 the recognition device for the visit to the cultural and sports facility in [specific reference] can be used to implement the recognition method for the visit to the cultural and sports facility described above. The detailed description therein should be similar to the description in the method part above. To avoid redundancy, it will not be elaborated here.

[0166] Based on the same technical concept, the embodiment of the present application also provides an electronic device, which is used to execute the above-mentioned recognition method for the visit to the cultural and sports facility. Figure 6 It is a schematic structural diagram of an electronic device for implementing various embodiments of the present application. The electronic device may vary greatly due to configuration or performance differences. It may include a processor 610, a communication interface 620, a memory 630, and a communication bus 640. Among them, the processor 610, the communication interface 620, and the memory 630 communicate with each other through the communication bus 640. The processor 610 can call a computer program stored in the memory 630 and running on the processor 610 to execute the following steps:

[0167] Obtain user signaling data provided by an operator, where the user signaling data includes: user location information of a user connected to a base station through a mobile device and time information of the user's movement trajectory;

[0168] Determine a target sports and cultural facility according to the user location information in the user signaling data;

[0169] Based on the user signaling data and the target sports and cultural facility, determine a multi-dimensional feature set, where the multi-dimensional feature set includes: spatial features of the location association between the user and the target sports and cultural facility, temporal features of the user's visit to the target sports and cultural facility, user attribute features of the user's behavior preferences, and facility attribute features of the construction situation of the target sports and cultural facility.

[0170] Input the feature map formed by the multi-dimensional feature set into a trained spatio-temporal prediction model, and through the spatio-temporal prediction model, output the user's visit result to the target sports and cultural facility, where the visit result is used to optimize the deployment of the target sports and cultural facility.

[0171] Adopt the technical solution of the embodiment of the present application. Obtain user signaling data provided by an operator, where the user signaling data includes: user location information of a user connected to a base station through a mobile device and time information of the user's movement trajectory; determine a target sports and cultural facility according to the user location information in the user signaling data; based on the user signaling data and the target sports and cultural facility, determine a multi-dimensional feature set, where the multi-dimensional feature set includes: spatial features of the location association between the user and the target sports and cultural facility, temporal features of the user's visit to the target sports and cultural facility, user attribute features of the user's behavior preferences, and facility attribute features of the construction situation of the target sports and cultural facility; input the feature map formed by the multi-dimensional feature set into a trained spatio-temporal prediction model, and through the spatio-temporal prediction model, output the user's visit result to the target sports and cultural facility, where the visit result is used to optimize the deployment of the target sports and cultural facility. It can be seen that through the user signaling data, the user location information can be obtained, and then the target sports and cultural facility can be determined. According to the user signaling data and the target sports and cultural facility, the spatial features of the location association between the user and the target sports and cultural facility, the temporal features of the user's visit to the target sports and cultural facility, the user attribute features with the user's personal preferences, and the facility attribute features of the construction situation of the target sports and cultural facility are combined as a multi-dimensional feature set. The feature map of the multi-dimensional feature set is input into a trained spatio-temporal prediction model, and the user's visit result to the target sports and cultural facility is output. Through the enhanced processing of the user signaling data and the combination with the features of the user and the target sports and cultural facility, the situation of the user's visit to the target sports and cultural facility is analyzed multi-dimensionally, making the visit result identified by the spatio-temporal prediction model more accurate, and accurately optimizing the deployment of the target sports and cultural facility according to the identified visit result, so as to solve the problem of low accuracy in identifying the visit to the sports and cultural facility.

[0172] The specific implementation steps can refer to the steps of the embodiment of the recognition method for the visit to the above-mentioned cultural and sports facilities, and can achieve the same technical effects. To avoid repetition, they will not be elaborated here.

[0173] It should be noted that the electronic devices in the embodiments of the present application include: servers, terminals, or other devices other than terminals.

[0174] The above structure of the electronic device does not limit the electronic device. The electronic device may include more or fewer components than those shown in the figure, or combine some components, or have different component arrangements. For example, the input unit may include a Graphics Processing Unit (GPU) and a microphone, and the display unit may be configured with a display panel in the form of a liquid crystal display, an organic light-emitting diode, etc. The user input unit includes at least one of a touch panel and other input devices. The touch panel is also called a touch screen. Other input devices may include, but are not limited to, a physical keyboard, function keys (such as volume control keys, switch keys, etc.), a trackball, a mouse, a joystick, which will not be elaborated here.

[0175] The memory can be used to store software programs and various data. The memory may mainly include a first storage area for storing programs or instructions and a second storage area for storing data. Among them, the first storage area can store an operating system, application programs or instructions required for at least one function (such as a sound playback function, an image playback function, etc.). In addition, the memory can include volatile memory or non-volatile memory, or the memory can include both volatile and non-volatile memory. Among them, the non-volatile memory can be a Read-Only Memory (ROM), a Programmable ROM (PROM), an Erasable PROM (EPROM), an Electrically Erasable PROM (EEPROM), or a flash memory. The volatile memory can be a Random Access Memory (RAM), a Static RAM (SRAM), a Dynamic RAM (DRAM), a Synchronous DRAM (SDRAM), a Double Data Rate SDRAM (DDR SDRAM), an Enhanced SDRAM (ESDRAM), a Synchlink DRAM (SLDRAM), and a Direct Rambus RAM (DRRAM).

[0176] The processor may include one or more processing units; optionally, the processor integrates an application processor and a modem processor. Among them, the application processor mainly processes operations related to the operating system, user interface, and application programs, etc., and the modem processor mainly processes wireless communication signals, such as a baseband processor. It can be understood that the above-mentioned modem processor may not be integrated into the processor either.

[0177] The embodiments of the present application also provide a readable storage medium, on which a program or instruction is stored. When the program or instruction is executed by a processor, it implements each process of the above-mentioned recognition method embodiment of the visit to the cultural and sports facilities, and can achieve the same technical effect. To avoid repetition, it will not be elaborated here.

[0178] Among them, the processor is the processor in the electronic device described in the above embodiments. The readable storage medium includes computer-readable storage media, such as computer read-only memory (ROM), random access memory (RAM), magnetic disks, or optical discs, etc.

[0179] Another embodiment of the present application provides a chip, which includes a processor and a communication interface. The communication interface is coupled to the processor. The processor is used to run programs or instructions to implement each process of the above-described embodiment of the recognition method for the arrival of the cultural and sports facilities, and can achieve the same technical effects. To avoid repetition, it will not be elaborated here.

[0180] It should be understood that the chip mentioned in the embodiments of the present application may also be referred to as a system-on-chip, system chip, chip system, or system-on-chip, etc.

[0181] Another embodiment of the present application provides a computer program product, which includes a computer program. When the computer program is executed by a processor, the processor is used to run the program or instruction to implement each process of the above-described embodiment of the product recommendation method, and can achieve the same technical effects. To avoid repetition, it will not be elaborated here.

[0182] It should be noted that in this article, the term "including", "comprising", or any other variant thereof is intended to cover non-exclusive inclusion, so that a process, method, article, or device including a series of elements not only includes those elements, but also includes other elements not expressly listed, or further includes elements inherent to such process, method, article, or device. Without further limitation, an element defined by the statement "including one..." does not exclude the existence of additional identical elements in the process, method, article, or device including that element. In addition, it should be pointed out that the scope of the methods and devices in the embodiments of the present application is not limited to performing functions in the order shown or discussed, and may also include performing functions in a substantially simultaneous manner or in a reverse order according to the functions involved. For example, the described method may be performed in an order different from that described, and various steps may be added, omitted, or combined. Additionally, the features described with reference to certain examples may be combined in other examples.

[0183] Through the description of the above embodiments, those skilled in the art can clearly understand that the methods of the above embodiments can be implemented by means of software plus a necessary general hardware platform. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present application, in essence or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) and includes several instructions for causing a terminal (which can be a mobile phone, computer, server, air conditioner, or network device, etc.) to execute the methods described in various embodiments of the present application.

[0184] The embodiments of the present application have been described above in conjunction with the accompanying drawings. However, the present application is not limited to the above specific implementation manners. The above specific implementation manners are merely illustrative rather than restrictive. Under the inspiration of the present application, those of ordinary skill in the art can also make many forms without departing from the purpose of the present application and the scope protected by the claims, and all of them belong to the protection scope of the present application.

Claims

1. A method for identifying the visit to a cultural and sports facility, characterized in that, The method includes: Obtaining user signaling data provided by an operator, where the user signaling data includes: user location information of a user connected to a base station through a mobile device and time information of the user's movement trajectory; Determining a target cultural and sports facility according to the user location information in the user signaling data; Determining a multi-dimensional feature set based on the user signaling data and the target cultural and sports facility, where the multi-dimensional feature set includes: a spatial feature of the location association between the user and the target cultural and sports facility, a temporal feature of the user's visit to the target cultural and sports facility, a user attribute feature of the user's behavior preference, and a facility attribute feature of the construction situation of the target cultural and sports facility; Inputting a feature map formed by the multi-dimensional feature set into a trained spatio-temporal prediction model, and outputting, through the spatio-temporal prediction model, a visit result of the user to the target cultural and sports facility, where the visit result is used to optimize the deployment of the target cultural and sports facility.

2. The method according to claim 1, wherein The multi-dimensional feature set includes a spatial feature of the location association between the user and the target cultural and sports facility; The determining of the multi-dimensional feature set according to the user signaling data and the target cultural and sports facility includes: Calculating the distance from the user to the target cultural and sports facility according to the user location information in the user signaling data; Determining an extended distance from the user to outside the target cultural and sports facility according to the distance from the user to the target cultural and sports facility; Determining a preset range around the target cultural and sports facility according to the distance from the user to the target cultural and sports facility and the extended distance; Determining the moving distance and total staying duration of the user within the preset range based on the user location information and the time information of the user's location movement in the user signaling data; Determining the average roaming speed of the user based on the moving distance and the corresponding moving time; Determining the total staying duration and the average roaming speed as the spatial feature of the location association between the user and the target cultural and sports facility.

3. The method according to claim 1, wherein The multi-dimensional feature set further includes a temporal feature of the user's visit to the target cultural and sports facility, a user attribute feature of the user's behavior preference, and a facility attribute feature of the construction situation of the target cultural and sports facility; The determining of the multi-dimensional feature set according to the user signaling data and the target cultural and sports facility further includes: Based on the user signaling data, determining the date type and time period attribute of the user's visit to the target cultural and sports facility, and determining the date type and the time period attribute as the temporal feature of the user; the date type includes: working days and non-working days, and the time period attribute includes: working hours and non-working hours; Obtaining the user's Internet access information, and determining the user's behavior preference according to the Internet access information, and determining the user's behavior preference as the user attribute feature; Obtaining the construction situation of the target cultural and sports facility according to the target cultural and sports facility, and determining the construction situation of the target cultural and sports facility as the facility attribute feature of the target cultural and sports facility.

4. The method according to claim 1, wherein Inputting the feature map formed by the multi-dimensional feature set into the trained spatio-temporal prediction model, and outputting the arrival result of the user at the target cultural and sports facility through the spatio-temporal prediction model, including: Performing splicing processing on the multi-dimensional feature set through a feedforward artificial neural network to obtain the feature map corresponding to the multi-dimensional feature set; Inputting the feature map into the trained spatio-temporal prediction model, and outputting the arrival result of the user at the target cultural and sports facility through the attention mechanism of the spatio-temporal prediction model.

5. The method according to claim 1, wherein The training of the spatio-temporal prediction model includes: Obtaining the sample feature map after splicing the sample multi-dimensional feature sets of multiple sample users, and the arrival situation of the sample users at the sample target cultural and sports facilities; Inputting the sample feature map into the spatio-temporal prediction model to be trained, and processing the sample feature map through the convolutional layer and pooling layer of the spatio-temporal prediction model to be trained to obtain high-order features; Inputting the high-order features into the attention mechanism of the spatio-temporal prediction model to be trained, and outputting the sample arrival result of the sample users at the sample target cultural and sports facilities through the attention mechanism; Training the spatio-temporal prediction model to be trained according to the arrival situation and the sample arrival result to obtain the trained spatio-temporal prediction model.

6. The method according to claim 5, wherein After obtaining the trained spatio-temporal prediction model, it includes: Determining the evaluation index of the sample arrival result according to the arrival situation and the sample arrival result of multiple sample users, and the evaluation index includes one or more of the accuracy rate, hit rate, recall rate, and mean square error of the sample users accessing the sample target cultural and sports facilities; Evaluating and monitoring the trained spatio-temporal prediction model according to the evaluation index.

7. An identification device for the arrival of a sports facility, characterized in that, Including: An acquisition module for acquiring user signaling data provided by an operator, where the user signaling data includes: user location information and time information of the user's movement trajectory connected by a mobile device and a base station; A positioning module for determining a target cultural and sports facility according to the user location information in the user signaling data; A determination module for determining a multi-dimensional feature set based on the user signaling data and the target cultural and sports facility, and the multi-dimensional feature set includes: spatial features of the location association between the user and the target cultural and sports facility, temporal features of the user's arrival at the target cultural and sports facility, user attribute features of the user's behavior preferences, and facility attribute features of the construction situation of the target cultural and sports facility; A prediction module for inputting the feature map formed by the multi-dimensional feature set into the trained spatio-temporal prediction model, and outputting the arrival result of the user at the target cultural and sports facility through the spatio-temporal prediction model, where the arrival result is used to optimize the deployment of the target cultural and sports facility.

8. An electronic device, characterized in that, Including a processor and a memory electrically connected to the processor, the memory stores a computer program, and the processor is used to call and execute the computer program from the memory to implement a method for identifying the arrival of a cultural and sports facility as described in any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that, The storage medium is used to store a computer program, and the computer program can be executed by a processor to implement a method for identifying a visit to a cultural and sports facility according to any one of claims 1 to 6.

10. A computer program product, characterized in that, It includes a computer program, and when the computer program is executed by a processor, it implements a method for identifying a visit to a cultural and sports facility according to any one of claims 1 to 6.

Images