Electric connection performance supplementary pushing method, device and equipment

Abstract

The invention discloses an electric connection performance supplementary pushing method, device and equipment, and the method is applied to the technical field of logistics, and the method comprises the steps: receiving a user ID query request, and querying a user ID matched with a waybill number at the optimal call time in an order data set; under the condition that the user ID is determined to be credible, determining the user ID as a target user ID; predicting an order prediction result of the target user ID in a future time period by adopting a time sequence prediction model; according to the order prediction result, caching a target waybill list having an association relationship with the target user ID in a cache database; adopting an association rule mining algorithm to analyze a waybill association relationship between different waybills in the target waybill list; and determining a target order needing to perform electric connection performance and supplementarily deducing an electric connection performance result. The method can ensure that all orders can be subjected to electric connection performance judgment in time.

Description

Technical Field

[0001] The present invention relates to the field of computer technology, and in particular to a method, device and equipment for supplementing the performance of a telecom contract. Background Art

[0002] In the logistics and distribution sector, tele-fulfillment is a crucial step in ensuring smooth order delivery. Existing tele-fulfillment systems typically rely on a single data source, unable to effectively handle complex scenarios involving multiple orders and multiple users. This results in low accuracy and efficiency in tele-fulfillment. Furthermore, existing systems lack an effective mechanism for post-processing orders that do not meet tele-fulfillment regulations, preventing timely tele-fulfillment decisions for some orders. Summary of the Invention

[0003] The present invention provides a method, device and equipment for telephone fulfillment and supplementary push, which can quickly obtain user ID and waybill list, improve data processing efficiency; based on call records and cached data, it can intelligently determine whether the order has been fulfilled by telephone, reducing manual intervention.

[0004] In one aspect, the present invention provides a method for supplementing the performance of a telecom connection, the method comprising: Receive a user ID query request, and search the order data set for a user ID that matches the waybill number at the optimal call time; Performing a credibility evaluation on the user ID using a Bayesian classification algorithm, and determining the user ID as a target user ID if the user ID is determined to be credible; Use a time series prediction model to predict the order prediction results of the target user ID in the future period; caching a target waybill list associated with the target user ID in a cache database according to the order prediction result; Using an association rule mining algorithm to analyze the waybill association relationships between different waybill items in the target waybill list; According to the cache database and the waybill association relationship, the target order that needs to be fulfilled by telephone is determined and the result of the telephone fulfillment is supplemented.

[0005] In an exemplary embodiment, receiving a user ID query request and searching the order data set for a user ID that matches the waybill number at the optimal call time includes: Receive a user ID query request, perform format verification on the waybill number carried in the request, and obtain a verification result; When the verification result indicates that the input format of the waybill number meets the requirements for calling the Vienna interface with the waybill number, the optimal calling time and the optimal calling path of the interface are determined by the intelligent interface calling optimization model; The interface is called according to the optimal calling path, and a user ID that matches the waybill number at the optimal calling time is searched in the order data set.

[0006] In an exemplary embodiment, the intelligent interface calls the training method of the optimization model including: Obtaining sample interface call data of a sample interface in a historical period; the sample interface is marked with a sample optimal call time label and a sample optimal call path label, and the sample interface call data includes at least one of interface response time, call success rate, and call frequency; Inputting the sample interface call data into a reinforcement learning model to extract sample busyness characteristics and sample network status characteristics of the sample interface; Obtaining a sample optimal call time result of the sample interface according to the sample busyness characteristics, and obtaining a sample optimal call path result of the sample interface according to the sample network status characteristics; Determining target loss data based on a difference between the sample best call time result and the sample best call time label, and a difference between the sample best call path result and the sample best call path label; The model parameters of the reinforcement learning model are adjusted according to the target loss data until a training end condition is met, and the reinforcement learning model at the end of training is determined as the intelligent interface call optimization model.

[0007] In an exemplary embodiment, before calling the interface according to the optimal call path and searching the order dataset for a user ID that matches the waybill number at the optimal call time, the method further includes: Obtain order data from a logistics order system, and perform data cleaning on missing values, duplicate values, and abnormal values in the order data to obtain cleaned data; Preprocessing the cleaned data using natural language processing technology to obtain processed data; Extract key information from the processed data and construct an order data set.

[0008] In an exemplary embodiment, the user ID is an ID currently obtained by the Vienna interface, and the credibility evaluation of the user ID using the Bayesian classification algorithm includes: Obtaining the correct probability and the incorrect probability of the historical user ID in the current Vienna interface; Get the data characteristics returned by the current Vienna interface; Based on the data characteristics, the correct probability and the error probability of the historical user ID, a Bayesian classification algorithm is used to calculate the predicted probability that the user ID is the correct result; If the predicted probability is less than a preset threshold, it is determined that the user ID is untrustworthy; If the predicted probability is greater than or equal to the preset threshold, it is determined that the user ID is credible.

[0009] In an exemplary embodiment, the analyzing the waybill association relationships between different waybills in the target waybill list using an association rule mining algorithm includes: Obtain target order attributes of each target waybill in the target waybill list; the target order attributes include at least one of commodity type, order time, and delivery address; According to the target order attributes, the waybills with associated relationships in the target waybill list are aggregated to obtain a combination of orders with associated relationships.

[0010] In an exemplary embodiment, caching the target waybill list associated with the target user ID in a cache database according to the order prediction result includes: Obtain key data from the target waybill list; Using blockchain technology to encrypt and store the key data in the cache database; Accordingly, after caching the target waybill list associated with the target user ID in the cache database according to the order prediction result, the method further includes: When the remaining storage capacity of the cache database is less than a preset capacity threshold, obtaining the access time and access count of each data in the cache database; Filtering the data to be deleted by using the LRU algorithm and the access time and access count of each data, and deleting the data to be deleted from the cache database; In response to a data query request, using a Bloom filter to determine whether the data to be queried is in the cache database; If the judgment result is that the probability that the data to be queried exists in the cache database is greater than the preset probability threshold, querying whether the data to be queried exists in the cache database; If not, it is determined that the data to be queried is not in the cache database.

[0011] Another aspect provides a device for supplementing the performance of a telecom contract, the device comprising: A request receiving module, configured to receive a user ID query request and search the order data set for a user ID that matches the waybill number at the optimal call time; a target ID determination module, configured to perform a credibility assessment on the user ID using a Bayesian classification algorithm, and determine the user ID as a target user ID if the user ID is determined to be credible; An order result prediction module is used to predict the order prediction results of the target user ID in the future period using a time series prediction model; A cache module, configured to cache a target waybill list associated with the target user ID in a cache database according to the order prediction result; A waybill relationship determination module, configured to analyze the waybill association relationships between different waybills in the target waybill list using an association rule mining algorithm; The telephone connection result determination module is used to determine the target order that needs to be fulfilled by telephone connection based on the cache database and the waybill association relationship and to supplement the telephone connection fulfillment result.

[0012] In an exemplary embodiment, the request receiving module includes: A verification result determination unit, configured to receive a user ID query request, and perform format verification on the waybill number carried in the request to obtain a verification result; an optimal time determination unit, configured to determine an optimal call time and an optimal call path for the interface through an intelligent interface call optimization model when the verification result indicates that the input format of the waybill number meets the requirements for calling the Vienna interface for the waybill number; A matching unit is configured to call the interface according to the optimal calling path, and search the order data set for a user ID that matches the waybill number at the optimal calling time.

[0013] In an exemplary embodiment, the apparatus further comprises: A sample data acquisition module is used to acquire sample interface call data of a sample interface in a historical period; the sample interface is marked with a sample optimal call time label and a sample optimal call path label, and the sample interface call data includes at least one of interface response time, call success rate, and call frequency; A sample feature extraction module is used to input the sample interface call data into a reinforcement learning model to extract the sample busyness feature and sample network status feature of the sample interface; A sample result determination module, configured to obtain a sample optimal call time result of the sample interface according to the sample busyness characteristics, and obtain a sample optimal call path result of the sample interface according to the sample network status characteristics; a target loss determination module, configured to determine target loss data based on a difference between the sample best call time result and the sample best call time label, and a difference between the sample best call path result and the sample best call path label; A model training module is used to adjust the model parameters of the reinforcement learning model according to the target loss data until the training end condition is met, and determine the reinforcement learning model at the end of training as the intelligent interface call optimization model.

[0014] In an exemplary embodiment, the apparatus further comprises: A data acquisition module is used to obtain order data from the logistics order system and perform data cleaning on missing values, duplicate values, and abnormal values in the order data to obtain cleaned data; A data processing module, configured to pre-process the cleaned data using natural language processing technology to obtain processed data; The data set construction module is used to extract key information from the processed data and construct an order data set.

[0015] In an exemplary embodiment, the user ID is an ID currently acquired by the Vienna interface, and the target ID determination module includes: A probability acquisition unit, configured to acquire a correct probability and an incorrect probability of a historical user ID in the current Vienna interface; A data feature acquisition unit, configured to acquire the data features returned by the current Vienna interface; A prediction probability calculation unit, configured to calculate the prediction probability that the user ID is a correct result using a Bayesian classification algorithm based on the data features, the correct probability and the incorrect probability of the historical user ID; a first determining unit, configured to determine that the user ID is untrustworthy if the predicted probability is less than a preset threshold; The second determining unit is configured to determine that the user ID is credible if the predicted probability is greater than or equal to the preset threshold.

[0016] In an exemplary embodiment, the waybill relationship determination module includes: A target attribute acquisition unit, configured to acquire a target order attribute of each target waybill in the target waybill list; the target order attribute includes at least one of a commodity type, an order time, and a delivery address; The order association unit is used to aggregate the waybills with associated relationships in the target waybill list according to the target order attributes to obtain an order combination with associated relationships.

[0017] In an exemplary embodiment, the cache module is further configured to obtain key data from the target waybill list; and encrypt and store the key data in the cache database using blockchain technology; Accordingly, the device further includes: An access information acquisition module, configured to acquire the access time and access count of each data in the cache database when the remaining storage capacity of the cache database is less than a preset capacity threshold; A data deletion module is used to filter out data to be deleted by using an LRU algorithm and the access time and access count of each data, and delete the data to be deleted from the cache database; A data query module, configured to respond to a data query request and use a Bloom filter to determine whether the data to be queried is in the cache database; a judgment module, configured to query whether the data to be queried exists in the cache database if a judgment result shows that the probability that the data to be queried exists in the cache database is greater than a preset probability threshold; The determination module is configured to determine that the data to be queried is not in the cache database if the data to be queried does not exist.

[0018] On the other hand, an electronic device is provided, comprising a processor and a memory, wherein the memory stores at least one instruction or at least one program, and the at least one instruction or at least one program is loaded and executed by the processor to implement the above-mentioned method for supplementing the fulfillment of the contract.

[0019] On the other hand, a computer storage medium is provided, which stores at least one instruction or at least one program, and the at least one instruction or at least one program is loaded and executed by a processor to implement the above-mentioned method for supplementary promotion of telecom performance.

[0020] Another aspect provides a computer program product or computer program, comprising computer instructions stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium and executes the computer instructions, causing the computer device to implement the above-described method for supplementary push notification of contract performance.

[0021] The method, device and equipment for supplementary promotion of contract fulfillment provided by the present invention have the following technical effects: The present invention receives a user ID query request, queries the order data set for the user ID that matches the waybill number at the optimal call time; performs a credibility assessment on the user ID through a Bayesian classification algorithm, and determines the user ID as the target user ID when it is determined that the user ID is credible; uses a time series prediction model to predict order prediction results for the target user ID in future time periods; based on the order prediction results, caches a target waybill list that has an association relationship with the target user ID in a cache database; thereby quickly and accurately obtaining the target user ID and the corresponding waybill list; uses an association rule mining algorithm to analyze the waybill association relationship between different waybills in the target waybill list; based on the cache database and the waybill association relationship, determines the target order that needs to be fulfilled by telephone and supplements the result of the telephone fulfillment, which can intelligently judge whether the order has been fulfilled by telephone and reduce manual intervention; thereby supplements the orders that have not been fulfilled by telephone to ensure that all orders can be judged for telephone fulfillment in a timely manner. BRIEF DESCRIPTION OF THE DRAWINGS

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

[0023] Figure 1 This is a schematic diagram of a system for supplementing the performance of a contract through a telephone connection provided in an embodiment of this specification; Figure 2 This is a flowchart of a method for supplementing the performance of a teleconference provided in an embodiment of this specification; Figure 3 This is a flow chart of a method provided by an embodiment of this specification for receiving a user ID query request and searching an order data set for a user ID that matches the waybill number at the optimal call time; Figure 4 This is a flowchart of a training method for an intelligent interface calling an optimization model provided in an embodiment of this specification; Figure 5 This is a flowchart of an exemplary method for supplementing the performance of a teleconference provided in an embodiment of this specification; Figure 6 This is a structural diagram of a device for supplementing the performance of a contract through telecom connection provided in an embodiment of this specification; Figure 7 This is a structural diagram of a server provided in an embodiment of this specification. DETAILED DESCRIPTION

[0024] The following will be combined with the drawings in the embodiments of this specification to clearly and completely describe the technical solutions in the embodiments of this specification. Obviously, the embodiments described are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making any creative efforts shall fall within the scope of protection of the present invention.

[0025] It should be noted that the terms "first", "second", etc. in the description and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that the numbers used in this way are interchangeable where appropriate so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product or server that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0026] See also Figure 1 , Figure 1 This is a schematic diagram of a system for pushing back the contract through a tele-connection contract, as provided in an embodiment of this specification. Figure 1 As shown, the telecom fulfillment supplementary push system may include at least a server 01 and a client 02.

[0027] Specifically, in the embodiments of this specification, the server 01 may include a standalone server, a distributed server, or a server cluster consisting of multiple servers. It may also be a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, CDN (Content Delivery Network), and big data and artificial intelligence platforms. Server 01 may include a network communication unit, a processor, and memory, among other things. Specifically, the server 01 may be used to determine target orders requiring telecom fulfillment and to provide supplementary telecom fulfillment results.

[0028] Specifically, in the embodiments of this specification, the client 02 may include a physical device such as a smartphone, desktop computer, tablet computer, laptop computer, digital assistant, smart wearable device, smart speaker, in-vehicle terminal, smart TV, etc. It may also include software running on the physical device, such as a web page provided by a service provider to a user, or an application provided by the service provider to a user. Specifically, the client 02 may be used to display target orders that require telephone fulfillment.

[0029] The following describes a method for supplementing the performance of a telecom contract according to the present invention. Figure 2 It is a flowchart of a method for supplementing the performance of a teleconference provided in an embodiment of this specification. This specification provides method operation steps as described in the embodiment or flowchart, but may include more or fewer operation steps based on conventional or non-creative labor. The order of steps listed in the embodiment is only one way of executing the steps among many, and does not represent the only execution order. When the actual system or server product is executed, it can be executed in sequence or in parallel (for example, in a parallel processor or multi-threaded processing environment) according to the method shown in the embodiment or the accompanying drawings. Specifically, Figure 2 As shown, the method may include: S201: Receive a user ID query request, and search the order data set for a user ID that matches the waybill number at the optimal call time. In the embodiments of this specification, when the Vienna interface is called through the waybill number to obtain the user ID, the intelligent interface calls the optimization model and the Bayesian classification algorithm to work together to ensure that the accurate user ID is obtained. The Vienna interface is an external interface specifically used to query the user ID. The system sends a request to the interface through the HTTP / HTTPS protocol, and the request parameter is the waybill number. Before sending the request, the legitimacy of the waybill number is checked to ensure that it meets the input format requirements of the interface. In order to improve the efficiency of the interface call, an asynchronous call is adopted to avoid blocking the main thread. At the same time, a timeout is set to prevent the system from waiting for a long time due to slow interface response.

[0030] S203: Performing credibility evaluation on the user ID using a Bayesian classification algorithm, and determining the user ID as a target user ID if the user ID is determined to be credible.

[0031] S205: Using a time series prediction model to predict order prediction results for the target user ID in a future period.

[0032] S207: Cache a target waybill list associated with the target user ID in a cache database according to the order prediction result.

[0033] S209: Analyze the waybill association relationships between different waybills in the target waybill list using an association rule mining algorithm.

[0034] S2011: According to the cache database and the waybill association relationship, the target order that needs to be fulfilled by telephone is determined and the result of the telephone fulfillment is supplemented.

[0035] In an embodiment of the present specification, before calling the interface according to the optimal call path and searching the order dataset for a user ID that matches the waybill number at the optimal call time, the method further includes: Obtain order data from a logistics order system, and perform data cleaning on missing values, duplicate values, and abnormal values in the order data to obtain cleaned data; Preprocessing the cleaned data using natural language processing technology to obtain processed data; Extract key information from the processed data and construct an order data set.

[0036] In the embodiment of this specification, after obtaining order data from the unified order system, the data cleaning algorithm and NLP technology are immediately started to perform data preprocessing, extract key information, and construct a complete order data set.

[0037] The unified order system serves as a central hub for all types of order information. Data is sourced from a wide range of sources, including online e-commerce platforms and offline store systems. The system utilizes a stable network connection and a standardized API to periodically pull or subscribe to order data from the unified order system in real time. To ensure stable and secure data transmission, SSL / TLS encryption is used to prevent data theft or tampering during transmission.

[0038] After acquiring order data, due to the diversity and complexity of data sources, the data may contain missing values, duplicate values, outliers, and other issues. Data cleaning algorithms are used to address these issues. Missing values are handled differently depending on the data type and business logic. Numerical data can be filled using the mean, median, or mode. Text data can be inferred based on the context or filled with a default value. Duplicate values are removed by comparing key identifying fields (such as order numbers). Outliers are identified and addressed using statistical methods (such as the Z-score method) or machine learning methods (such as the isolation forest algorithm).

[0039] Natural language processing (NLP) technology plays a crucial role in order data preprocessing. For textual information in an order, such as recipient notes and product descriptions, we first perform word segmentation to break the text into individual words. We then perform part-of-speech tagging, labeling each word with its part of speech (e.g., noun, verb, adjective, etc.) to facilitate subsequent semantic analysis. Next, we perform named entity recognition (NER) to identify key entities in the text, such as names of people, places, and organizations. For example, we can identify specific delivery addresses and special requests from recipient notes.

[0040] After data cleaning and NLP preprocessing, key information is extracted from the order data, such as the order number, waybill number, recipient name, address, contact number, product information, and order status. This key information is integrated into a unified data structure to construct a complete order dataset. This dataset serves as the foundation for subsequent processes, providing accurate data support for operations such as user ID query and waybill list query.

[0041] In the embodiments of this specification, Figure 3 As shown, the receiving of the user ID query request and searching the order data set for the user ID that matches the waybill number at the optimal call time include: S20101: Receive a user ID query request, perform format verification on the waybill number carried in the request, and obtain a verification result; S20103: When the verification result indicates that the input format of the waybill number meets the requirements for calling the Vienna interface for the waybill number, determine the optimal calling time and optimal calling path of the interface through the intelligent interface calling optimization model; S20105: Call the interface according to the optimal calling path, and search the order data set for a user ID that matches the waybill number at the optimal calling time.

[0042] In the examples of this specification, the waybill number is verified for validity before sending a request to ensure it complies with the interface's input format requirements. To improve the efficiency of the interface call, an asynchronous call is used to avoid blocking the main thread. A timeout is also set to prevent the system from waiting for extended periods due to slow interface responses.

[0043] In the embodiments of this specification, Figure 4 As shown, the training method of the intelligent interface calling the optimization model includes: S401: Obtain sample interface call data of a sample interface in a historical period; the sample interface is marked with a sample optimal call time label and a sample optimal call path label, and the sample interface call data includes at least one of interface response time, call success rate, and call frequency; S403: Inputting the sample interface call data into a reinforcement learning model to extract sample busyness characteristics and sample network status characteristics of the sample interface; S405: Obtaining a sample optimal call time result of the sample interface according to the sample busyness characteristic, and obtaining a sample optimal call path result of the sample interface according to the sample network status characteristic; S407: Determine target loss data according to the difference between the sample best call time result and the sample best call time label, and the difference between the sample best call path result and the sample best call path label; S409: Adjusting the model parameters of the reinforcement learning model according to the target loss data until a training end condition is met, and determining the reinforcement learning model at the end of training as the intelligent interface call optimization model.

[0044] In the embodiments of this specification, an intelligent interface call optimization model is built using a reinforcement learning algorithm. This model continuously learns from historical interface call data, including information such as interface response time, success rate, and call frequency, to optimize interface call strategies. For example, the model can select the optimal call time based on interface traffic levels during different time periods, or choose the optimal network path based on network conditions. The model then makes real-time adjustments and optimizations based on the feedback from interface calls (e.g., success or failure) to improve the efficiency and stability of interface calls.

[0045] In the embodiment of this specification, the user ID is the ID currently obtained by the Vienna interface, and the credibility evaluation of the user ID using the Bayesian classification algorithm includes: Obtaining the correct probability and the incorrect probability of the historical user ID in the current Vienna interface; Get the data characteristics returned by the current Vienna interface; Based on the data characteristics, the correct probability and the error probability of the historical user ID, a Bayesian classification algorithm is used to calculate the predicted probability that the user ID is the correct result; If the predicted probability is less than a preset threshold, it is determined that the user ID is untrustworthy; If the predicted probability is greater than or equal to the preset threshold, it is determined that the user ID is credible.

[0046] In the embodiments of this specification, a Bayesian classification algorithm is used to assess the credibility of user ID data returned by the interface. Based on Bayes' theorem, this algorithm combines the correct and incorrect probabilities of user IDs in historical data with the characteristics of the data returned by the current interface to calculate the probability that the returned user ID is correct. If the calculated probability falls below a set threshold, the user ID is deemed untrustworthy, and the system automatically triggers a backup interface or re-invokes the primary interface for querying. The collaborative work of the Bayesian classification algorithm ensures that the retrieved user ID is accurate and reliable.

[0047] In the embodiment of this specification, the association rule mining algorithm is used to analyze the waybill association relationship between different waybills in the target waybill list, including: Obtain target order attributes of each target waybill in the target waybill list; the target order attributes include at least one of commodity type, order time, and delivery address; According to the target order attributes, the waybills with associated relationships in the target waybill list are aggregated to obtain a combination of orders with associated relationships.

[0048] In the embodiment of this specification, a time series prediction model is used to cache the waybill list in advance, and after calling the Vienna interface to obtain the latest data, an association rule mining algorithm is used to analyze the waybill association relationship.

[0049] Time series forecasting models (such as ARIMA and Prophet) are used to predict future order trends for users. Based on historical order data, these models analyze trends in factors such as order quantity and order timing to predict likely future orders. Based on these forecasts, the system caches potentially relevant shipping order lists in advance, reducing the number of real-time interface calls. For example, if the model predicts that a user is likely to place new orders within the next week, the system will pre-fetch the user's shipping order list from the Vienna interface and cache it.

[0050] To obtain the latest waybill list, the system calls the Vienna API again. Again, asynchronous calls and timeouts are used to ensure efficient and stable API calls. After obtaining the latest data, it is merged and updated with pre-cached data to ensure timeliness and accuracy.

[0051] Association rule mining algorithms, such as the Apriori algorithm, are used to analyze the potential relationships between different waybills for the same user. These algorithms mine various attributes within waybill data (such as product type, order date, and delivery address) to discover association rules between different waybills. For example, they can identify patterns such as a user frequently purchasing several items at once, or multiple orders shipped to the same address within a specific time period. These association rules can provide valuable information for subsequent contract fulfillment decisions and logistics and delivery optimization.

[0052] In the embodiment of this specification, caching the target waybill list associated with the target user ID in the cache database according to the order prediction result includes: Obtain key data from the target waybill list; Using blockchain technology to encrypt and store the key data in the cache database; Accordingly, after caching the target waybill list associated with the target user ID in the cache database according to the order prediction result, the method further includes: When the remaining storage capacity of the cache database is less than a preset capacity threshold, obtaining the access time and access count of each data in the cache database; Filtering the data to be deleted by using the LRU algorithm and the access time and access count of each data, and deleting the data to be deleted from the cache database; In response to a data query request, using a Bloom filter to determine whether the data to be queried is in the cache database; If the judgment result is that the probability that the data to be queried exists in the cache database is greater than the preset probability threshold, querying whether the data to be queried exists in the cache database; If not, it is determined that the data to be queried is not in the cache database.

[0053] In the embodiment of this specification, the queried data is cached and managed according to the LRU algorithm and Bloom filter, and encrypted, stored and traced using blockchain technology.

[0054] Cache management is performed using the LRU algorithm and Bloom filters. The LRU (Least Recently Used) algorithm is a common cache eviction strategy that determines which data should be evicted based on access time. When cache space is insufficient, the system prioritizes the least recently used data. The LRU algorithm ensures that the most frequently used data is always in the cache, improving the cache hit rate.

[0055] A Bloom filter is a highly space-efficient probabilistic data structure used to quickly determine whether an element exists in a set. In cache management, Bloom filters can quickly determine whether a piece of data already exists in the cache, thereby reducing unnecessary cache queries. When a query requires data, a Bloom filter first performs a quick check. If the result indicates that the data may exist, the cache is then searched. If the result indicates that the data does not exist, the data is directly determined to be not in the cache, avoiding unnecessary cache accesses.

[0056] Blockchain technology is used for encrypted storage and traceability. Blockchain technology boasts decentralization, immutability, and traceability. When caching data, blockchain technology is used to encrypt and store key data (such as waybill numbers and user IDs). Each data block contains the hash value of the previous block, forming a chain structure to ensure data integrity and security. Furthermore, blockchain's traceability function allows for easy querying of data sources and modification history, providing strong support for data auditing and management. For example, in the event of data anomalies or disputes, the blockchain can be used to trace the data back to its original source and every modification record.

[0057] In some embodiments, you can subscribe to a Kafka queue to obtain call record data, and use the sliding window algorithm and ASR combined with the DNN model to perform real-time analysis and speech-to-text processing.

[0058] Call log data is obtained by subscribing to a Kafka queue. Kafka is a high-throughput distributed message queue system. The industrial mobile phone department publishes call log data to the Kafka queue as messages. The system subscribes to this queue through a Kafka consumer and obtains call log data in real time. To ensure data reliability and sequentiality, Kafka's multi-partition and multi-replication mechanism is used. Each partition stores a portion of the data, and multiple replicas ensure data redundancy. If a replica fails, the system automatically switches to another replica to continue retrieving data.

[0059] A sliding window algorithm, combined with ASR and a DNN model, performs real-time analysis and speech-to-text conversion. The sliding window algorithm is used for real-time analysis of call log data. This algorithm collects statistics and analyzes call logs within a fixed-size time window, such as the number of calls, average call duration, and call frequency. By continuously sliding the window, changing trends in call behavior can be monitored in real time.

[0060] Automatic Speech Recognition (ASR) technology combined with a Deep Neural Network (DNN) model is used to convert call speech into text. Trained on large-scale speech data, the DNN model accurately recognizes speech content in varying accents, speaking speeds, and ambient noise. The converted text undergoes further processing and analysis, such as extracting key information and performing sentiment analysis, to provide richer information for telecom operators to assess contract performance.

[0061] Based on call records and cached data, decision tree models and random forest algorithms can be used to determine the fulfillment of the call, and then reviewed by an expert system. Re-push fulfillment results: At the time of receipt, orders that have not been fulfilled by the call will be re-pushed according to the priority queue algorithm. The message queue transaction mechanism and feedback mechanism are used to ensure the success of the re-push.

[0062] In the embodiments of this specification, Figure 5 As shown, Figure 5 A method for supplementing the performance of a telecom contract provided in this embodiment includes: The consumer order center tags Kafka and obtains orders that require telephone fulfillment; Call the waybill number to obtain the recipient's user ID (billing center); according to the user ID dimension, each user's waybill number can be aggregated (there may be multiple: A, B, C); Obtain the delivery salesperson record of the waybill center based on the waybill number; Determine whether there is a distribution record for the waybill number; if so, determine whether there is a marked waybill number A with a distribution record; Call two interfaces of the billing center (get the user ID based on the waybill number, and query all waybill numbers within 2 days based on the user ID) to obtain all waybill numbers (A, m, n) for the same recipient as the marked waybill number A. Obtain the receipt record of the waybill center based on the marked waybill number A; Check whether the marked waybill number A has been signed for. If so, obtain the call records generated by waybill number A from the unified call database. Obtain valid call records of waybill number A in closed loop; Waybill number A determines whether a telephone connection has actually been made based on the closed-loop telephone connection rules and whether the goods have been delivered to the door, and pushes the telephone connection result to the Diantongda application.

[0063] It can be seen from the technical solutions provided by the above embodiments of this specification that the embodiments of this specification receive a user ID query request, and query the order data set for a user ID that matches the waybill number at the optimal call time; the user ID is credibility evaluated by a Bayesian classification algorithm, and when it is determined that the user ID is credible, the user ID is determined as the target user ID; a time series prediction model is used to predict the order prediction results of the target user ID in the future time period; based on the order prediction results, a target waybill list that has an association relationship with the target user ID is cached in a cache database; thereby, the target user ID and the corresponding waybill list can be obtained quickly and accurately; an association rule mining algorithm is used to analyze the waybill association relationship between different waybills in the target waybill list; based on the cache database and the waybill association relationship, the target order that needs to be fulfilled by telephone is determined and the telephone fulfillment result is supplemented, which can intelligently determine whether the order has been fulfilled by telephone and reduce manual intervention; thereby, orders that have not been fulfilled by telephone are supplemented to ensure that all orders can be judged for telephone fulfillment in a timely manner.

[0064] The embodiment of this specification also provides a device for supplementing the performance of the contract through telephone connection, such as Figure 6 As shown, the device includes: A request receiving module 610 is configured to receive a user ID query request and query the order data set for a user ID that matches the waybill number at the optimal call time; a target ID determination module 620 configured to perform a credibility assessment on the user ID using a Bayesian classification algorithm, and determine the user ID as a target user ID if the user ID is determined to be credible; An order result prediction module 630 is configured to use a time series prediction model to predict order prediction results for the target user ID in a future period; A cache module 640 is configured to cache a target waybill list associated with the target user ID in a cache database according to the order prediction result; Waybill relationship determination module 650, configured to analyze the waybill relationship between different waybills in the target waybill list using an association rule mining algorithm; The telephone connection result determination module 660 is used to determine the target order that needs to be fulfilled by telephone connection based on the cache database and the waybill association relationship and to supplement the telephone connection fulfillment result.

[0065] In an exemplary embodiment, the request receiving module includes: A verification result determination unit, configured to receive a user ID query request, and perform format verification on the waybill number carried in the request to obtain a verification result; an optimal time determination unit, configured to determine an optimal call time and an optimal call path for the interface through an intelligent interface call optimization model when the verification result indicates that the input format of the waybill number meets the requirements for calling the Vienna interface for the waybill number; A matching unit is configured to call the interface according to the optimal calling path, and search the order data set for a user ID that matches the waybill number at the optimal calling time.

[0066] In an exemplary embodiment, the apparatus further comprises: A sample data acquisition module is used to acquire sample interface call data of a sample interface in a historical period; the sample interface is marked with a sample optimal call time label and a sample optimal call path label, and the sample interface call data includes at least one of interface response time, call success rate, and call frequency; A sample feature extraction module is used to input the sample interface call data into a reinforcement learning model to extract the sample busyness feature and sample network status feature of the sample interface; A sample result determination module, configured to obtain a sample optimal call time result of the sample interface according to the sample busyness characteristics, and obtain a sample optimal call path result of the sample interface according to the sample network status characteristics; a target loss determination module, configured to determine target loss data based on a difference between the sample best call time result and the sample best call time label, and a difference between the sample best call path result and the sample best call path label; A model training module is used to adjust the model parameters of the reinforcement learning model according to the target loss data until the training end condition is met, and determine the reinforcement learning model at the end of training as the intelligent interface call optimization model.

[0067] In an exemplary embodiment, the apparatus further comprises: A data acquisition module is used to obtain order data from the logistics order system and perform data cleaning on missing values, duplicate values, and abnormal values in the order data to obtain cleaned data; A data processing module, configured to pre-process the cleaned data using natural language processing technology to obtain processed data; The data set construction module is used to extract key information from the processed data and construct an order data set.

[0068] In an exemplary embodiment, the user ID is an ID currently acquired by the Vienna interface, and the target ID determination module includes: A probability acquisition unit, configured to acquire a correct probability and an incorrect probability of a historical user ID in the current Vienna interface; A data feature acquisition unit, configured to acquire the data features returned by the current Vienna interface; A prediction probability calculation unit, configured to calculate the prediction probability that the user ID is a correct result using a Bayesian classification algorithm based on the data features, the correct probability and the incorrect probability of the historical user ID; a first determining unit, configured to determine that the user ID is untrustworthy if the predicted probability is less than a preset threshold; The second determining unit is configured to determine that the user ID is credible if the predicted probability is greater than or equal to the preset threshold.

[0069] In an exemplary embodiment, the waybill relationship determination module includes: A target attribute acquisition unit, configured to acquire a target order attribute of each target waybill in the target waybill list; the target order attribute includes at least one of a commodity type, an order time, and a delivery address; The order association unit is used to aggregate the waybills with associated relationships in the target waybill list according to the target order attributes to obtain an order combination with associated relationships.

[0070] In an exemplary embodiment, the cache module is further configured to obtain key data from the target waybill list; and encrypt and store the key data in the cache database using blockchain technology; Accordingly, the device further includes: An access information acquisition module, configured to acquire the access time and access count of each data in the cache database when the remaining storage capacity of the cache database is less than a preset capacity threshold; A data deletion module is used to filter out data to be deleted by using an LRU algorithm and the access time and access count of each data, and delete the data to be deleted from the cache database; A data query module, configured to respond to a data query request and use a Bloom filter to determine whether the data to be queried is in the cache database; a judgment module, configured to query whether the data to be queried exists in the cache database if a judgment result shows that the probability that the data to be queried exists in the cache database is greater than a preset probability threshold; The determination module is configured to determine that the data to be queried is not in the cache database if the data to be queried does not exist.

[0071] The device and method embodiments in the device embodiments are based on the same inventive concept.

[0072] An embodiment of this specification provides an electronic device, which includes a processor and a memory, wherein the memory stores at least one instruction or at least one program, and the at least one instruction or at least one program is loaded and executed by the processor to implement the method for supplementing the fulfillment of the contract as provided in the above method embodiment.

[0073] An embodiment of the present invention also provides a computer storage medium, which can be set in a terminal to store at least one instruction or at least one program related to a method for supplementing the performance of a telephone contract in an embodiment of the method. The at least one instruction or at least one program is loaded and executed by the processor to implement the method for supplementing the performance of a telephone contract provided in the above-mentioned method embodiment.

[0074] Embodiments of the present invention further provide a computer program product or computer program, which includes computer instructions stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium and executes the computer instructions, causing the computer device to implement the method for supplementary push notification of contract fulfillment provided in the above-mentioned method embodiment.

[0075] Optionally, in the embodiments of this specification, the storage medium may be located in at least one of the multiple network servers in the computer network. Optionally, in this embodiment, the storage medium may include, but is not limited to, a USB flash drive, a read-only memory (ROM), a random access memory (RAM), a mobile hard drive, a magnetic disk, or an optical disk, among other media capable of storing program code.

[0076] The memory described in the embodiments of this specification can be used to store software programs and modules, and the processor executes various functional applications and data processing by running the software programs and modules stored in the memory. The memory may mainly include a program storage area and a data storage area, wherein the program storage area can store an operating system, application programs required for functions, etc.; the data storage area can store data created according to the use of the device, etc. In addition, the memory may include a high-speed random access memory and may also include a non-volatile memory, such as at least one disk storage device, a flash memory device, or other volatile solid-state storage device. Accordingly, the memory may also include a memory controller to provide the processor with access to the memory.

[0077] The embodiment of the method for supplementing the performance of the contract through telephone connection provided in the embodiment of this specification can be executed in a mobile terminal, a computer terminal, a server or a similar computing device. Taking running on a server as an example, Figure 7 This is a hardware structure diagram of a server for a method of supplementing the performance of a contract through a telephone call provided in an embodiment of this specification. Figure 7As shown, the server 700 may vary significantly due to different configurations or performance, and may include one or more central processing units (CPUs) 710 (CPUs 710 may include, but are not limited to, processing devices such as microprocessors (MCUs) or programmable logic devices (FPGAs), memory 730 for storing data, and one or more storage media 720 (e.g., one or more mass storage devices) for storing applications 723 or data 722. The memory 730 and storage media 720 may be either transient or persistent storage. The program stored in the storage medium 720 may include one or more modules, each of which may include a series of instruction operations on the server. Furthermore, the CPU 710 may be configured to communicate with the storage medium 720 to execute the series of instruction operations in the storage medium 720 on the server 700. The server 700 may also include one or more power supplies 760, one or more wired or wireless network interfaces 750, one or more input and output interfaces 740, and / or one or more operating systems 721, such as Windows Server™, Mac OS X™, Unix™, Linux™, FreeBSD™, etc.

[0078] The input / output interface 740 can be used to receive or transmit data via a network. A specific example of the aforementioned network may include a wireless network provided by the communications provider of the server 700. In one embodiment, the input / output interface 740 may include a network interface controller (NIC), which can be connected to other network devices via a base station to enable communication with the Internet. In another embodiment, the input / output interface 740 may be a radio frequency (RF) module for wireless communication with the Internet.

[0079] It can be understood by those skilled in the art that Figure 7 The structure shown is only for illustration and does not limit the structure of the above electronic device. Figure 7 More or fewer components than shown, or with Figure 7 Different configurations shown.

[0080] It can be seen from the embodiments of the method, device, electronic device or storage medium for supplementary push of telephone fulfillment provided by the above-mentioned present invention that the present invention receives a user ID query request, queries the user ID that matches the waybill number at the optimal call time in the order data set; performs credibility evaluation on the user ID through the Bayesian classification algorithm, and determines the user ID as the target user ID when it is determined that the user ID is credible; adopts a time series prediction model to predict the order prediction results of the target user ID in the future time period; based on the order prediction results, caches the target waybill list that has an association relationship with the target user ID in the cache database; thereby, the target user ID and the corresponding waybill list can be obtained quickly and accurately; adopts an association rule mining algorithm to analyze the waybill association relationship between different waybills in the target waybill list; based on the cache database and the waybill association relationship, determines the target order that needs to be fulfilled by telephone and supplements the telephone fulfillment result, which can intelligently judge whether the order has been fulfilled by telephone and reduce manual intervention; thereby, supplements are made for orders that have not been fulfilled by telephone rules, ensuring that all orders can be judged for telephone fulfillment in a timely manner.

[0081] It should be noted that the order in which the embodiments of this specification are presented is for illustrative purposes only and does not represent the superiority or inferiority of the embodiments. Furthermore, the foregoing descriptions are of specific embodiments of this specification. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recited in the claims may be performed in an order different from that in the embodiments and still achieve the desired results. Furthermore, the processes depicted in the accompanying drawings do not necessarily require the specific order or sequential order shown to achieve the desired results. In certain embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0082] The various embodiments in this specification are described in a progressive manner. Similar portions between the various embodiments can be referenced to each other, and each embodiment focuses on the differences from the other embodiments. In particular, the device, equipment, and storage medium embodiments are generally similar to the method embodiments, so their descriptions are relatively simplified. For relevant portions, refer to the descriptions of the method embodiments.

[0083] Those skilled in the art will understand that all or part of the steps of implementing the above embodiments may be accomplished by hardware, or by a program instructing the relevant hardware to accomplish the steps. The program may be stored in a computer storage medium, and the above-mentioned storage medium may be a read-only memory, a disk, or an optical disk, etc.

[0084] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. A method for supplementing the performance of a telecom contract, characterized in that: The method comprises: Receive a user ID query request, and search the order data set for a user ID that matches the waybill number at the optimal call time; Performing a credibility evaluation on the user ID using a Bayesian classification algorithm, and determining the user ID as a target user ID if the user ID is determined to be credible; Use a time series prediction model to predict the order prediction results of the target user ID in the future period; caching a target waybill list associated with the target user ID in a cache database according to the order prediction result; Using an association rule mining algorithm to analyze the waybill association relationships between different waybill items in the target waybill list; According to the cache database and the waybill association relationship, the target order that needs to be fulfilled by telephone is determined and the result of the telephone fulfillment is supplemented.

2. The method according to claim 1, characterized in that The receiving of the user ID query request and searching the order data set for a user ID that matches the waybill number at the optimal call time includes: Receive a user ID query request, perform format verification on the waybill number carried in the request, and obtain a verification result; When the verification result indicates that the input format of the waybill number meets the requirements for calling the Vienna interface with the waybill number, the optimal calling time and the optimal calling path of the interface are determined by the intelligent interface calling optimization model; The interface is called according to the optimal calling path, and a user ID that matches the waybill number at the optimal calling time is searched in the order data set.

3. The method according to claim 2, characterized in that The training method of the intelligent interface calling the optimization model includes: Obtaining sample interface call data of a sample interface in a historical period; the sample interface is marked with a sample optimal call time label and a sample optimal call path label, and the sample interface call data includes at least one of interface response time, call success rate, and call frequency; Inputting the sample interface call data into a reinforcement learning model to extract sample busyness characteristics and sample network status characteristics of the sample interface; Obtaining a sample optimal call time result of the sample interface according to the sample busyness characteristics, and obtaining a sample optimal call path result of the sample interface according to the sample network status characteristics; Determining target loss data based on a difference between the sample best call time result and the sample best call time label, and a difference between the sample best call path result and the sample best call path label; The model parameters of the reinforcement learning model are adjusted according to the target loss data until a training end condition is met, and the reinforcement learning model at the end of training is determined as the intelligent interface call optimization model.

4. The method according to claim 1, wherein Before calling the interface according to the optimal call path and searching the order data set for a user ID that matches the waybill number at the optimal call time, the method further includes: Obtain order data from a logistics order system, and perform data cleaning on missing values, duplicate values, and abnormal values in the order data to obtain cleaned data; Preprocessing the cleaned data using natural language processing technology to obtain processed data; Extract key information from the processed data and construct an order data set.

5. The method according to claim 1, wherein The user ID is the ID currently obtained by the Vienna interface, and the credibility evaluation of the user ID using the Bayesian classification algorithm includes: Obtaining the correct probability and the incorrect probability of the historical user ID in the current Vienna interface; Get the data characteristics returned by the current Vienna interface; Based on the data characteristics, the correct probability and the error probability of the historical user ID, a Bayesian classification algorithm is used to calculate the predicted probability that the user ID is the correct result; If the predicted probability is less than a preset threshold, it is determined that the user ID is untrustworthy; If the predicted probability is greater than or equal to the preset threshold, it is determined that the user ID is credible.

6. The method according to claim 1, characterized in that The adopting of an association rule mining algorithm to analyze the waybill association relationships between different waybills in the target waybill list includes: Obtain target order attributes of each target waybill in the target waybill list; the target order attributes include at least one of commodity type, order time, and delivery address; According to the target order attributes, the waybills with associated relationships in the target waybill list are aggregated to obtain a combination of orders with associated relationships.

7. The method according to claim 1, characterized in that The step of caching a target waybill list associated with the target user ID in a cache database according to the order prediction result includes: Obtain key data from the target waybill list; Using blockchain technology to encrypt and store the key data in the cache database; Accordingly, after caching the target waybill list associated with the target user ID in the cache database according to the order prediction result, the method further includes: When the remaining storage capacity of the cache database is less than a preset capacity threshold, obtaining the access time and access count of each data in the cache database; Filtering the data to be deleted by using the LRU algorithm and the access time and access count of each data, and deleting the data to be deleted from the cache database; In response to a data query request, using a Bloom filter to determine whether the data to be queried is in the cache database; If the judgment result is that the probability that the data to be queried exists in the cache database is greater than the preset probability threshold, querying whether the data to be queried exists in the cache database; If not, it is determined that the data to be queried is not in the cache database.

8. A device for supplementing the performance of a contract through telecom connection, characterized in that: The device comprises: A request receiving module, configured to receive a user ID query request and search the order data set for a user ID that matches the waybill number at the optimal call time; a target ID determination module, configured to perform a credibility assessment on the user ID using a Bayesian classification algorithm, and determine the user ID as a target user ID if the user ID is determined to be credible; An order result prediction module is used to predict the order prediction results of the target user ID in the future period using a time series prediction model; A cache module, configured to cache a target waybill list associated with the target user ID in a cache database according to the order prediction result; A waybill relationship determination module, configured to analyze the waybill association relationships between different waybills in the target waybill list using an association rule mining algorithm; The telephone connection result determination module is used to determine the target order that needs to be fulfilled by telephone connection based on the cache database and the waybill association relationship and to supplement the telephone connection fulfillment result.

9. An electronic device, characterized in that: The device includes: a processor and a memory, wherein the memory stores at least one instruction or at least one program, and the at least one instruction or at least one program is loaded and executed by the processor to implement the method for supplementing the performance of the telecommunication contract as described in any one of claims 1 to 7.

10. A computer storage medium, characterized in that The computer storage medium stores at least one instruction or at least one program, and the at least one instruction or at least one program is loaded and executed by the processor to implement the method for supplementing the performance of the telecommunication contract as described in any one of claims 1 to 7.

Images