Service information pushing method and system and terminal equipment

Abstract

The invention provides a service information pushing method and system and terminal equipment, and is suitable for the technical field of smart cities, and the method comprises the steps: carrying out the processing of user service demand monitoring information, service information pushing equipment state information, user service behavior information and user service recommendation communication resource information, obtaining initial service information pushing equipment state parameter information; and performing iterative optimization processing on the initial service information pushing equipment state parameter information to obtain target service information pushing equipment state parameter information, thereby performing service information pushing through the service information pushing equipment according to the target service information pushing equipment state parameter information. According to the application, deep fusion and intelligent processing of multi-source information are realized, service information pushing equipment state parameter information is adaptively generated and optimized, service information pushing can accurately match user requirements, timeliness of service information pushing is ensured, pertinence, high efficiency and reliability of service information pushing are improved, and living quality of residents is improved.

Description

Technical Field

[0001] The present application belongs to the field of smart city technology, and in particular relates to a service information push method, system, and terminal device. Background Art

[0002] In the current field of smart city construction, with the rapid development of information technology, various digital services have been widely penetrated into urban management and residents' lives.

[0003] Existing technologies typically predict user needs based solely on demand, pushing service information based on the predicted results. However, existing technologies are deficient in terms of individual service matching and long-term user experience optimization. The low accuracy of user service demand predictions hinders the effectiveness of communication resources used for service information push, limiting the operational quality of community services. Summary of the Invention

[0004] In view of this, the embodiments of the present application provide a service information push method, system and terminal device, aiming to solve the problems in the existing technology that the user's service information push experience cannot be optimized in the long term and the accuracy and effectiveness of service push cannot be guaranteed.

[0005] A first aspect of an embodiment of the present application provides a service information push method, including:

[0006] Obtain multiple user service demand monitoring information, service information push device status information, and user service behavior information;

[0007] Classify and process the user service demand monitoring information to obtain multiple community service demand information;

[0008] Parsing the service information push device status information to obtain multiple service information push device communication status parsing information;

[0009] Analyze and predict the user service behavior information to obtain multiple user service behavior prediction information;

[0010] Obtaining multiple initial service information push device state parameter information based on the multiple community service demand information, service push device communication state analysis information, user service behavior prediction information, and preset user service recommended communication resource information;

[0011] Iterative optimization processing is performed on the multiple initial service information push device state parameter information to obtain target service information push device state parameter information, so as to push service information through the service information push device according to the target service information push device state parameter information.

[0012] A second aspect of the embodiments of the present application provides a service information push system, including:

[0013] Information acquisition module, used to obtain multiple user service demand monitoring information, service information push device status information and user service behavior information;

[0014] A community service demand information generating module is used to classify and process the user service demand monitoring information to obtain a plurality of community service demand information;

[0015] a service push device communication status parsing information generating module, configured to parse and process the service information push device status information to obtain a plurality of service push device communication status parsing information;

[0016] A user service behavior prediction information generation module is used to analyze and predict the user service behavior information to obtain multiple user service behavior prediction information;

[0017] An initial service information push device state parameter information generation module is configured to obtain a plurality of initial service information push device state parameter information based on the plurality of community service demand information, service push device communication state analysis information, user service behavior prediction information, and preset user service recommended communication resource information;

[0018] The target service information push device state parameter information generation module is used to iteratively optimize the multiple initial service information push device state parameter information to obtain the target service information push device state parameter information, so as to push service information according to the target service information push device state parameter information through the service information push device.

[0019] A third aspect of an embodiment of the present application provides a terminal device, which includes a memory and a processor, wherein the memory stores a computer program that can be run on the processor, and when the processor executes the computer program, it implements the steps of the service information push method described in the first aspect above.

[0020] A fourth aspect of an embodiment of the present application provides a computer-readable storage medium, comprising: storing a computer program, which, when executed by a processor, implements the steps of the service information push method described in the first aspect above.

[0021] Compared with the prior art, the beneficial effects of the embodiments of the present application are as follows: the present application can realize the deep integration and intelligent processing of multi-source information, clarify community service needs by classifying user service demand monitoring information, grasp the communication network status by analyzing the service information push device status information, analyze and predict user service behavior information to grasp user behavior trends, and then generate and optimize service information push device status parameter information based on multi-dimensional information, so that service information push can accurately match community user needs, efficiently utilize communication resources, adapt to user behavior patterns, and improve the pertinence, timeliness and reliability of service information push, thereby promoting the development of smart elderly care and smart business, and improving residents' quality of life and urban operation efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following briefly introduces the drawings required for use in the embodiments or descriptions of the prior art. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0023] Figure 1 This is a schematic diagram of the implementation process of the service information push method provided in Example 1 of the present application;

[0024] Figure 2 This is a schematic diagram of the implementation flow of the service information push method provided in Example 2 of the present application;

[0025] Figure 3 This is a schematic diagram of the implementation flow of the service information push method provided in Example 3 of the present application;

[0026] Figure 4 This is a schematic diagram of the implementation flow of the service information push method provided in Example 4 of the present application;

[0027] Figure 5 This is a schematic diagram of the implementation flow of the service information push method provided in Example 5 of the present application;

[0028] Figure 6 This is a schematic diagram of the implementation flow of the service information push method provided in Example 6 of the present application;

[0029] Figure 7 This is a schematic diagram of the implementation flow of the service information push method provided in Example 7 of the present application;

[0030] Figure 8 This is a schematic diagram of the structure of the service information push system provided in an embodiment of the present application;

[0031] Figure 9 It is a schematic diagram of the terminal device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0032] In the following description, specific details such as specific system structures and techniques are provided for purposes of illustration rather than limitation to facilitate a thorough understanding of the embodiments of the present application. However, it will be apparent to those skilled in the art that the present application may be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to avoid obscuring the description of the present application with unnecessary detail.

[0033] In order to illustrate the technical solution described in this application, specific embodiments are provided below.

[0034] Figure 1 The following is a flowchart of the implementation of the service information push method provided in Example 1 of the present application, which is detailed as follows:

[0035] Step S101: Acquire multiple user service demand monitoring information, service information push device status information, and user service behavior information.

[0036] In this embodiment, user service demand monitoring information can refer to users' specific needs for smart community services and related attributes, including structured information such as demand type, urgency, and time sensitivity. This information can be obtained directly from users actively submitting service requests through channels such as community apps and physical buttons on terminal devices, such as obtaining the text of the demand and trigger status. It can also be obtained by inferring potential needs through AI algorithms using IoT devices deployed in the community to sense user behavior trajectories, such as automatically generating health monitoring needs when an elderly person has not moved for an extended period of time. It can also include users' historical service records for subsequent analysis of periodic needs, such as shopping service needs at fixed times each week. Service requests can include requests for emergency care for the elderly and business service inquiries. Device status information for service information push can refer to the operating status and communication capability parameters of service push devices, such as drones, base stations, and smart terminal devices. This information can include hardware resources and communication quality. This information can be collected in real time through embedded sensors, such as transmit power, battery life, and CPU utilization, and reported to the management platform via the MAC layer protocol for subsequent access. It can also be measured through methods such as received signal strength indicators (RSIs) and channel probe packets, and calculated using the Shannon formula for communication rate and bit error rate. It can also be obtained through GPS and other positioning systems, and environmental perception can be used to assess communication link stability. User service behavior information can refer to the interaction records and behavioral patterns between users and the service push system, including quantifiable characteristics such as historical reception rates, interaction delays, and feedback scores. This information can be generated by recording user responses to service push notifications, such as clicks, ignores, and feedback scores, to form a historical reception record. It can also be inferred by linking the user's wearable devices, such as smart bracelets, with their exercise status and physiological indicators, such as reducing the frequency of non-emergency service push notifications during exercise.

[0037] Step S102: Classify and process the user service demand monitoring information to obtain a plurality of community service demand information.

[0038] In this embodiment, the neighborhood radius and the minimum number of samples can be determined first, and the user service demand monitoring information can be converted into points in space. The number of neighbors of each point within the neighborhood radius is calculated. If the number of neighbors of a point is not less than the minimum number of samples, it is defined as a core point. All points in the neighborhood of the core point constitute a density-reachable area. If two points can be connected by a core point chain, they belong to the same cluster. Edge points do not constitute the core due to insufficient number of neighbors but can be included in the core points. Noise points are completely isolated from all clusters. By traversing the neighborhood density connection relationship of all demand points, demand points with continuous density accessibility are divided into the same community service demand category, thereby realizing classification processing of user service demand monitoring information and obtaining multiple community service demand information, thereby identifying clusters of arbitrary shapes through density connectivity, and effectively dealing with the complex distribution characteristics of demand information.

[0039] Step S103: parse the service information push device status information to obtain multiple pieces of service information push device communication status parsing information.

[0040] In this embodiment, by extracting parameters such as transmission power, signal strength, channel gain, etc. from the service information push device status information, they are mapped into feature vectors in a multidimensional space, and a neighborhood relationship is constructed based on the similarity measurement between vectors. The density distribution in the neighborhood of each device state vector is calculated, and the area with a density significantly higher than the threshold is divided into a cluster of normal device working states, and the area with a sudden density change is identified as an abnormal state. By traversing the neighborhood density connectivity of all device state vectors, device states with similar communication characteristics are divided into the same category, and at the same time, indicators such as the communication rate and bit error rate of each category are calculated, thereby realizing the parsing and processing of the service information push device status information, and obtaining multiple service push device communication status parsing information. This process analyzes the distribution characteristics of the device status through density connectivity and effectively identifies the normal and abnormal modes of the device communication status.

[0041] Step S104: performing analysis and prediction calculation based on the user service behavior information to obtain a plurality of user service behavior prediction information.

[0042] In this embodiment, a time-dependent processing mechanism can be constructed to organize user service behavior information into serial data in chronological order, and memory units can be used to selectively retain and update historical behavior features, effectively memorize behavior patterns over long time spans, and forget irrelevant short-term fluctuations. Through a multi-level information processing flow, current behavior features are integrated with historical memory information to generate prediction results for future behavior. This can capture long-term dependencies and periodic patterns in user behavior, process serial data such as reception rate and interaction delay in user service behavior information, and iteratively update state information in memory units to achieve prediction calculations for users' future service behaviors, thereby obtaining multiple user service behavior prediction information. This process effectively responds to the dynamic temporal changes in user behavior data by adaptively adjusting the degree of retention of historical information.

[0043] Step S105 , obtaining a plurality of initial service information push device state parameter information based on the plurality of community service demand information, service push device communication state analysis information, user service behavior prediction information, and preset user service recommended communication resource information.

[0044] In this embodiment, the preset user service recommendation communication resource information can be manually set, or can be a predefined resource configuration reference standard based on user characteristics, service requirements, and the communication environment. Community service demand information, service push device communication status analysis information, user service behavior prediction information, and preset user service recommendation communication resource information can be integrated to randomly generate multiple service information push device state parameter combinations as initial solutions. These initial solutions simulate the distribution of group members in the solution space, with each solution corresponding to a device state parameter configuration. By evaluating the initial solutions' performance in terms of demand matching and resource utilization, a score is calculated for each initial solution, thereby generating multiple initial service information push device state parameter combinations.

[0045] Step S106 , iteratively optimizing the multiple initial service information push device state parameter information to obtain target service information push device state parameter information, so as to push service information through the service information push device according to the target service information push device state parameter information.

[0046] In this embodiment, based on the quality scores of initial solutions, the collaborative and competitive behavior of individuals in a biological population can be simulated. High-performing solutions are explored and expanded to evolve towards higher optimization, while poor-performing solutions are adjusted and mutated to avoid being trapped in local optima. During each iteration, the search strategy is dynamically adjusted based on the quality and distribution of solutions, and the device state parameter combinations are continuously updated. After multiple rounds of iterative optimization, the solution with the best overall score is ultimately selected, representing the target service information push device state parameter information, which is then used to guide the service information push device in delivering efficient and accurate service information.

[0047] The service information push method provided in the embodiment of the present application can realize the deep integration and intelligent processing of multi-source information, clarify community service needs by classifying user service demand monitoring information, grasp the communication network status by analyzing the service information push device status information, analyze and predict user service behavior information to grasp user behavior trends, and then generate and optimize service information push device status parameter information based on multi-dimensional information, so that service information push can accurately match community user needs, efficiently utilize communication resources, adapt to user behavior patterns, and improve the pertinence, timeliness and reliability of service information push, thereby promoting the development of smart elderly care and smart business, and improving residents' quality of life and urban operation efficiency.

[0048] Figure 2 The flowchart of the service information push method provided in the second embodiment of the present application is shown. The difference between the second embodiment and the first embodiment is that step S102 specifically includes:

[0049] Step S201 : performing word segmentation processing on the user service demand monitoring information to obtain user service demand text information, user service demand generation time information, and user service demand business type information.

[0050] In this embodiment, the text content in the user service demand monitoring information can be segmented through natural language processing technology, and the user service demand text information can be obtained after removing stop words. At the same time, the timestamp of the demand generation is extracted from the demand record and converted into the user service demand generation time information, and the user service demand business type information is determined according to the business attribute label of the demand. For example, the demand for "first aid for elderly people falling in nursing homes" submitted through the community APP can obtain text information such as "nursing home", "elderly", "fall", and "first aid" after word segmentation. The generation time is "2025-06-20 09:30", and the business type is "nursing care first aid".

[0051] Step S202 : determining emergency community service demand information, high-frequency community service demand information, and general community service demand information according to the user service demand generation time information and the user service demand business type information.

[0052] In this embodiment, if the interval between the user service demand generation time and the current time is less than a preset emergency time threshold (e.g., one hour) and the service type is elderly care or emergency first aid, then the user service demand is determined to be an emergency community service demand. If a service demand for a certain type of service exceeds a high-frequency threshold (e.g., five times) within a preset time window (e.g., one week), the user service demand is classified as a high-frequency community service demand. The rest are classified as ordinary community service demand. For example, if a service demand for elderly care or emergency first aid is generated 30 minutes from the current time, the user service demand is determined to be an emergency community service demand. If a service demand for commercial consulting services occurs eight times within a week, the user service demand is determined to be a high-frequency community service demand.

[0053] Step S203 : performing keyword matching processing based on the user service demand text information and a preset service demand information database to obtain a plurality of user service demand text keyword matching information.

[0054] In this embodiment, the preset service demand information database can be manually set. Keywords in the user service demand text information can be compared with standard keywords in the preset service demand information database to calculate the keyword matching degree and weight. For example, if the keyword "first aid" in the demand text matches the keyword "medical first aid" in the service demand information database at a matching degree of 90%, corresponding user service demand text keyword matching information is generated, including matching keywords, matching scores, and corresponding service types.

[0055] Step S204 , obtaining a plurality of community service demand information based on the plurality of user service demand text keyword matching information, emergency community service demand information, high-frequency community service demand information, and common community service demand information.

[0056] In this embodiment, the user service demand text keyword matching information can be associated and integrated with the emergency, high-frequency, and ordinary community service demand information. For example, if a certain demand belongs to the emergency community service demand information and the text keyword matches "first aid", then community service demand information including the degree of urgency, business type, and keyword matching results will be generated, and finally multiple structured community service demand information will be formed.

[0057] The service information push method provided in the embodiment of the present application realizes multi-dimensional classification of user service needs by performing word segmentation processing, time and business type correlation analysis and keyword matching on user service demand monitoring information, making community service demand information more hierarchical and targeted, and being able to more accurately match the urgency, high-frequency characteristics and text content features of user needs, providing more detailed demand dimensions for the generation and optimization of subsequent service information push device status parameters, further improving the accuracy and effectiveness of service information push, and enhancing adaptability to smart community service scenarios.

[0058] Figure 3 The flowchart of the service information push method provided in the third embodiment of the present application is shown. The difference between the third embodiment and the first embodiment is that step S103 specifically includes:

[0059] Step S301: extract and process the service information push device status information to obtain service push device status running time information, service push device transmission power information, service push device channel quality monitoring information, service push device power status information, and service push device resource occupancy information.

[0060] In this embodiment, data can be collected in real time through the monitoring module built into the service push device. For example, the service push device status running time information is extracted from the device's system log to accurately record the device's working time since startup; the service push device's sending power information is obtained through a power sensor, such as the wireless transmission power value of the drone; signal strength detection and channel detection technology are used to calculate the service push device channel quality monitoring information, including parameters such as the received signal strength indication, channel gain, and noise power; the service push device power status information is read through the battery management system, including the remaining power, charging status, etc.; the service push device resource occupancy information is obtained from the device's resource scheduling module, such as CPU usage, memory occupancy, network bandwidth occupancy, etc., thereby completing the structured disassembly of the original device status information.

[0061] Step S302 , calculating service information push device status representation information based on the service push device sending power information, service push device channel quality monitoring information, service push device power status information, service push device resource occupancy information, and preset service information push device status parsing weight information.

[0062] In this embodiment, the preset service information push device status parsing weight information can be manually set and can be a parameter pre-set based on the device's operating characteristics and service requirements, used to measure the importance of different status indicators. For example, for services with high real-time requirements, the weight of channel quality monitoring information is set to 0.4; for devices that are sensitive to battery life, the weight of power status information is set to 0.3. Based on the service information push device status parsing weight information, a weighted summation of the service push device's transmit power information, the service push device's channel quality monitoring information, the service push device's power status information, and the service push device's resource usage information can be performed, and the weighted summation result can be used as the service information push device status representation information.

[0063] Step S303: obtaining communication status parsing information of multiple service push devices according to the service push device status running time information and the service information push device status representation information.

[0064] In this embodiment, the time-varying trends of device status representation information are analyzed in conjunction with the service push device status runtime information. For example, if a device operates at high load for a long period of time and its status representation information continues to deteriorate, such as a drop in power status or reduced channel quality, the device is determined to have entered a fatigue warning state. If the status representation information fluctuates dramatically within a short period of time, such as a sudden change in transmit power, the runtime information can be combined to locate the time period when the anomaly occurred, generating service push device communication status parsing information containing the anomaly type, timestamp, and severity. Furthermore, by comparing status representation information at different time points, the device's operating modes can be divided into normal, warning, and faulty modes, ultimately outputting multiple structured service push device communication status parsing information to provide a basis for subsequent resource scheduling and service push strategies.

[0065] The service information push method provided in the embodiment of the present application realizes a refined assessment of the operating status of the service information push device by performing multi-dimensional decomposition, weighted integration and dynamic analysis of the service information push device status information, and provides more comprehensive and dynamic device status data support for generating accurate service information push device status parameters, thereby optimizing resource allocation strategies, ensuring the stability and efficiency of service push, and improving the overall reliability of the smart community service system.

[0066] Figure 4The flowchart of the service information push method provided in the fourth embodiment of the present application is shown. The difference between the fourth embodiment and the first embodiment is that step S104 specifically includes:

[0067] Step S401: extracting the user service behavior information to obtain user service information receiving time information, user service usage type information, and user service feedback information.

[0068] In this embodiment, the interaction logs between users and the service push system are parsed to extract the timestamp of each service push and convert it into the time the user received the service information. Information about the user's service usage type, such as elderly care and first aid, or business consultation, is then obtained from the push content tags. User ratings, comments, and other data are then collected to form user service feedback information. For example, a user receives a business service consultation push at 10:15 on June 20, 2025, clicks on it, and gives it an "average" rating. After processing, the corresponding reception time, usage type, and feedback information are generated.

[0069] Step S402 : generating a plurality of user service behavior pattern information according to the user service information receiving time information, the user service usage type information, and the user service feedback information.

[0070] In this embodiment, features from user service information reception time information, user service usage type information, and user service feedback information can be extracted for correlation analysis. For example, if a user frequently receives and provides positive feedback on elderly care services between 9:00 AM and 11:00 AM on weekdays, behavioral pattern information indicating a preference for elderly care services on weekday mornings will be generated. If a user's feedback score for commercial service consulting information is consistently below a threshold and the feedback is received at scattered times, behavioral pattern information indicating a low interest in commercial services will be generated. Ultimately, multiple patterns of information reflecting user behavior patterns will be generated.

[0071] Step S403: randomly extracting a plurality of user service behavior pattern information according to preset user service behavior pattern reference point quantity information to generate user service behavior pattern reference point information.

[0072] In this embodiment, the preset number of user service behavior pattern reference points can be set manually, and can take a value of 6 or 5, which can be used as the number of groups of the initial user service behavior pattern information, that is, determining how many groups multiple user service behavior pattern information can be divided into.

[0073] Step S404 : calculating the logical distance between the user service behavior pattern information and the user service behavior pattern reference point information to obtain user behavior pattern distance representation information.

[0074] In this embodiment, a metric such as cosine similarity or Euclidean distance can be used to calculate the logical distance between each behavioral pattern and each reference point. For example, for the "weekday morning elderly care service preference" pattern, the distance between it and the five reference points is calculated in terms of time (e.g., whether they are all morning hours) and service type (e.g., whether they are all elderly care services). These multi-dimensional distances are then integrated into a single numerical representation to form a distance representation of the user's behavioral patterns, quantifying the similarity between the behavioral patterns.

[0075] Step S405 : generating a plurality of user service behavior pattern group information according to the user behavior pattern distance representation information and the user service behavior pattern reference point information.

[0076] In this embodiment, each behavioral pattern can be assigned to the category represented by the closest reference point to form an initial behavioral pattern group. For example, if the "weekday morning elderly care service preference" pattern is closest to the reference point "high-frequency elderly care service users," it will be assigned to the pattern group corresponding to that reference point, ultimately generating multiple user service behavior pattern groups such as the "elderly care service core user group" and the "commercial service potential user group."

[0077] Step S406: Calculate the average value of each user service behavior pattern group information to obtain user service behavior pattern group center information.

[0078] In this embodiment, the feature vectors of all behavioral patterns within each pattern group (such as reception time distribution and service type weight) can be averaged. For example, in the "Elderly Care Service Core User Group," the average reception time (such as 10:00 AM) and average service type preference weight (0.8 for Elderly Care) of all users are calculated to generate a new center vector as the center information of the user service behavior pattern group, representing the typical behavioral characteristics of this group.

[0079] Step S407, determining whether the user service behavior pattern group center information is the same as the user service behavior pattern reference point information; if so, proceeding to step S408; if not, proceeding to step S409.

[0080] In this embodiment, the feature vectors of the newly generated cluster center information can be compared dimension by dimension with the original reference point information. For example, comparing the new center of the "Elderly Care Service Core User Group" (10:00 AM, Elderly Care 0.8) with the original reference point (9:00 AM, Elderly Care 0.7), if any dimension difference exceeds a preset threshold (such as a time difference ≥ 30 minutes or a weight difference ≥ 0.1), it is determined to be different and requires re-iteration. If all dimensions meet the similarity requirements, it is considered converged and the prediction stage is entered.

[0081] Step S408: performing prediction calculation on the plurality of user service behavior pattern group information to obtain a plurality of user service behavior prediction information.

[0082] In this embodiment, future behavior predictions can be generated based on the historical behavior patterns and current status of each pattern group, combined with a time series prediction algorithm. For example, for the "core user group of elderly care services," it is predicted that their acceptance rate for elderly care services will be 90% around 10 a.m. on Sunday, with a feedback score maintained at 4.5 points. For the "potential user group of commercial services," it is predicted that their response rate to commercial push notifications will increase by 20% on weekends. This generates multiple user service behavior prediction information containing parameters such as time, service type, and response probability.

[0083] Step S409: Use the user service behavior pattern group center information as the user service behavior pattern reference point information, and return to step S404.

[0084] In this example, the newly calculated cluster center information is used to update the reference point information. For example, the new center of the "Elderly Care Service Core User Cluster" (10:00 AM, Elderly Care Category 0.8) is used as the new reference point. The distances between all behavior patterns and the new reference point are recalculated and assigned again. The calculation results are continuously adjusted through iterative optimization until convergence conditions are met.

[0085] The service information push method provided in the embodiment of the present application realizes accurate identification and prediction of user behavior patterns by extracting, classifying and iteratively optimizing user service behavior information. It can not only discover the common characteristics of user groups, but also capture the dynamic changes of behavior patterns, provide more detailed user portrait support for service push strategies, make the push content, time and method more in line with user needs, and further improve the personalization level and resource utilization efficiency of smart community services.

[0086] Figure 5 The flowchart of the service information push method provided in the fifth embodiment of the present application is shown. The difference between the fifth embodiment and the fourth embodiment is that the step S408 specifically includes:

[0087] Step S501 : generating first user service behavior pattern group feature information based on a plurality of user service behavior pattern group information and a preset first user service behavior pattern feature extraction matrix.

[0088] In this embodiment, the preset first user service behavior pattern feature extraction matrix can be manually set to extract time dimension features from user service behavior pattern group information. This can be achieved by performing a weighted operation on the reception time distribution of the "elderly care service core user group" using the first user service behavior pattern feature extraction matrix, extracting the high-frequency reception period around 10 a.m. on weekdays. This time information is then converted into a feature vector to generate feature information for the first user service behavior pattern group, highlighting the temporal patterns of user behavior.

[0089] Step S502 : generating second user service behavior pattern group feature information based on a plurality of user service behavior pattern group information and a preset second user service behavior pattern feature extraction matrix.

[0090] In this embodiment, a preset second-user service behavior pattern feature extraction matrix is ​​used to extract service type preference features. For example, for a "potential user group for commercial services," the second-user service behavior pattern feature extraction matrix is ​​used to calculate preference weights for each service type, such as 0.6 for commercial services and 0.3 for lifestyle services. This service type information is then converted into feature vectors to generate feature information for the second-user service behavior pattern group, quantifying users' preferences for different service types.

[0091] Step S503 : generating third user service behavior pattern group feature information according to the plurality of user service behavior pattern group information and a preset third user service behavior pattern feature extraction matrix.

[0092] In this embodiment, the preset third user service behavior pattern feature extraction matrix can be manually set and can be used to extract user feedback rating features. For example, a convolution operation is performed on the feedback rating data of the "elderly care service core user group" to extract rating trends (e.g., consistently above 4.5 points) and stability features, which are converted into feature vectors to generate third user service behavior pattern group feature information, reflecting user satisfaction with the service and its changing trends.

[0093] Step S504: Generate user service behavior pattern group interaction characteristic information based on the first user service behavior pattern group characteristic information and the second user service behavior pattern group characteristic information.

[0094] In this embodiment, time dimension features can be integrated with service type preference features through matrix multiplication or concatenation operations. For example, the association weight between 10:00 AM and the type of elderly care service is calculated. If the elderly care service acceptance rate during this period reaches 90%, an interaction feature vector is generated to characterize the interaction relationship between the specific time and the service type, forming interactive feature information of the user service behavior pattern group, revealing the correlation of user behavior across dimensions.

[0095] Step S505 : generating user service behavior pattern group fusion feature information based on the user service behavior pattern group interaction feature information and the third user service behavior pattern group feature information.

[0096] In this embodiment, cross-dimensional interaction features can be deeply integrated with feedback scoring features. For example, combining the elderly care service receiving behavior at 10 a.m. with the average feedback score of 4.5 points, the attention mechanism assigns higher weight to high-scoring behaviors, generating a comprehensive feature vector that includes time, type, and feedback, forming the integrated feature information of the user service behavior pattern group, and comprehensively characterizing the multi-dimensional attributes of the user behavior pattern.

[0097] Step S506 : obtaining user service behavior pattern group feature mapping information according to the user service behavior pattern group fusion feature information and a preset user service behavior pattern feature mapping matrix.

[0098] In this embodiment, the preset user service behavior pattern feature mapping matrix can be manually set and used to map the comprehensive feature vector to the prediction space. For example, through matrix operations, the fused features are converted into vectors representing prediction dimensions such as future acceptance rate and response probability. For example, [time feature, type feature, feedback feature] can be mapped to [0.9 (acceptance rate), 0.85 (response probability)] to obtain user service behavior pattern group feature mapping information, providing an intermediate representation for subsequent prediction.

[0099] Step S507 : performing mapping transformation processing on the user service behavior pattern group feature mapping information according to a preset user service behavior pattern feature mapping transformation matrix to obtain user service behavior pattern group feature mapping transformation information and the number of user service behavior pattern group feature mapping transformations.

[0100] In this embodiment, the preset user service behavior pattern feature mapping transformation matrix can be manually set and used to iteratively optimize the prediction representation. During the first transformation, the mapping information is nonlinearly transformed to enhance the feature expression capability, and the number of transformations is recorded as 1. During the subsequent transformation, the historical transformation results are further integrated, such as combining the reception rate prediction value after the first transformation with the current feedback features to obtain a more accurate prediction intermediate value. The number of transformations is increased by 1 after each transformation until the iteration condition is met.

[0101] Step S508 , determining whether the number of changes in the user service behavior pattern group feature mapping is greater than a preset threshold value for the number of changes in the user service behavior pattern group feature mapping; if so, proceeding to step S509 ; if not, proceeding to step S510 .

[0102] In this embodiment, the preset threshold for the number of user service behavior pattern group feature mapping transformations can be manually set and can be used to control the iteration depth. When the number of user service behavior pattern group feature mapping transformations exceeds the preset threshold, the feature representation is considered to be fully optimized and iteration can be stopped. When the number of user service behavior pattern group feature mapping transformations is less than or equal to the preset threshold, feature optimization through the mapping transformation matrix is ​​continued to avoid insufficient prediction accuracy due to insufficient iterations.

[0103] Step S509 : obtaining a plurality of user service behavior prediction information according to the user service behavior pattern group feature mapping transformation information.

[0104] In this embodiment, the final feature map transformation information can be converted into specific prediction results. For example, if the transformed vector is [0.92 (morning reception rate for elderly care services), 0.75 (weekend response rate for commercial services)], corresponding user service behavior prediction information is generated. This clarifies the response probability and feedback trends of each pattern group for different services at a specific time in the future, providing accurate prediction data for service delivery strategies.

[0105] Step S510 , using the user service behavior pattern group feature mapping transformation information as user service behavior pattern group fusion feature information, and returning to step S506 .

[0106] In this embodiment, when the number of iterations does not reach the threshold, the currently transformed features are used as new fusion features and are re-transformed through the feature mapping matrix until the number of transformations exceeds the threshold, ensuring that the feature representation fully captures the dynamic laws of user behavior.

[0107] The service information push method provided in the embodiment of the present application realizes in-depth modeling and accurate prediction of user behavior patterns through multi-dimensional feature extraction, cross-dimensional interactive analysis and iterative mapping transformation. It enhances the feature representation capability through iterative optimization, makes the prediction results more in line with the complex dynamic changes of user behavior, provides more refined and accurate user behavior prediction support for smart community service push, and further improves the intelligence level of service push and user experience.

[0108] Figure 6 The flowchart of the service information push method provided in the sixth embodiment of the present application is shown. The difference between the sixth embodiment and the first embodiment is that the step S105 specifically includes:

[0109] Step S601: Generate multiple service demand priority information and multiple user service recommendation type information based on the community service demand information and user service behavior prediction information; the service demand priority information and the user service recommendation type information are in one-to-one correspondence.

[0110] In this embodiment, service demand priority information is generated based on attributes such as urgency and time sensitivity in community service demand information, combined with the user's response probability for different services as shown in the user's service behavior prediction information. For example, urgent community service demand information (such as emergency care for the elderly) is assigned a high priority, while general community service demand information is assigned a medium or low priority. Furthermore, based on the user's preference probability for elderly care services and commercial services as shown in the user's service behavior prediction information, user service recommendation type information is generated, such as "high-frequency elderly care service recommendation" and "potential commercial service recommendation." This ensures that each service demand priority information corresponds to a unique recommendation type, achieving a precise correlation between demand and recommendation.

[0111] Step S602 : generating a plurality of service recommendation priority resource occupancy information according to the service demand priority information, the user service recommendation type information, the service push device communication state analysis information and the preset user service recommendation communication resource information.

[0112] In this embodiment, the service demand priority information, user service recommendation type information, service push device communication status analysis information (such as device communication rate, channel quality) and preset user service recommendation communication resource information (such as bandwidth thresholds and latency requirements for different service types) are integrated. For example, high-priority elderly emergency services need to match devices with good communication status (bit error rate < 10 -6 ), and generate service recommendation priority resource occupancy information based on preset resource standards (bandwidth ≥ 1Mbps), clarify the resource occupancy quota and priority ranking of various services on different devices, and provide a quantitative basis for subsequent resource allocation.

[0113] Step S603: Generate multiple pieces of initial service information push device status parameter information based on the multiple pieces of service recommendation priority resource occupancy information.

[0114] In this embodiment, multiple service recommendation priority resource occupancy information can be converted into device state parameter combinations. For example, for the high-priority requirement of "high-frequency elderly care service recommendations," initial service information push device state parameter information containing parameters such as resource allocation priority, communication rate, and channel gain is generated by combining parameters such as the available bandwidth and transmit power of a base station in the device communication state analysis information. This ensures that each parameter combination meets the resource occupancy requirements and device operation constraints of the corresponding service, forming multiple feasible initial solutions.

[0115] The service information push method provided in the embodiment of the present application converts abstract service requirements and user behaviors into quantifiable device parameter configurations through layered processing and integration of multi-source information, thereby ensuring both resource allocation for high-priority requirements and the rationality of parameter configuration, laying the initial parameter foundation for subsequent precise service push, and effectively improving the matching efficiency of services and resources.

[0116] Figure 7 The flowchart of the service information push method provided in the seventh embodiment of the present application is shown. The difference between the seventh embodiment and the sixth embodiment is that:

[0117] The initial service information push device state parameter information includes initial service push resource allocation priority information, initial service push communication rate information, and initial service push channel gain information; the initial service push resource allocation priority information corresponds to the service demand priority information one by one;

[0118] The step S106 specifically includes:

[0119] Step S701 : calculating and obtaining initial user service push matching degree information based on the plurality of community service demand information and user service recommendation type information corresponding to the initial service push resource allocation priority information.

[0120] In this embodiment, for each community service demand information, the degree of match between it and the user service recommendation type corresponding to the initial service push resource allocation priority information is calculated. For example, if an emergency elderly care first aid demand corresponds to the "high-frequency elderly care service recommendation" type, if this type is given a high priority in the initial resource allocation, the match degree is 90%; if the priority is lower, the match degree is correspondingly lower, and the initial user service push matching degree information is finally generated, reflecting the fit between the demand and the recommendation type.

[0121] Step S702: Calculate initial service push communication resource utilization information based on the multiple pieces of initial service push resource allocation priority information, initial service push communication rate information, and initial service push channel gain information.

[0122] In this embodiment, the resource allocation order for each service is determined based on the initial service push resource allocation priority information. The actual utilization of communication resources is calculated based on the initial service push communication rate information and channel gain information. For example, if a high-priority service occupies 60% of the device's bandwidth, and medium- and low-priority services occupy the remaining 40%, the actual transmission efficiency is calculated based on the channel gain to assess whether the resource allocation meets the preset utilization target (e.g., ≥80%), and the initial service push communication resource utilization information is generated.

[0123] Step S703 : Calculate and obtain multiple pieces of initial service information push quality metric information based on the multiple pieces of initial user service push matching degree information, initial service push communication resource utilization information, and preset service information push quality metric weight information.

[0124] In this embodiment, preset service information push quality metric weights (e.g., a matching weight of 0.6 and a resource utilization weight of 0.4) are weighted together to sum the initial user service push matching information and the initial service push communication resource utilization information. For example, if an initial parameter combination has a matching degree of 0.8 and a resource utilization of 0.7, the resulting weighted quality metric is 0.8 × 0.6 + 0.7 × 0.4 = 0.76. This ultimately generates multiple pieces of initial service information push quality metrics reflecting the quality of each parameter combination.

[0125] Step S704: using the initial service information push device state parameter information corresponding to the maximum value of the plurality of initial service information push quality metric information as service information push device state parameter optimization benchmark information.

[0126] In this embodiment, the maximum value is selected from multiple initial service information push quality metrics, and the corresponding initial service information push device state parameter information is determined as the optimization benchmark. For example, the parameter combination with the highest quality metric value (matching degree 0.9, resource utilization 0.85) is used as the starting point for subsequent iterative optimization, ensuring that the optimization direction is always towards the optimal overall performance solution.

[0127] Step S705, based on the multiple initial service information push device state parameter information, service information push device state parameter optimization benchmark information and preset service information push device state parameter optimization step information, obtain multiple intermediate service information push device state parameter information and intermediate service information push device state parameter optimization times information; the intermediate service information push device state parameter information includes intermediate service push resource allocation priority information, intermediate service push communication rate information and intermediate service push channel gain information; the intermediate service push resource allocation priority information corresponds one-to-one to the service demand priority information.

[0128] In this embodiment, the preset service information push device state parameter optimization step size information can be manually set. Initial parameter information can be iteratively adjusted based on the preset service information push device state parameter optimization step size information (e.g., resource allocation priority adjustment ±1, communication rate adjustment ±50 kbps). Based on the optimization benchmark, multiple intermediate parameter combinations are generated in the solution space, such as adjusting the resource allocation priority or channel gain of a particular service, and the number of optimizations is recorded. For example, in the first iteration, five intermediate parameter combinations are generated, and the number of optimizations is recorded as 1, until all possible solutions within the preset step size range are reached.

[0129] Step S706, determining whether the intermediate service information push device state parameter optimization times information is less than a preset service information push device state parameter optimization iteration times threshold; if so, proceeding to step S707; if not, proceeding to step S708.

[0130] In this embodiment, the preset threshold for the number of iterations for optimizing the device status parameters for service information push can be manually set to control the depth of optimization. If the number of intermediate optimizations is less than the threshold, the iterative adjustment of the parameters continues; if the number reaches the threshold, the iterations cease and the final evaluation phase begins, avoiding excessive optimization and wasting computing resources.

[0131] Step S707, use the multiple intermediate service push resource allocation priority information as the initial service push resource allocation priority information, use the intermediate service push communication rate information as the initial service push communication rate information and use the intermediate service push channel gain information as the initial service push channel gain information, and return to step S701.

[0132] In this embodiment, the initial parameters are overwritten with the intermediate service push resource allocation priority, communication rate, and channel gain information generated in the current iteration, serving as the starting point for a new iteration. For example, the intermediate parameters from the last iteration (priority + 1, rate + 50 kbps) are used as the new initial parameters, and the matching degree and resource utilization are recalculated, gradually approaching the optimal solution.

[0133] Step S708 : calculating intermediate user service push matching degree information based on the plurality of community service demand information and the user service recommendation type information corresponding to the intermediate service push resource allocation priority information.

[0134] In this embodiment, the matching degree between the intermediate service push resource allocation priority information generated in the final iteration and the user service recommendation type corresponding to the community service demand information is recalculated. For example, the matching degree between the high-priority service and the recommended type in the final intermediate parameters is improved to 0.95, generating more accurate intermediate user service push matching degree information, reflecting the demand fit after iterative optimization.

[0135] Step S709 : Calculate the intermediate service push communication resource utilization information based on the plurality of intermediate service push resource allocation priority information, intermediate service push communication rate information, and intermediate service push channel gain information.

[0136] In this embodiment, communication resource utilization is re-evaluated based on the resource allocation priority, communication rate, and channel gain in the final intermediate parameters. For example, after optimization, the bandwidth occupancy of the high-priority service increases to 70%, and the channel gain increases by 10dB, resulting in a calculated resource utilization of 0.9. Communication resource utilization information for intermediate service push is generated to verify the optimized resource utilization efficiency.

[0137] Step S710 , calculating and obtaining a plurality of intermediate service information push quality metric information according to the plurality of intermediate user service push matching degree information, intermediate service push communication resource utilization information and preset service information push quality metric weight information.

[0138] In this embodiment, a weighted calculation is performed on the intermediate user service push matching information and the intermediate service push communication resource utilization information. For example, if the final intermediate parameter matching degree is 0.95 and the resource utilization is 0.9, the weighted quality metric value is 0.95 × 0.6 + 0.9 × 0.4 = 0.93. Multiple intermediate service information push quality metrics are generated to quantify the overall performance of the final parameter combination.

[0139] Step S711: The intermediate service information push device state parameter information corresponding to the maximum value of the plurality of intermediate service information push quality metric information is used as the target service information push device state parameter information.

[0140] In this embodiment, the maximum value is selected from multiple intermediate service information push quality metrics, and the corresponding intermediate service information push device state parameter information is used as the target parameter. For example, the parameter combination with the highest quality metric value (matching degree 0.95, resource utilization 0.9) is determined as the target service information push device state parameter information, ensuring that service push accurately matches user needs while efficiently utilizing communication resources.

[0141] The service information push method provided in the embodiment of the present application combines community service needs with user behavior predictions to generate priorities and recommendation types, then associates device status with preset resource standards to generate initial parameters, and dynamically adjusts resource allocation, communication rate and other parameters through iterative optimization, thereby achieving deep coupling of service needs, user behavior and device resources. This method not only ensures that high-priority services have priority access to high-quality communication resources, but also iteratively optimizes by quantifying matching and resource utilization, so that the target parameters can maximize user needs and achieve efficient scheduling of communication resources, further improving the accuracy of service push and the efficiency of system resource utilization, and providing more scientific decision-making support for the intelligent service of smart communities.

[0142] Corresponding to the method of the above embodiment, Figure 8A structural block diagram of the service information push system provided by an embodiment of the present application is shown. For ease of explanation, only the parts related to the embodiment of the present application are shown. Figure 8 The exemplary service information push system may be the execution subject of the service information push method provided in the aforementioned first embodiment.

[0143] Reference Figure 8 , the service information push system includes:

[0144] Information acquisition module 810, used to obtain multiple user service demand monitoring information, service information push device status information and user service behavior information;

[0145] The community service demand information generating module 820 is used to classify and process the user service demand monitoring information to obtain a plurality of community service demand information;

[0146] The service push device communication status parsing information generating module 830 is configured to parse the service information push device status information to obtain multiple pieces of service push device communication status parsing information;

[0147] A user service behavior prediction information generation module 840 is configured to perform analysis and prediction calculations based on the user service behavior information to obtain a plurality of user service behavior prediction information;

[0148] An initial service information push device state parameter information generating module 850 is configured to obtain a plurality of initial service information push device state parameter information based on the plurality of community service demand information, service push device communication state parsing information, user service behavior prediction information, and preset user service recommended communication resource information;

[0149] The target service information push device state parameter information generation module 860 is used to iteratively optimize the multiple initial service information push device state parameter information to obtain the target service information push device state parameter information, so as to push service information according to the target service information push device state parameter information through the service information push device.

[0150] The process of each module realizing its own function in the service information push system provided in the embodiment of the present application can be specifically referred to the aforementioned Figure 1 The description of the first embodiment is omitted here.

[0151] It should be understood that the size of the serial numbers of the steps in the above embodiments does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this application.

[0152] It should be understood that when used in the present specification and the appended claims, the term "comprising" indicates the presence of described features, integers, steps, operations, elements and / or components, but does not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components and / or collections thereof.

[0153] It will also be understood that the term "and / or" used in this specification and the appended claims refers to and includes any and all possible combinations of one or more of the associated listed items.

[0154] As used in this specification and the appended claims, the term "if" can be interpreted as "when" or "upon" or "in response to determining" or "in response to detecting," depending on the context. Similarly, the phrase "if it is determined" or "if [described condition or event] is detected" can be interpreted as meaning "upon determination" or "in response to determining" or "upon detection of [described condition or event]" or "in response to detecting [described condition or event]," depending on the context.

[0155] In addition, in the description of the present specification and the appended claims, the terms "first", "second", "third", etc. are only used to distinguish descriptions and should not be understood as indicating or implying relative importance. It should also be understood that although the terms "first", "second", etc. are used in the text to describe various elements in some embodiments of the present application, these elements should not be limited by these terms. These terms are only used to distinguish one element from another. For example, a first table can be named a second table, and similarly, a second table can be named a first table without departing from the scope of the various described embodiments. Both the first table and the second table are tables, but they are not the same table.

[0156] References to "one embodiment" or "some embodiments" in this specification mean that a particular feature, structure, or characteristic described in conjunction with that embodiment is included in one or more embodiments of the present application. Thus, phrases such as "in one embodiment," "in some embodiments," "in other embodiments," and "in other embodiments" appearing in various places in this specification do not necessarily refer to the same embodiment, but rather mean "one or more but not all embodiments," unless otherwise specifically emphasized. The terms "including," "comprising," "having," and variations thereof all mean "including but not limited to," unless otherwise specifically emphasized.

[0157] The service information push method provided in the embodiments of the present application can be applied to terminal devices such as mobile phones, tablet computers, wearable devices, vehicle-mounted devices, augmented reality (AR) / virtual reality (VR) devices, laptop computers, ultra-mobile personal computers (UMPCs), netbooks, and personal digital assistants (PDAs). The embodiments of the present application do not impose any restrictions on the specific types of terminal devices.

[0158] For example, the terminal device can be a station (STAION, ST) in a WLAN, a cellular phone, a cordless phone, a Session Initiation Protocol (SIP) phone, a Wireless Local Loop (WLL) station, a Personal Digital Assistant (PDA) device, a handheld device with wireless communication function, a computing device or other processing device connected to a wireless modem, a vehicle-mounted device, a vehicle networking terminal, a computer, a laptop computer, a handheld communication device, a handheld computing device, a satellite wireless device, a wireless modem card, a TV set-top box (STB), customer premise equipment (CPE) and / or other devices for communicating on a wireless system and a next-generation communication system, such as a mobile terminal in a 5G network or a mobile terminal in a future evolved Public Land Mobile Network (PLMN) network.

[0159] As an example and not a limitation, when the terminal device is a wearable device, the wearable device can also be a general term for wearable devices that are intelligently designed and developed using wearable technology for daily wear, such as glasses, gloves, watches, clothing and shoes. A wearable device is a portable device that is worn directly on the body or integrated into the user's clothes or accessories. Wearable devices are not only hardware devices, but also achieve powerful functions through software support, data interaction, and cloud interaction. Broadly speaking, wearable smart devices include those that are full-featured, large in size, and can achieve complete or partial functions without relying on smartphones, such as smart watches or smart glasses, as well as those that only focus on a certain type of application function and need to be used in conjunction with other devices such as smartphones, such as various smart bracelets and smart jewelry for vital sign monitoring.

[0160] Figure 9This is a schematic diagram of the structure of a terminal device provided by an embodiment of the present application. Figure 9 As shown, the terminal device 9 of this embodiment includes: at least one processor 90 ( Figure 9 Only one is shown), a memory 91, wherein the memory 91 stores a computer program 92 that can be run on the processor 90. When the processor 90 executes the computer program 92, the steps in the above-mentioned various service information push method embodiments are implemented, such as Figure 1 Alternatively, when the processor 90 executes the computer program 92, the functions of the modules / units in the above-mentioned system embodiments are realized, for example, Figure 8 Functions of modules 810 to 840 are shown.

[0161] The terminal device 9 can be a computing device such as a desktop computer, a notebook, a PDA, a cloud server, etc. The terminal device can include, but is not limited to, a processor 90 and a memory 91. It can be understood by those skilled in the art that Figure 9 It is only an example of the terminal device 9 and does not constitute a limitation on the terminal device 9. It may include more or fewer components than shown in the figure, or a combination of certain components, or different components. For example, the terminal device may also include an input and sending device, a network access device, a bus, etc.

[0162] The processor 90 may be a central processing unit (CPU), other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA), other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or any conventional processor.

[0163] In some embodiments, the memory 91 may be an internal storage unit of the terminal device 9, such as a hard drive or memory of the terminal device 9. The memory 91 may also be an external storage device of the terminal device 9, such as a plug-in hard drive, a Smart Media Card (SMC), a Secure Digital (SD) card, a flash memory card, etc. Furthermore, the memory 91 may include both an internal storage unit of the terminal device 9 and an external storage device. The memory 91 is used to store an operating system, application programs, a boot loader, data, and other programs, such as the program code of the computer program. The memory 91 may also be used to temporarily store data that has been sent or is about to be sent.

[0164] In addition, the functional units in the various embodiments of the present application may be integrated into a single processing unit, or each unit may exist physically separately, or two or more units may be integrated into a single unit. The aforementioned integrated units may be implemented in the form of hardware or software functional units.

[0165] An embodiment of the present application also provides a terminal device, which includes at least one memory, at least one processor, and a computer program stored in the at least one memory and executable on the at least one processor. When the processor executes the computer program, the terminal device implements the steps of any of the above-mentioned method embodiments.

[0166] An embodiment of the present application further provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps in the above-mentioned various method embodiments can be implemented.

[0167] An embodiment of the present application provides a computer program product. When the computer program product is run on a terminal device, the terminal device can implement the steps in the above-mentioned method embodiments when executing the computer program product.

[0168] If the integrated module / unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present application can implement all or part of the processes in the above-mentioned embodiment method by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium. When the computer program is executed by a processor, it can implement the steps of each of the above-mentioned method embodiments. The computer program includes computer program code, which can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium can include: any entity or device that can carry the computer program code, recording medium, USB flash drive, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signal, telecommunication signal and software distribution medium.

[0169] In the above embodiments, the description of each embodiment has its own focus. For parts that are not described or recorded in detail in a certain embodiment, reference can be made to the relevant description of other embodiments.

[0170] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0171] The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of these units may be selected to achieve the purpose of this embodiment according to actual needs.

[0172] The above-described embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. These modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the various embodiments of the present application, and should all be included in the scope of protection of the present application.

Claims

1. A service information push method, characterized in that: include: Obtain multiple user service demand monitoring information, service information push device status information, and user service behavior information; Classify and process the user service demand monitoring information to obtain multiple community service demand information; Parsing the service information push device status information to obtain multiple service information push device communication status parsing information; Analyze and predict the user service behavior information to obtain multiple user service behavior prediction information; Obtaining multiple initial service information push device state parameter information based on the multiple community service demand information, service push device communication state analysis information, user service behavior prediction information, and preset user service recommended communication resource information; Iterative optimization processing is performed on the multiple initial service information push device state parameter information to obtain target service information push device state parameter information, so as to push service information through the service information push device according to the target service information push device state parameter information.

2. The service information push method according to claim 1, wherein: The step of classifying and processing the user service demand monitoring information to obtain a plurality of community service demand information specifically includes: Performing word segmentation processing on the user service demand monitoring information to obtain user service demand text information, user service demand generation time information, and user service demand business type information; Determine emergency community service demand information, high-frequency community service demand information, and general community service demand information based on the user service demand generation time information and the user service demand business type information; Perform keyword matching processing based on the user service demand text information and a preset service demand information database to obtain multiple user service demand text keyword matching information; A plurality of community service demand information is obtained based on the plurality of user service demand text keyword matching information, emergency community service demand information, high-frequency community service demand information and general community service demand information.

3. The service information push method according to claim 1, wherein: The step of parsing the service information push device status information to obtain multiple service information push device communication status parsing information specifically includes: Extracting and processing the service information push device status information to obtain service push device status running time information, service push device transmission power information, service push device channel quality monitoring information, service push device power status information, and service push device resource occupancy information; Calculate service information push device status representation information based on the service push device transmission power information, service push device channel quality monitoring information, service push device power status information, service push device resource occupancy information, and preset service information push device status parsing weight information; A plurality of service push device communication state parsing information is obtained according to the service push device state running time information and the service information push device state representation information.

4. The service information push method according to claim 1, wherein: The step of analyzing and predicting the user service behavior information to obtain a plurality of user service behavior prediction information specifically includes: Performing information extraction processing on the user service behavior information to obtain user service information reception time information, user service usage type information, and user service feedback information; generating a plurality of user service behavior pattern information according to the user service information reception time information, the user service usage type information, and the user service feedback information; Randomly extracting a plurality of user service behavior pattern information according to preset user service behavior pattern reference point quantity information to generate user service behavior pattern reference point information; Calculating the logical distance between the user service behavior pattern information and the user service behavior pattern reference point information to obtain user behavior pattern distance representation information; Generating a plurality of user service behavior pattern group information according to the user behavior pattern distance representation information and the user service behavior pattern reference point information; Calculating the average value of each of the user service behavior pattern group information to obtain the user service behavior pattern group center information; Determining whether the user service behavior pattern group center information is the same as the user service behavior pattern reference point information; If so, performing prediction calculation on the plurality of user service behavior pattern group information to obtain a plurality of user service behavior prediction information; If not, the user service behavior pattern group center information is used as the user service behavior pattern reference point information, and the process returns to the step of calculating the logical distance between the user service behavior pattern information and the user service behavior pattern reference point information to obtain the user behavior pattern distance representation information.

5. The service information push method according to claim 4, wherein: The step of performing prediction calculation on the plurality of user service behavior pattern group information to obtain a plurality of user service behavior prediction information specifically includes: Generate first user service behavior pattern group feature information based on multiple user service behavior pattern group information and a preset first user service behavior pattern feature extraction matrix; generating second user service behavior pattern group feature information based on the plurality of user service behavior pattern group information and a preset second user service behavior pattern feature extraction matrix; Generating third user service behavior pattern group feature information according to the plurality of user service behavior pattern group information and a preset third user service behavior pattern feature extraction matrix; generating user service behavior pattern group interaction characteristic information based on the first user service behavior pattern group characteristic information and the second user service behavior pattern group characteristic information; generating user service behavior pattern group fusion feature information based on the user service behavior pattern group interaction feature information and the third user service behavior pattern group feature information; Obtaining user service behavior pattern group feature mapping information according to the user service behavior pattern group fusion feature information and a preset user service behavior pattern feature mapping matrix; According to a preset user service behavior pattern feature mapping transformation matrix, mapping transformation processing is performed on the user service behavior pattern group feature mapping information to obtain user service behavior pattern group feature mapping transformation information and the number of user service behavior pattern group feature mapping transformations; Determining whether the number of changes in the user service behavior pattern group feature mapping is greater than a preset user service behavior pattern group feature mapping change number threshold; If so, obtaining a plurality of user service behavior prediction information according to the user service behavior pattern group feature mapping transformation information; If not, the user service behavior pattern group feature mapping transformation information is used as the user service behavior pattern group fusion feature information, and the process returns to the step of obtaining the user service behavior pattern group feature mapping information based on the user service behavior pattern group fusion feature information and the preset user service behavior pattern feature mapping matrix.

6. The service information push method according to claim 1, wherein: The step of obtaining a plurality of initial service information push device state parameter information based on the plurality of community service demand information, service push device communication state analysis information, user service behavior prediction information, and preset user service recommended communication resource information specifically includes: Generate multiple service demand priority information and multiple user service recommendation type information based on the community service demand information and the user service behavior prediction information; the service demand priority information corresponds to the user service recommendation type information in a one-to-one manner; Generate multiple service recommendation priority resource occupancy information based on the service demand priority information, user service recommendation type information, service push device communication status analysis information, and preset user service recommendation communication resource information; A plurality of initial service information push device state parameter information is generated according to the plurality of service recommendation priority resource occupancy information.

7. The service information push method according to claim 6, wherein: The initial service information push device state parameter information includes initial service push resource allocation priority information, initial service push communication rate information, and initial service push channel gain information; the initial service push resource allocation priority information corresponds to the service demand priority information one by one; The step of iteratively optimizing the plurality of initial service information push device state parameter information to obtain target service information push device state parameter information, and pushing service information according to the target service information push device state parameter information by the service information push device specifically includes: Calculating initial user service push matching degree information based on the user service recommendation type information corresponding to the plurality of community service demand information and the initial service push resource allocation priority information; Calculating initial service push communication resource utilization information based on the plurality of initial service push resource allocation priority information, initial service push communication rate information, and initial service push channel gain information; Calculating a plurality of initial service information push quality measurement information based on the plurality of initial user service push matching degree information, the initial service push communication resource utilization information, and the preset service information push quality measurement weight information; using the initial service information push device state parameter information corresponding to the maximum value of the plurality of initial service information push quality metric information as service information push device state parameter optimization benchmark information; Based on the plurality of initial service information push device state parameter information, the service information push device state parameter optimization benchmark information, and the preset service information push device state parameter optimization step information, a plurality of intermediate service information push device state parameter information and intermediate service information push device state parameter optimization times information are obtained; the intermediate service information push device state parameter information includes intermediate service push resource allocation priority information, intermediate service push communication rate information, and intermediate service push channel gain information; the intermediate service push resource allocation priority information corresponds one-to-one to the service demand priority information; Determine whether the intermediate service information push device state parameter optimization number information is less than a preset service information push device state parameter optimization iteration number threshold; If so, the plurality of intermediate service push resource allocation priority information is used as the initial service push resource allocation priority information, the intermediate service push communication rate information is used as the initial service push communication rate information, and the intermediate service push channel gain information is used as the initial service push channel gain information, and the process returns to the step of calculating the initial user service push matching degree information based on the user service recommendation type information corresponding to the plurality of community service demand information and the initial service push resource allocation priority information; If not, calculating the intermediate user service push matching degree information based on the user service recommendation type information corresponding to the plurality of community service demand information and the intermediate service push resource allocation priority information; Calculating intermediate service push communication resource utilization information based on the plurality of intermediate service push resource allocation priority information, intermediate service push communication rate information, and intermediate service push channel gain information; Calculating a plurality of intermediate service information push quality measurement information based on the plurality of intermediate user service push matching degree information, the intermediate service push communication resource utilization information, and the preset service information push quality measurement weight information; The intermediate service information push device state parameter information corresponding to the maximum value of the plurality of intermediate service information push quality metric information is used as the target service information push device state parameter information.

8. A service information push system, characterized in that: include: Information acquisition module, used to obtain multiple user service demand monitoring information, service information push device status information and user service behavior information; A community service demand information generating module is used to classify and process the user service demand monitoring information to obtain a plurality of community service demand information; a service push device communication status parsing information generating module, configured to parse and process the service information push device status information to obtain a plurality of service push device communication status parsing information; A user service behavior prediction information generation module is used to analyze and predict the user service behavior information to obtain multiple user service behavior prediction information; An initial service information push device state parameter information generation module is configured to obtain a plurality of initial service information push device state parameter information based on the plurality of community service demand information, service push device communication state analysis information, user service behavior prediction information, and preset user service recommended communication resource information; The target service information push device state parameter information generation module is used to iteratively optimize the multiple initial service information push device state parameter information to obtain the target service information push device state parameter information, so as to push service information according to the target service information push device state parameter information through the service information push device.

9. A terminal device, characterized in that: The terminal device includes a memory and a processor, wherein the memory stores a computer program that can be run on the processor, and when the processor executes the computer program, the steps of the method according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

Images