A method and system for matching private numbers with local information of calling and called numbers

Abstract

The present invention relates to a method and system for matching private numbers with local information of calling and called numbers, belonging to the field of communication technology, and the method comprises: user input and request submission steps; preprocessing and strategy selection steps; private number search and allocation steps; allocation result feedback steps; subsequent processing and resource optimization steps. The present invention realizes accurate allocation of private numbers by introducing local information and matching strategies, meets users' specific requirements for number locality, and optimizes the utilization efficiency of number resources.

Description

Technical Field

[0001] The present invention relates to the field of communication technology, and in particular to a method and system for matching a privacy number based on location information of a calling or called number. Background Art

[0002] With the rapid development of communication technology and the increasing awareness of users about privacy protection, the privacy communication system has gradually become an important part of the communication industry. The system allocates temporary privacy numbers to users to hide the numbers during calls, effectively protecting the users' personal privacy. However, in actual applications, users have more sophisticated requirements for the allocation of privacy numbers, especially hoping that the location of the privacy number can be consistent with the location of the calling and called numbers or at least in the same province, so as to enhance the authenticity and credibility of the communication.

[0003] In the prior art, random allocation and number resource restriction are usually used to allocate numbers. However, for the random allocation method, most current privacy communication systems use the method of randomly allocating privacy numbers, which cannot meet the needs of users for specific requirements of number locations. As for the number resource restriction method, due to the limited privacy number resources, it is impossible to cover all cities and counties, resulting in users being unable to obtain privacy numbers that fully match their needs. In summary, the prior art lacks flexible matching strategy settings and cannot be personalized according to different user needs. Summary of the invention

[0004] The purpose of the present invention is to provide a method and system for matching the privacy number with the local information of the calling and called numbers. By introducing local information and matching strategies, the accurate allocation of privacy numbers can be achieved, the user's specific requirements for number location can be met, and the utilization efficiency of number resources can be optimized.

[0005] A first aspect of the present invention provides a method for matching a private number with a calling or called number location information, the method comprising:

[0006] User input and request submission steps: The user enters the calling and called numbers, location information, target city, alternative cities, and selected matching strategies through the system interface; all necessary fields must be filled in and the format is correct, and the system verifies the integrity and validity of the input information in real time;

[0007] Preprocessing and strategy selection step: Determine the initial search scope and allocation logic based on the matching strategy selected by the user;

[0008] Privacy number search and allocation steps: According to the preset search order, first the target city, then the same province, and then the whole country, start searching the privacy number pool;

[0009] Allocation result feedback step: providing real-time feedback of the allocation result to the user;

[0010] Subsequent processing and resource optimization steps: Regularly analyze allocation data to identify hot and cold areas of number resource usage.

[0011] In combination with the first aspect, further, the user input is multi-dimensional user input. The user not only provides the calling and called numbers, but also needs to clearly specify the territorial information of these numbers, and the territorial information is identified by province, city, district codes or area codes; when the user proposes further detailed requirements, one or more target cities are accurately specified as the preferred allocation area for the privacy number through the target city field; the alternative city field is introduced as an alternative, allowing the user to specify the suboptimal city option that the system should consider when there are no available numbers in the preferred target city.

[0012] In combination with the first aspect, further, the matching strategy selected by the user further includes: a strict matching strategy, the system only searches the privacy number pool within the target city specified by the user. If there are no available numbers in all target cities, the allocation fails and the specific reason is fed back to the user; a semi-strict matching strategy: first try to allocate in the target city. If it fails, the search range is automatically expanded to other cities in the same province as the user-specified city. If there are still no available numbers in the same province, whether to continue searching is determined by whether the user has set a secondareacode for an alternative city. Otherwise, the allocation fails; a non-strict matching strategy: first try to allocate in the order of strict matching and semi-strict matching. If both fail, the restrictions are further relaxed to search for available privacy numbers nationwide.

[0013] In combination with the first aspect, further, the privacy number search and allocation further includes: in each search stage, checking whether the number resources within the current range meet user needs, and the user needs refer to whether they meet the specific number type required by the user or whether they meet the specific number segment required by the user; if an available number is found, an allocation operation is performed, the number pool status is updated, and an allocation result record is generated; if there is no available number within the current search range, it is decided whether to continue searching the next range based on the matching strategy; the allocation result record includes the assigned privacy number or the reason for the allocation failure; if the allocation is successful, instructions and precautions for the use of the privacy number can also be provided; if the allocation fails, corresponding suggestions will be provided based on the matching strategy selected by the user or the user will be guided to readjust the input information.

[0014] In combination with the first aspect, further, the subsequent processing and resource optimization step further includes:

[0015] Maintain a dynamically updated privacy number pool, including number resources in various cities and their current status; use intelligent prediction algorithms to predict possible future number needs based on historical allocation data and current number usage, and allocate and optimize resources in advance; automatically adjust the number pool allocation strategy and resource allocation ratio based on the analysis results of the intelligent prediction algorithm to optimize overall utilization efficiency; for privacy numbers that have not been used for a long time, the system can automatically recycle them and re-incorporate them into the number pool for management, realizing an automatic recovery and reallocation mechanism for number resources to ensure efficient use of the number pool.

[0016] In combination with the first aspect, further, the semi-strict matching strategy further includes:

[0017] Input information parsing step: parsing the target city code list and the alternative city code list input by the user;

[0018] Preferred city allocation step: traverse each area code in the target city list, query the privacy number pool corresponding to the area code for the area code, and check whether there is an available number; if there is an available number, allocate the number to the user and end the allocation process; if there is no available number under the area code, continue to try the next area code; if there is no available number in all preferred cities, enter the extended allocation of cities in the same province: for each preferred city, obtain the province information where it is located; traverse other cities in the province except the preferred city, and for each city, query the privacy number pool of the city to check whether there is an available number; if there is an available number, allocate the number to the user and end the allocation process; if there is no available number in all other cities in the province, continue to consider the province where the next preferred city is located;

[0019] Alternative city allocation step: If the user provides an alternative city, and the above steps fail to successfully allocate numbers, then the list of alternative cities is traversed, and the same allocation steps as the preferred city are performed on the alternative cities;

[0020] Allocation logging: If all attempts fail, the allocation failure is logged and feedback is provided to the user.

[0021] In combination with the first aspect, further, a weighted allocation algorithm is used to manage the number pool, specifically comprising the following steps:

[0022] Data collection and preprocessing: Collect the allocation records of privacy numbers in various cities over the past period of time, including the allocation time, quantity and user type; also collect external data sources, including population data, economic development level and communication activity of cities;

[0023] Construct demand prediction features: Based on historical allocation data, a time series model is constructed to predict the demand for privacy numbers in various cities in the future; population, economic level and communication activity are converted into quantifiable specific features such as population density, GDP growth rate and average daily call volume;

[0024] Ensemble learning and time series prediction: Use multiple basic models to make predictions separately, and then input the prediction results as new features into a meta-model to obtain the final prediction probability P(Ai); use a weighted allocation algorithm to assign a weight wi to each city, wi=f(P(Ai), population, economic level), where f is a function that comprehensively evaluates various factors and gives weights. P(Ai) represents the probability that the number demand of city Ai will be met in the future.

[0025] Introducing the attention mechanism: In the LSTM or Transformer model, by adding an attention layer to dynamically adjust the weights of different input features or time steps, the number demand of prefecture-level cities Ai can be more accurately predicted;

[0026] Weight calculation function:

[0027] wi = α·P(Ai)+β·population density i+γ·GDP growth rate i+δ·average daily call volume i;

[0028] Among them, α, β, γ, and δ are coefficients obtained through genetic algorithms, particle swarm optimization, or weight allocation based on expert experience, which are used to adjust the influence of different features on the weights, and i refers to different prefecture-level cities;

[0029] Dynamic weight adjustment: When a specific event is detected, the weight adjustment algorithm is automatically triggered to dynamically adjust the weights of relevant cities according to the nature and scope of the event; a closed-loop mechanism of user feedback and weight adjustment is established to adjust the weight coefficients α, β, γ, δ in real time according to the distribution efficiency of user satisfaction.

[0030] Introduce fuzzy logic: define fuzzy sets and fuzzy rules, transform the input features of population density, GDP growth rate, and average daily call volume into fuzzy variables; calculate the weight of each city in different fuzzy states according to fuzzy rules, and finally obtain the final weight wi through the defuzzification process;

[0031] Regional association analysis based on graph neural network: Construct a city-to-city association graph, where nodes represent cities and edges represent certain associations between cities. Use the GNN model to propagate information on the graph and learn the embedding representation of each city, which contains the information of its neighboring cities. Calculate the weight wi based on the learned embedding representation, so that the weight depends not only on the characteristics of the city itself, but also takes into account the influence of its neighboring cities.

[0032] Allocation strategy optimization: According to the calculated weight wi, cities are sorted by priority to form a priority queue; when allocating numbers, first try to allocate from the cities with the highest priority; for cities with higher weights, reserve a certain proportion of privacy number resources to ensure rapid response during peak demand; establish a user feedback mechanism to collect user satisfaction data on allocation results, which is used to further optimize the model and weight allocation strategy;

[0033] Intelligent management: It has self-learning capabilities and can continuously optimize the prediction model and weight calculation function based on historical allocation results and user feedback; it introduces anomaly detection mechanisms to promptly detect and handle abnormal allocation situations.

[0034] A second aspect of the present invention provides a system for matching the location information of the calling and called numbers with the privacy number nearby, the system comprising:

[0035] User input and request submission module: Users input the calling and called numbers, location information, target cities, alternative cities, and selected matching strategies through the system interface; all necessary fields must be filled in and the format is correct, and the system verifies the integrity and validity of the input information in real time;

[0036] Preprocessing and strategy selection module: The system determines the initial search scope and allocation logic based on the matching strategy selected by the user;

[0037] Privacy number search and allocation module: The system starts searching the privacy number pool in the preset search order, first the target city, then the same province, and then the whole country;

[0038] Allocation result feedback module: the system will provide real-time feedback of allocation results to users;

[0039] Subsequent processing and resource optimization module: The system regularly analyzes allocation data and identifies hot and cold areas of number resource usage.

[0040] A third aspect of the present invention provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of a method for matching the location information of a calling and called number with a privacy number nearby.

[0041] The fourth aspect of the present invention provides a computer device, including: a memory for storing a computer program; a processor for executing the computer program to implement the steps of a method for matching the location information of a calling and called number with a privacy number nearby.

[0042] The key points of the present invention are as follows:

[0043] Introduce territorial information and matching strategies as the basis for privacy number allocation to improve the accuracy and flexibility of allocation.

[0044] A progressive allocation logic has been designed from the target city to the same province and then to the whole country to ensure that user needs are met as much as possible with limited resources.

[0045] A variety of matching strategies are provided for users to choose from, meeting personalized needs in different scenarios. The present invention can be applied to China Unicom's online privacy communication service system.

[0046] The present invention has the following advantages: providing a flexible and efficient privacy number allocation method and mechanism, realizing accurate allocation of privacy numbers by introducing territorial information and matching strategies, meeting users' specific requirements for number territories, and optimizing the utilization efficiency of number resources. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] Figure 1 It is a flowchart of the steps of an embodiment of a method for matching the location information of a calling and called number with a privacy number nearby according to the present invention;

[0048] Figure 2 It is a schematic diagram of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0049] It should be noted that, in the absence of conflict, the embodiments and features in the embodiments of the present application can be combined with each other. The present invention will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

[0050] The present invention aims to provide a method and system for matching the local information of the calling and called numbers with the nearest private number, so as to solve the problems in the existing private communication system that the allocation of private numbers is highly random, cannot meet the specific local requirements of users, and the number resource allocation is inflexible. The core of the present invention is to achieve accurate, efficient and flexible allocation of private numbers by introducing detailed user input information (including the calling and called numbers, local information, target cities and candidate cities, and complex matching strategy settings), combined with advanced algorithms and data processing technologies.

[0051] 1. Multi-dimensional user input:

[0052] Users not only provide the calling and called numbers, but also need to clearly specify the location information of these numbers (such as through province, city, district or area code identification).

[0053] Users can further refine their requirements, as shown in Table 1, and use the Target City field to accurately specify one or more target cities as the preferred allocation area for privacy numbers.

[0054] The secondareacode field for alternative cities is introduced as an alternative, allowing users to specify the second-best city option that the system should consider when there are no available numbers in the preferred target city.

[0055] Provides flexible matching strategy options, including but not limited to strict matching, semi-strict matching, and non-strict matching. Users can choose the most suitable matching strategy according to their own needs.

[0056] 2. Implement complex matching strategies:

[0057] Strict match: The system only searches the private number pool within the target city or city specified by the user (multiple numbers can be supported). If there are no available numbers in all target cities or cities, the allocation fails and the specific reason is fed back to the user.

[0058] Semi-strict match: First try to allocate in the target city. If it fails, the search range will be automatically expanded to other cities in the same province as the user-specified city. If there is still no available number in the same province, whether to continue searching will be determined based on whether the user has set an alternative city (secondareacode). Otherwise, the allocation fails.

[0059] Non-strict matching: First, the allocation is attempted in the order of strict matching and semi-strict matching. If both fail, the restrictions are further relaxed to search for available privacy numbers nationwide.

[0060] 3. Manage smart number pool:

[0061] The system maintains a dynamically updated privacy number pool, which includes number resources in various cities and their current status (such as whether they have been allocated).

[0062] Introduce intelligent prediction algorithms to predict possible future number demands based on historical allocation data and current number usage, and allocate and optimize resources in advance.

[0063] Implement automatic recovery and reallocation mechanism of number resources to ensure efficient use of number pool.

[0064] 4. User interaction and feedback:

[0065] Provides an intuitive and easy-to-use user interface to guide users through the process of binding a private number, including entering information, selecting a matching strategy, etc.

[0066] During the allocation process, users will be provided with real-time feedback on the allocation progress and results, including successfully allocated privacy numbers, reasons for allocation failures, and recommended follow-up operations.

[0067] Allows users to readjust input information or matching strategies and re-initiate allocation requests after allocation fails.

[0068]

[0069] Table 1 Field name type correspondence table

[0070] The specific process of the present invention is as follows Figure 1 As shown:

[0071] Step 1: User input and request submission:

[0072] The user enters the calling and called numbers, location information, target city (multiple), alternative city (optional) and selected matching strategy through the system interface.

[0073] The system verifies the completeness and validity of the input information, ensuring that all required fields are filled in and in the correct format.

[0074] The user input of the present invention is a multi-dimensional user input. The user not only provides the calling and called numbers, but also needs to clearly specify the territorial information of the numbers, and the territorial information is identified by the province, city, district code or area code; when the user proposes further detailed requirements, one or more target cities are accurately specified as the preferred allocation area for the privacy number through the target city field; the alternative city field is introduced as an alternative, allowing the user to specify the suboptimal city option to be considered when there is no available number in the preferred target city.

[0075] Step 2: Preprocessing and strategy selection:

[0076] The system determines the initial search scope and allocation logic based on the matching strategy selected by the user.

[0077] If the user selects non-strict matching, the system automatically sets the search scope to nationwide; if semi-strict matching or strict matching is selected, the system will initialize the settings based on the target city and alternative cities specified by the user.

[0078] The invention provides a method for matching the location information of the calling and called numbers with the nearest private number. The innovation lies in its complex matching strategy implementation, especially the "semi-strict matching" strategy, which combines accuracy and flexibility to meet the diverse needs of different users. The following is a detailed algorithm step and description of the "semi-strict matching" strategy:

[0079] Traditional privacy number allocation systems often use strict territorial matching or completely random allocation methods, while the "semi-strict matching" strategy provides a more flexible and intelligent solution. It first attempts to allocate in the user's preferred city. If it cannot be met, it will automatically expand to other cities in the same province. This expansion strategy not only takes into account the user's territorial preferences, but also makes full use of existing number resources and improves the allocation success rate.

[0080] Detailed steps of the "semi-strict matching" algorithm:

[0081] 1. Input information analysis:

[0082] Parse the areacode (target area code list, which can contain multiple areas) and secondareacode (alternative area code list, which is optional) entered by the user.

[0083] Verify the validity of the input, such as whether the area code is within the range supported by the system.

[0084] 2. Try to allocate the preferred cities:

[0085] Iterate through each area code in the areacode list and perform the following steps for each area code:

[0086] Query the privacy number pool corresponding to the area code to check whether there are available numbers.

[0087] If there is an available number, the number is allocated to the user and the allocation process ends.

[0088] If no numbers are available in that area code, it will try the next area code.

[0089] If there are no available numbers in all preferred cities, proceed to the next step.

[0090] 3. Expansion distribution within the same province, city or district:

[0091] For each preferred city, obtain the province information where it is located.

[0092] Traverse all cities in the province except the first city (this can be achieved by querying the province-city mapping table), and perform the following steps for each city:

[0093] Query the privacy number pool of the city to check whether there are available numbers.

[0094] If there is an available number, the number is allocated to the user and the allocation process ends.

[0095] If no numbers are available in all other cities within the province, the province where the next preferred city is located will be considered (if there are multiple preferred cities in different provinces).

[0096] 4. Alternative city allocation attempt (if set):

[0097] If the user provides a secondareacode and the above steps fail to successfully allocate a number, the secondareacode list is traversed and the same allocation attempt process as the preferred city is performed for each alternative city.

[0098] 5. Handling allocation failure:

[0099] If all attempts fail, the reason for the allocation failure will be recorded (such as "there are no available numbers in all target cities and cities in the same province") and feedback will be provided to the user.

[0100] Although the "semi-strict matching" strategy mainly relies on logical judgment and database query and does not involve complex mathematical formulas, a probability-based prediction model can be introduced to optimize number pool management as a supplement to algorithm innovation.

[0101] Assume that P(Ai) represents the probability that the number demand of city Ai will be met in the future, which can be calculated based on historical allocation data. The system can dynamically adjust the allocation priority and resource allocation strategy of the privacy number pool based on this probability value.

[0102] For example, a weighted allocation algorithm can be designed to assign a weight wi to each city. The weight calculation can be based on P(Ai) and other factors (such as the city’s population, economic development level, etc.):

[0103] wi=f(P(Ai), population, economic level)

[0104] Where f is a function designed according to the specific situation, which is used to comprehensively evaluate various factors and give weights. When allocating numbers, the system can give priority to cities with higher weights.

[0105] Although such a design goes beyond the direct scope of the "semi-strict matching" strategy, it provides ideas for the overall optimization of the privacy number allocation system and reflects the continuity and extensibility of algorithm innovation.

[0106] To further enhance the innovation and practicality of the weighted allocation algorithm, we can design it to be more detailed and dynamic, while incorporating more data analysis and machine learning elements. The following is a more detailed and innovative algorithm description:

[0107] Innovative weighted allocation algorithm

[0108] 1. Data Collection and Preprocessing

[0109] Historical allocation data: collects the allocation records of privacy numbers in various cities over a period of time, including allocation time, quantity, user type and other information.

[0110] External data sources: Integrate external data sources such as population data of cities, economic development level (such as GDP, per capita income, etc.), communication activity (such as number of mobile phone users, call duration, etc.), etc.

[0111] 2. Feature Construction

[0112] Demand forecasting features: Based on historical allocation data, a time series model (such as ARIMA, LSTM, etc.) is constructed to predict the demand for privacy numbers in various cities in the future.

[0113] Characteristics of influencing factors: Convert external data sources such as population, economic level, and communication activity into quantifiable characteristics, such as population density, GDP growth rate, and average daily call volume.

[0114] 3. Innovation of Probabilistic Forecasting Model

[0115] 3.1 Combination of Ensemble Learning and Time Series Forecasting

[0116] Innovation: Not only can we use traditional machine learning or deep learning models for prediction, but we can also combine ensemble learning (such as Stacking, Blending) with time series prediction (such as LSTM, ARIMA). First, we use multiple basic models (such as random forest, GBDT, LSTM, etc.) to make predictions separately, and then input these prediction results into a meta-model as new features to obtain the final prediction probability P(Ai).

[0117] Advantages: This method can make full use of the advantages of different models and improve the accuracy and robustness of predictions.

[0118] 3.2 Introducing the Attention Mechanism

[0119] Introducing the attention mechanism into the deep learning model enables the model to automatically learn and focus on the features or time periods that have the greatest impact on the prediction results.

[0120] Implementation: In models such as LSTM or Transformer, by adding an attention layer to dynamically adjust the weights of different input features or time steps, the number demand of city Ai can be predicted more accurately. In short, the time step here is each unit arranged in chronological order in the sequence data, such as every day, every hour in the time series data. In the scenario of number demand prediction, each time step may represent the observed value of number usage or related influencing factors of city Ai in different time periods.

[0121] 4. Innovation of weight calculation function

[0122] The design of the comprehensive evaluation function f should take into account the balance of multiple dimensions. A possible function form is: wi = α·P(Ai)+β·population density i+γ·GDP growth rate i+δ·average daily call volume i;

[0123] Among them, α, β, γ, and δ are coefficients obtained through optimization algorithms (such as genetic algorithms, particle swarm optimization, etc.) or weight allocation based on expert experience, which are used to adjust the influence of different characteristics on the weights; i refers to different prefecture-level cities.

[0124] 4.1 Dynamic Weight Adjustment Mechanism

[0125] A dynamic weight adjustment mechanism based on real-time data is designed so that the weight wi can be automatically adjusted according to the real-time operating status of the system and changes in the external environment.

[0126] Implementation method: Event-driven adjustment: When the system detects a specific event (such as a natural disaster, a large-scale event, etc.), it automatically triggers the weight adjustment algorithm to dynamically adjust the weights of the relevant cities based on the nature and scope of the event.

[0127] Feedback loop adjustment: Establish a closed-loop system of user feedback and weight adjustment, and adjust the weight coefficients α, β, γ, δ in real time based on feedback indicators such as user satisfaction and allocation efficiency.

[0128] 4.2 Introduction of Fuzzy Logic

[0129] Fuzzy logic is introduced into the weight calculation function to deal with the uncertainty and ambiguity in the input data.

[0130] Implementation method: Define fuzzy sets and fuzzy rules, and convert input features such as population density, GDP growth rate, and average daily call volume into fuzzy variables.

[0131] The weight of each city in different fuzzy states is calculated according to fuzzy rules, and finally the final weight wi is obtained through the defuzzification process.

[0132] 4.3 Regional Correlation Analysis Based on Graph Neural Network

[0133] Graph Neural Network (GNN) is used to analyze the correlation and mutual influence between cities, so as to calculate the weights more accurately.

[0134] Implementation method: Construct a city-to-city relationship graph, in which nodes represent cities and edges represent some kind of relationship between cities (such as geographical proximity, close economic ties, etc.).

[0135] Use the GNN model to propagate information on the graph and learn the embedding representation of each city, which contains the information of its neighboring cities.

[0136] The weight wi is calculated based on the learned embedding representation, so that the weight not only depends on the characteristics of the city itself, but also takes into account the influence of its neighboring cities.

[0137] These innovations can significantly improve the intelligence level and allocation efficiency of the privacy number allocation system, and provide strong technical support for patent applications.

[0138] 5. Allocation strategy optimization

[0139] Priority queue: According to the calculated weight wi, the cities are sorted by priority to form a priority queue. When allocating numbers, the system first tries to allocate from the city with the highest priority.

[0140] Resource reservation: For cities with higher weights, the system can reserve a certain proportion of privacy number resources to ensure a rapid response during peak demand.

[0141] Feedback mechanism: Establish a user feedback mechanism to collect user satisfaction data on allocation results for further optimization of the model and weight allocation strategy.

[0142] 6. Intelligent management

[0143] Adaptive learning: The system should have self-learning capabilities and be able to continuously optimize the prediction model and weight calculation function based on historical allocation results and user feedback.

[0144] Anomaly detection: Introduce anomaly detection mechanism to promptly detect and handle abnormal allocation situations, such as the resource imbalance problem caused by a large number of numbers being concentrated in a few cities.

[0145] Through the above design, the weighted allocation algorithm not only realizes the intelligent management of the privacy number allocation process, but also improves the accuracy and flexibility of allocation, and better meets the diverse needs of different users. At the same time, the innovation of the algorithm is reflected in its comprehensive use of data analysis, machine learning and dynamic adjustment strategies, which provides strong support for the continuous optimization of the privacy number allocation system.

[0146] The user-selected matching strategies of the present invention include: strict matching, the system only searches the privacy number pool within the target city specified by the user. If there are no available numbers in all target cities, the allocation fails and the specific reasons are fed back to the user; semi-strict matching: first try to allocate in the target city. If it fails, the search range is automatically expanded to other cities in the same province as the user-specified city. If there are still no available numbers in the same province, whether to continue searching is determined based on whether the user has set up alternative cities. Otherwise, the allocation fails; non-strict matching: first try to allocate in the order of strict matching and semi-strict matching. If both fail, the restrictions are further relaxed to search for available privacy numbers nationwide.

[0147] Step 3: Privacy number search and allocation:

[0148] The system starts searching the privacy number pool in a preset search order (such as the target city first, then the same province, and then the whole country).

[0149] At each search stage, the system checks whether the number resources in the current range meet user requirements (such as number type, number segment, etc.).

[0150] If an available number is found, the allocation operation is performed, the number pool status is updated, and an allocation result record is generated. The allocation result record includes the allocated privacy number or the reason for the allocation failure; if the allocation is successful, the system can also provide instructions and precautions for the use of the privacy number; if the allocation fails, the system will provide corresponding suggestions based on the matching strategy selected by the user or guide the user to readjust the input information.

[0151] If there are no available numbers in the current search range, the matching strategy determines whether to continue searching the next range.

[0152] The system maintains a dynamically updated privacy number pool, which includes number resources in various cities and their current status (such as whether they have been allocated).

[0153] Introduce intelligent prediction algorithms to predict possible future number demands based on historical allocation data and current number usage, and allocate and optimize resources in advance.

[0154] The automatic recycling and reallocation mechanism of number resources is realized to ensure the efficient use of the number pool. The privacy number search and allocation of the present invention includes: in each search stage, the system checks whether the number resources in the current range meet the user's needs, and the user needs refer to whether the specific number type required by the user is met or whether the specific number segment required by the user is met; if an available number is found, the allocation operation is performed, the number pool status is updated, and the allocation result record is generated; if there is no available number in the current search range, it is determined whether to continue searching the next range according to the matching strategy.

[0155] Step 4: Feedback on distribution results:

[0156] The system will provide real-time feedback of the allocation results (including the allocated privacy number or the reason for allocation failure) to the user.

[0157] If the allocation is successful, the system can also provide instructions and precautions for the use of the privacy number.

[0158] If the allocation fails, the system will provide corresponding suggestions or guide the user to readjust the input information based on the matching strategy selected by the user.

[0159] Provides an intuitive and easy-to-use user interface to guide users through the process of binding a private number, including entering information, selecting a matching strategy, etc.

[0160] During the allocation process, users will be provided with real-time feedback on the allocation progress and results, including successfully allocated privacy numbers, reasons for allocation failures, and recommended follow-up operations.

[0161] Allows users to readjust input information or matching strategies and re-initiate allocation requests after allocation fails.

[0162] Step 5: Subsequent processing and resource optimization:

[0163] The system regularly analyzes allocation data to identify hot and cold areas of number resource usage.

[0164] Based on the analysis results, the number pool allocation strategy and resource allocation ratio are automatically adjusted to optimize the overall utilization efficiency.

[0165] For privacy numbers that have not been used for a long time, the system can automatically recycle them and add them back to the number pool for management.

[0166] Furthermore, the present invention maintains a dynamically updated privacy number pool, which includes number resources in various cities and their current status; uses an intelligent prediction algorithm based on historical allocation data and current number usage to predict possible future number demands, and allocates and optimizes resources in advance; automatically adjusts the allocation strategy and resource allocation ratio of the number pool based on the analysis results of the intelligent prediction algorithm to optimize the overall utilization efficiency; for privacy numbers that have not been used for a long time, the system can automatically recycle them and re-incorporate them into the number pool for management, thereby realizing an automatic recovery and reallocation mechanism for number resources and ensuring efficient use of the number pool.

[0167] In addition, the present invention provides an intuitive and easy-to-use user interface to guide users through the binding process of private numbers, including inputting information and selecting matching strategies; during the allocation process, the allocation progress and results are fed back to users in real time, including the successfully allocated private numbers, the reasons for allocation failures, and recommended follow-up operations; and the user is allowed to readjust the input information or matching strategies after allocation failures and re-initiate allocation requests. The innovations of the present invention are:

[0168] The territorial information and matching strategies are introduced as the basis for the allocation of privacy numbers to improve the accuracy and flexibility of allocation. A progressive allocation logic is designed from the target city to the same province and then to the whole country to ensure that user needs are met as much as possible with limited resources. A variety of matching strategies are provided for users to choose from to meet personalized needs in different scenarios.

[0169] The present invention can be applied to China Unicom's online privacy communication service system.

[0170] Furthermore, the present invention provides a computer device, such as Figure 2 As shown, the electronic device includes one or more processors and memory. The processor may be a central processing unit (CPU) or other forms of processing units with data processing capabilities and / or instruction execution capabilities, and may control other components in the electronic device to perform desired functions. The memory may include one or more computer program products, and the computer program product may include various forms of computer-readable storage media, such as volatile memory and / or non-volatile memory. The volatile memory may include, for example, a random access memory (RAM) and / or a cache memory (cache), etc. The non-volatile memory may include, for example, a read-only memory (ROM), a hard disk, a flash memory, etc. One or more computer program instructions may be stored on the computer-readable storage medium, and the processor may run the program instructions to implement the method for information mining of historical change records of the software program of each embodiment of the present invention described above and / or other desired functions. In one example, the electronic device may also include: an input device and an output device, and these components are interconnected by a bus system and / or other forms of connection mechanisms (not shown).

[0171] In addition, the input device may also include, for example, a keyboard, a mouse, and the like.

[0172] The output device can output various information to the outside, and can include, for example, a display, a speaker, a printer, a communication network and a remote output device connected thereto, and the like.

[0173] Of course, to simplify, Figure 2 Only some of the components related to the present invention in the electronic device are shown, and components such as buses, input / output interfaces, etc. are omitted. In addition, depending on the specific application, the electronic device may also include any other appropriate components. The present invention provides specific implementation steps and logical processes of the privacy number allocation method, including the processing of input information, the application of matching strategies, and the return of allocation results. The design of matching strategies and their application in the system, especially how to dynamically adjust the allocation strategy according to the different needs of users. The organizational structure and management method of number pool data, and how to efficiently search and allocate privacy numbers.

[0174] It should be noted that the above detailed descriptions are exemplary and are intended to provide further explanation of the present application. Unless otherwise specified, all technical and scientific terms used herein have the same meaning as commonly understood by those of ordinary skill in the art to which the present application belongs.

[0175] In the above detailed description, reference is made to the accompanying drawings, which form a part of this document. In the accompanying drawings, similar symbols typically identify similar components unless the context indicates otherwise. The illustrated embodiments described in the detailed description, drawings, and claims are not meant to be limiting. Other embodiments may be used, and other changes may be made, without departing from the spirit or scope of the subject matter presented herein.

[0176] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A method for matching the location information of the calling and called numbers with the nearest private number, characterized in that: The method comprises: User input and request submission steps: The user enters the calling and called numbers, location information, target city, alternative cities, and selected matching strategies through the system interface; all necessary fields must be filled in and the format is correct, and the system verifies the integrity and validity of the input information in real time; Preprocessing and strategy selection step: Determine the initial search scope and allocation logic according to the matching strategy selected by the user; the matching strategy selected by the user further includes: strict matching strategy, the system only searches the privacy number pool in the target city specified by the user. If there are no available numbers in all target cities, the allocation fails and the specific reason is fed back to the user; semi-strict matching strategy: first try to allocate in the target city, if it fails, automatically expand the search scope to other cities in the same province as the user-specified city, if there are still no available numbers in the same province, decide whether to continue searching based on whether the user has set up alternative cities, otherwise the allocation fails; non-strict matching strategy: first try to allocate in the order of strict matching and semi-strict matching, if both fail, further relax the restrictions and search for available privacy numbers nationwide; The semi-strict matching strategy further includes: Input information parsing step: parsing the target city code list and the alternative city code list input by the user; Preferred city allocation steps: traverse each area code in the target city list, query the privacy number pool corresponding to the area code for the area code, and check whether there is an available number; if there is an available number, allocate the number to the user and end the allocation process; if there is no available number under the area code, continue to try the next area code; if there is no available number in all preferred cities, enter the extended allocation of cities in the same province; for each preferred city, obtain the province information where it is located; traverse other cities in the province except the preferred city, for each city, query the privacy number pool of the city, and check whether there is an available number; if there is an available number, allocate the number to the user and end the allocation process; if there is no available number in all other cities in the province, continue to consider the province where the next preferred city is located; Alternative city allocation step: If the user provides an alternative city and the above steps fail to successfully allocate numbers, the list of alternative cities is traversed, and the same allocation steps as the preferred city are performed on the alternative cities; Allocation record: If all attempts fail, the allocation failure is recorded and feedback is given to the user; The steps of searching and allocating private numbers are as follows: according to the preset search order, first the target city, then the province, and then the whole country, start searching the private number pool; the private number search and allocation further includes: in each search stage, check whether the number resources in the current range meet the user's needs, and the user needs refer to whether the specific number type required by the user is met or whether the specific number segment required by the user is met; if an available number is found, perform the allocation operation, update the number pool status, and generate an allocation result record; if there is no available number in the current search range, decide whether to continue searching the next range according to the matching strategy; the allocation result record includes the allocated private number or the reason for the allocation failure; if the allocation is successful, the instructions and precautions for the use of the private number can also be provided; if the allocation fails, provide corresponding suggestions or guide the user to readjust the input information according to the matching strategy selected by the user; Allocation result feedback step: providing real-time feedback of the allocation result to the user; Subsequent processing and resource optimization steps: regularly analyzing the allocation data to identify hot and cold areas of number resource usage; the subsequent processing and resource optimization steps further include: Maintain a dynamically updated privacy number pool, including number resources and their current status in various cities; use intelligent prediction algorithms to predict possible future number needs based on historical allocation data and current number usage, and allocate and optimize resources in advance; automatically adjust the number pool allocation strategy and resource allocation ratio based on the analysis results of the intelligent prediction algorithm to optimize overall usage efficiency; for privacy numbers that have not been used for a long time, the system can automatically recycle them and re-incorporate them into the number pool for management, realizing an automatic recycling and reallocation mechanism for number resources to ensure efficient use of the number pool; Using a weighted allocation algorithm to manage the number pool further includes the following steps: Data collection and preprocessing: Collect the allocation records of privacy numbers in various cities over the past period of time, including the allocation time, quantity and user type; also collect external data sources, including population data, economic development level and communication activity of cities; Build demand forecasting features: Based on historical allocation data, a time series model is constructed to predict the demand for privacy numbers in various cities in the future; population, economic level and communication activity are converted into quantifiable population density, GDP growth rate and average daily call volume; Ensemble learning and time series prediction: Use multiple basic models to make predictions separately, and then input the prediction results into a meta-model as new features to obtain the final prediction probability P(Ai); use a weighted allocation algorithm to assign a weight wi to each city, wi=f(P(Ai), population, economic level), where f is a function that comprehensively evaluates various factors and gives weights. P(Ai) represents the probability that the number demand of city Ai will be met in the future. Adding attention mechanism: In the LSTM or Transformer model, by adding attention mechanism to dynamically adjust the weights of different input features or time steps, the number demand of prefecture-level cities Ai can be predicted more accurately; Weight calculation function: ； Among them, α, β, γ, and δ are coefficients obtained through genetic algorithms, particle swarm optimization, or weight allocation based on expert experience, which are used to adjust the influence of different features on the weights, and i refers to different prefecture-level cities; Dynamically adjust weights: When a specific event is detected, the weight adjustment algorithm is automatically triggered to dynamically adjust the weights of relevant cities based on the nature and scope of the event; a closed-loop mechanism for user feedback and weight adjustment is established to adjust the weight coefficients α, β, γ, δ in real time based on the distribution efficiency of user satisfaction; Introduce fuzzy logic: define fuzzy sets and fuzzy rules, transform the input features of population density, GDP growth rate, and average daily call volume into fuzzy variables; calculate the weight of each city in different fuzzy states according to fuzzy rules, and finally obtain the final weight wi through the defuzzification process; Regional association analysis based on graph neural network: Construct a city-to-city association graph, where nodes represent cities and edges represent certain associations between cities. Use the GNN model to propagate information on the graph and learn the embedding representation of each city, which contains information about its neighboring cities. Calculate the weight wi based on the learned embedding representation, which depends not only on the characteristics of the city itself but also on the influence of neighboring cities. Allocation strategy optimization: According to the calculated weight wi, cities are sorted by priority to form a priority queue; when allocating numbers, first try to allocate from the cities with the highest priority; for cities with higher weights, reserve a certain proportion of privacy number resources to ensure rapid response during peak demand; establish a user feedback mechanism to collect user satisfaction data on allocation results, which is used to further optimize the model and weight allocation strategy; Intelligent management: It has self-learning capabilities and can continuously optimize the prediction model and weight calculation function based on historical allocation results and user feedback; it introduces anomaly detection mechanisms to promptly detect and handle abnormal allocation situations.

2. A method for matching the location information of the calling and called numbers with the privacy number nearby as claimed in claim 1, characterized in that: The user input is a multi-dimensional user input. The user not only provides the calling and called numbers, but also needs to clearly specify the geographical information of the numbers. The geographical information is identified by the province, city, district code or area code; when the user proposes further detailed requirements, one or more target cities are accurately specified as the preferred allocation area for the privacy number through the target city field; the alternative city field is introduced as an alternative, allowing the user to specify the suboptimal city option to be considered when there is no available number in the preferred target city.

3. A system for matching the local information of the calling and called numbers with the privacy number by using the method for matching the local information of the calling and called numbers with the privacy number according to claim 1, characterized in that: The system comprises: User input and request submission module: Users input the calling and called numbers, location information, target cities, alternative cities, and selected matching strategies through the system interface; all necessary fields must be filled in and the format is correct, and the system verifies the integrity and validity of the input information in real time; Preprocessing and strategy selection module: The system determines the initial search scope and allocation logic based on the matching strategy selected by the user; Privacy number search and allocation module: The system starts searching the privacy number pool in the preset search order, first the target city, then the same province, and then the whole country; Allocation result feedback module: the system will provide real-time feedback of allocation results to users; Subsequent processing and resource optimization module: The system regularly analyzes allocation data and identifies hot and cold areas of number resource usage.

4. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method for matching the location information of the calling and called numbers with the privacy number nearby as described in any one of claims 1 to 2 are implemented.

5. A computer device, characterized in that: include: Memory for storing computer programs; A processor is used to execute the computer program to implement the steps of the method for matching the location information of the calling and called numbers with the privacy number in the nearest place according to any one of claims 1 to 2.

Images