Bank self-service equipment application parameter configuration management method, terminal and medium

Abstract

The invention relates to the field of bank equipment management, and particularly provides a bank self-service equipment application parameter configuration management method, a terminal and a medium, a server receives parameter configuration information, and detects whether a parameter setting script of corresponding equipment exists in a database according to target automatic equipment information in the parameter configuration information; if yes, constructing a parameter modification description file of each piece of target self-service equipment according to the parameter configuration information, and calling a corresponding parameter setting script; and encrypting the parameter modification description file and the corresponding parameter setting script and then transmitting the encrypted file and the encrypted script to the client. And after the client receives the parameter setting script, according to the received parameter key value pair, performing atomization modification on the parameters of the target self-service equipment through at least one mode of calling a configuration interface of the equipment, modifying an operating system registry, updating a specific configuration file or restarting a specific system service. The parameter configuration efficiency is improved, and the operation and maintenance cost is reduced.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of bank equipment management, in particular to a bank self-service equipment application parameter configuration management method, a terminal and a medium. BACKGROUND

[0002] In daily operation and management, banks need to configure and adjust application parameters of various types and brands of self-service equipment such as cash dispensers, cash deposit and withdrawal all-in-one machines, non-cash self-service terminal equipment, intelligent teller machines, etc., such as new equipment going online, application program upgrading, equipment physical location relocation, and asset ownership transfer.

[0003] In the traditional parameter configuration mode, bank staff and equipment maintenance engineers mainly rely on on-site operation of the equipment, which is prone to parameter configuration errors, thereby causing equipment operation failure or abnormal account data. To improve the disadvantages of on-site operation, the scheme of "file distribution system issuing parameter upgrade package" is gradually adopted: the equipment manufacturer writes a special upgrade package according to the bank's parameter modification requirements, and after the bank's technology department simulates and verifies the effectiveness of the parameter settings in the test environment, the upgrade package is pushed to the self-service equipment in the production environment to complete the parameter modification. However, each parameter adjustment requires the cooperation of the bank's technology department and multiple manufacturers to complete the upgrade package writing, test environment verification, production environment submission, and other processes, and the collaboration between departments and manufacturers is complex, which not only prolongs the parameter configuration period, but also increases the communication cost and version management risk due to the large number of participants, reducing the parameter adjustment efficiency. SUMMARY

[0004] To solve the above problems, the present application provides a bank self-service equipment application parameter configuration management method, a terminal and a medium, which improves the parameter configuration efficiency and reduces the operation and maintenance cost.

[0005] In a first aspect, the technical solution of the present application provides a bank self-service equipment application parameter configuration management method, which is executed by a server and includes the following steps: Receiving parameter configuration information input by a user in a Web management interface, wherein the parameter configuration information includes target self-service equipment information; Detecting whether there is a parameter setting script of the corresponding equipment in the database according to the target automatic equipment information; if there is, constructing a parameter modification description file of each target self-service equipment according to the parameter configuration information, and calling the corresponding parameter setting script; Transmitting the parameter modification description file and the corresponding parameter setting script to the client after encryption.

[0006] In an optional embodiment, constructing a parameter modification description file of each target self-service equipment according to the parameter configuration information specifically includes: Analyzing the parameter configuration information, obtaining a target self-service device list and a general parameter value to be configured; the target self-service device list includes device identification information of at least two self-service devices; According to the target self-service device list, sequentially calling the latest current parameter snapshot of each target self-service device from the database; Traversing the target self-service device list, for each target self-service device in the list, creating a parameter modification description file, writing the general parameter value, the device identification information of the target self-service device, and the device-specific information extracted from the corresponding latest current parameter snapshot into the created parameter modification description file, and generating a description file containing parameter incremental modification content; Assigning a unique task serial number to each parameter modification description file, and storing the task serial number and the corresponding target self-service device in association.

[0007] In an optional embodiment, before constructing the parameter modification description file of each target self-service device according to the parameter configuration information, the following steps are further included: Based on the machine learning model, the current parameter configuration is matched with historical configuration cases for similarity, and the risk probability is predicted according to the matching result; If the predicted risk probability is higher than the risk threshold, an early warning and recommended value are issued on the Web interface.

[0008] In an optional embodiment, based on the machine learning model, the current parameter configuration is matched with historical configuration cases for similarity, and the risk probability is predicted according to the matching result, specifically including: Extracting historical configuration cases from the historical configuration record database, each historical configuration case forming a data sample; performing feature engineering processing on each data sample to extract and construct a feature vector; the feature vector includes the result label of the historical configuration case, used to identify success or failure; Analyzing the current parameter configuration information, and converting the current parameter configuration information into a to-be-predicted feature vector according to the same feature engineering processing method as the above steps; Calculating the similarity between the to-be-predicted feature vector and the feature vector of the historical configuration case; According to the calculation result, retrieving K historical cases most similar to the current configuration to form a similar case set; Inputting the to-be-predicted feature vector into a pre-trained parameter configuration risk prediction model to output a risk probability value; Fusing the similar case set and the risk probability value to generate a final risk prediction result, including a risk level, a prediction basis, and a modification suggestion generated when the risk probability value exceeds a threshold.

[0009] In an optional embodiment, the method generates a modification suggestion by the following steps: The parameter configuration risk prediction model obtains the feature importance contribution degree of the current to-be-predicted feature vector, identifies one or more key parameters that cause the risk probability to increase in the current prediction according to the feature importance contribution degree, and marks the key parameters as key risk factors; For each key risk factor, a corresponding safe value range is determined, including: taking the device static features of the current configuration as a constraint condition, retrieving all cases labeled as "success" from a historical configuration case feature library to form a success case set; extracting the parameter values corresponding to the key risk factor in the success case set to form a value distribution data set of the parameter; performing statistical analysis on the value distribution data set, and determining the main concentration interval of the corresponding parameter value by using a kernel density estimation algorithm, and taking the upper limit and lower limit of the main concentration interval as the critical values of the recommended safe value range of the key risk factor.

[0010] In an optional embodiment, the parameter configuration risk prediction model adopts a gradient boosting decision tree model.

[0011] In an optional embodiment, after the parameter modification description file and the corresponding parameter setting script are transmitted to the client after being encrypted, the following steps are further included: A monitoring timer is started after the configuration, and the running state performance data of the target automatic device is continuously collected within a preset time window. After the time window ends, the running state performance data collected is used to generate a result label for the current configuration operation by using an efficiency evaluation algorithm, including: comparing the target index after the configuration with the base index before the configuration, and determining whether the index change exceeds a predetermined reasonable threshold range, if not, the case is labeled as a success case, otherwise, the case is labeled as a failure case.

[0012] In a second aspect, the technical solution of the present application provides a bank self-service device application parameter configuration management method, which is executed by a client and specifically includes the following steps: An encrypted data packet from a server is received, which contains an encrypted parameter modification description file, a parameter setting script and an additional digital signature. The encrypted data packet is decrypted using a preset decryption key. The decrypted parameter modification description file is parsed to extract the target object of the current parameter configuration, the specific parameter key-value pairs to be modified, and the context information required for execution. The parameter setting script is loaded into the memory, and the parsed parameter key-value pairs are injected into the execution context of the parameter setting script in the form of command line parameters, environment variables or configuration files. The parameter setting script atomically modifies the parameters of the target self-service device by at least one of the following manners: calling a configuration interface of the device, modifying a system registry, updating a specific configuration file, or restarting a specific system service, according to the received parameter key-value pairs.

[0013] In a third aspect, the technical solution of the present application provides a terminal, comprising: a memory configured to store a bank self-service device application parameter configuration management program; a processor configured to execute the bank self-service device application parameter configuration management program to implement the steps of the bank self-service device application parameter configuration management method according to any one of the above aspects.

[0014] In a fourth aspect, the technical solution of the present application provides a computer readable storage medium, wherein the readable storage medium stores a bank self-service device application parameter configuration management program, and the bank self-service device application parameter configuration management program, when executed by a processor, implements the steps of the bank self-service device application parameter configuration management method according to any one of the above aspects.

[0015] As can be seen from the above technical solutions, the present application has the following advantages: 1. The present application realizes remote parameter configuration through a unified Web management interface of a server, without the need for on-site operation by staff and engineers; at the same time, the system matches the pre-set parameter setting script based on the “type, brand, and model” of the device, and only one script needs to be made and tested, and subsequent parameter modification does not require the participation of manufacturers, which greatly reduces the collaboration between departments and manufacturers, shortens the parameter configuration period, and significantly reduces the labor investment and time cost; 2. The present application detects whether there is a corresponding parameter setting script in the target self-service device information detection database, to ensure that the configuration operation matches the device characteristics; at the same time, the parameter configuration information is transmitted to the client after encryption, to avoid data tampering during transmission. Further, the system can also match the similarity between the current configuration and historical cases through a machine learning model, predict the risk probability, and issue a warning when the risk is high, to reduce parameter configuration errors from the aspects of operation specification, data security, and risk prediction, reduce the occurrence rate of device operation failure and account exception, and improve the overall operation stability of the self-service device; 3. The present application further assigns a unique task serial number to the parameter modification description file of each target self-service device during the parameter configuration process, and stores the associated device identification information; at the same time, the result tag (success / failure) and failure reason are recorded after the configuration is completed, so that the parameter modification history of each device can be completely traced, the audit demand is met, and subsequent device maintenance, problem tracing, and operation quality analysis are facilitated; 4、The application breaks through the parameter setting barrier of different brands and different types of self-service equipment, realizes the parameter management of all equipment through a unified system: the staff can directly filter the target equipment and input parameter configuration information on the Web interface, the system automatically completes script matching, description file generation and encrypted transmission, without the need to adapt to the configuration tools or format requirements of different manufacturers, solving the fragmentation problem of equipment management in traditional solutions, improving the convenience and efficiency of parameter configuration, and being suitable for the parameter batch adjustment scene of large-scale self-service equipment cluster of banks. BRIEF DESCRIPTION OF DRAWINGS

[0016] In order to more clearly illustrate the technical solutions of the present application, the following will briefly introduce the drawings needed to be used in the description, obviously, the drawings in the following description are only some embodiments of the present application, and for those skilled in the art, other drawings can also be obtained without creative labor on the basis of these drawings.

[0017] Figure 1 A bank self-service equipment application parameter configuration management method flowchart provided by the server for the embodiment of the present application.

[0018] Figure 2 A bank self-service equipment application parameter configuration management method flowchart provided by the client for the embodiment of the present application.

[0019] Figure 3 A terminal structure diagram provided by the embodiment of the present application. DETAILED DESCRIPTION

[0020] In order to make the application purpose, features and advantages of the present application more obvious and easy to understand, the following will use specific embodiments and drawings to clearly and completely describe the technical solutions protected by the present application, obviously, the following described embodiments are only some of the embodiments of the present application, not all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor are within the scope of protection of the present application.

[0021] Unless otherwise defined, all technical and scientific terms used in the present application have the same meaning as understood by those skilled in the art to which the present application belongs. The terms used in the specification of the present application are only for the purpose of describing the specific embodiments, and are not intended to limit the present application.

[0022] Figure 1 A bank self-service equipment application parameter configuration management method flowchart provided by the embodiment of the present application, the method is executed by the server, according to different needs, the order of steps in the flowchart can be changed, some can be omitted.

[0023] As Figure 1 shown, the method comprises the following steps.

[0024] S1, receiving parameter configuration information input by a user at a Web management interface, the parameter configuration information containing target self-service device information.

[0025] The server runs an application system providing Web services, and an operation and maintenance personnel logs in a Web management interface of the system through a browser. The Web management interface provides a form for the user to fill in or select, so as to generate the parameter configuration information, which mainly includes target self-service device information and parameter content to be configured.

[0026] The target self-service device information is used to accurately specify the object range of the current configuration operation, including: Device type: such as an automatic teller machine (ATM), a deposit and withdrawal integrated machine (CRS), an intelligent counter, etc. Brand and model: such as IBM, NCR, Guangdian Yuntong, etc. and specific models thereof; Device number: a unique identity of the device; IP address: a network address of the device, which can be used for accurate positioning; Affiliated institution information: such as branch, branch, and network point code, which is used for batch selection according to the organization.

[0027] The user can specify one or more devices as targets through checking, inputting, or importing files, etc.

[0028] Parameter content to be configured: that is, a parameter key Key and a corresponding target value Value that the user hopes to modify. For example, TransactionTimeout = 120, that is, modifying the transaction timeout time to 120 seconds.

[0029] After the user submits the form, the parameter configuration information is sent to the server through HTTP / HTTPS protocol, the Web application of the server receives and analyzes the information, and converts it into an internal data structure for subsequent processing.

[0030] S2, detecting whether there is a parameter setting script of the corresponding device in the database according to the target automatic device information; if there is, constructing a parameter modification description file of each target self-service device according to the parameter configuration information, and calling the corresponding parameter setting script.

[0031] After the server receives the configuration request, it first performs feasibility check and resource preparation.

[0032] Specifically, the server is provided with a configuration management database, in which parameter setting scripts for self-service devices of different brands, models, and even software versions are pre-stored. These scripts are programs for automatically modifying device parameters, which can be Shell scripts, PowerShell scripts, Python scripts, or batch files, etc. The server queries whether there is a matching script in the database according to the target self-service device information received in S1, especially the brand and model. It is ensured that subsequent operations will only be performed when there is an available execution tool, avoiding the issuance of invalid instructions to devices that cannot be processed, and improving the reliability of operations.

[0033] If a corresponding script is detected, the server starts to generate a parameter modification description file (usually in a structured format such as JSON, XML, or YAML) for each target device. This file is the "input" or "configuration list" for script execution, and its content at least includes: device_id: [device number], ip_address: [IP address], parameters: [list of parameter key-value pairs to be modified (from S1)]. This step creates an independent description file for each device, realizes individualized processing in batch operations, and ensures the accuracy of configuration instructions. At the same time, the server reads the matching script file into memory or prepares to send it from the configuration management database.

[0034] S3, the parameter modification description file and the corresponding parameter setting script are encrypted and transmitted to the client.

[0035] To prevent sensitive information from being stolen or tampered with during transmission, the server encrypts the parameter modification description file and parameter setting script generated in step S2 using a pre-set encryption algorithm (such as AES, RSA, etc.) before transmission. Preferably, a digital signature can also be attached to the encrypted data packet to ensure the integrity and authenticity of the data. After encryption, the server establishes a connection with the client agent program on the target device through a secure communication protocol and transmits the encrypted data packet to the client. The client agent program runs on the self-service device and is responsible for receiving instructions, executing scripts, and feeding back results.

[0036] In some optional embodiments, the parameter modification description file for each target self-service device is constructed according to the parameter configuration information in step S2, which specifically includes the following steps.

[0037] S201, analyze the parameter configuration information to obtain a list of target self-service devices and general parameter values to be configured; the list of target self-service devices includes device identification information of at least two self-service devices.

[0038] S202, according to the target self-service device list, from the database, sequentially call each target self-service device's latest current parameter snapshot.

[0039] S203, traversing the target self-service device list, for each target self-service device in the list, create a parameter modification description file, write the general parameter value, the device identification information of the target self-service device and the device-specific information extracted from the corresponding latest current parameter snapshot into the created parameter modification description file, generate a description file containing parameter incremental modification content.

[0040] S204, assign a unique task serial number to each parameter modification description file, and store the task serial number and the corresponding target self-service device.

[0041] First, the server parses the user-submitted batch configuration request, separating two core contents: one is the target device list, which is a collection of unique identifiers (such as device number, IP address) of several self-service devices; the other is the general parameter configuration set, which is a set of parameter key-value pairs that need to be uniformly applied to all devices in the list. Traverse each device identifier in the target device list and perform the following operations for each device: a) Create an empty description file: create a new, empty parameter modification description file in the server's temporary storage area, such as an XML or JSON format file; b) Inject device uniqueness information: write the unique identification information of the device currently being processed (including but not limited to device type, brand, model, device number, IP address, and institution information) into the description file's predefined field, ensuring the description file's binding relationship with the specific device; c) Inject differentiated configuration content: write the general parameter configuration set into the description file. In addition, to improve the accuracy and fault tolerance of the configuration, the system can also query the device's latest current configuration snapshot from the database and write some related parameters or device-specific parameters (such as hardware serial number, firmware version number, etc.) in the snapshot into the description file, forming a complete and context-rich configuration context; d) Generate file identifier: generate a globally unique task serial number or file identifier for the description file, and map the identifier with the target device's number, recording it in the task management database. This identifier is used to track the configuration task's delivery, execution and feedback status in subsequent steps.

[0042] Through the above process, the system decomposes and transforms a user-submitted batch parameter configuration request into a set of independent parameter modification description files corresponding to each target self-service device.

[0043] In some optional embodiments, in order to realize intelligent prediction and accurate suggestion of parameter configuration risks, before constructing the parameter modification description file of each target self-service device according to the parameter configuration information, the following steps are further included.

[0044] S211, based on the machine learning model, the current parameter configuration is matched with the historical configuration cases for similarity, and the risk probability is predicted according to the matching result.

[0045] S211.1, extract historical configuration cases from the historical configuration record database, each historical configuration case forms a data sample; perform feature engineering processing on each data sample to extract and construct a feature vector. The feature vector includes: Static features: attribute information of the target self-service device, including device type, brand, model, and affiliated organization; Dynamic features: environmental context information at the time of parameter configuration operation, including operating system version, network period, and application software version; Configuration content features: specific parameter keys and their corresponding parameter values contained in the parameter configuration information; Result label: a label generated according to the running state data of the target self-service device within a preset time window after parameter configuration, the label is used to identify whether the historical configuration case is a success case or a failure case; the running state data includes transaction success rate, fault code occurrence frequency, and device online rate.

[0046] S211.2, analyze the current parameter configuration information, and convert the current parameter configuration information into a to-be-predicted feature vector according to the same feature engineering processing method as the above steps.

[0047] S211.3, calculate the similarity between the to-be-predicted feature vector and the feature vector of the historical configuration case.

[0048] S211.4, according to the calculation result, retrieve the K most similar historical cases to form a similar case set.

[0049] The similarity calculation adopts cosine similarity or Euclidean distance algorithm; the K most similar historical cases are retrieved to form a similar case set.

[0050] S211.5, input the to-be-predicted feature vector into the pre-trained parameter configuration risk prediction model, and output a risk probability value.

[0051] The parameter configuration risk prediction model adopts a gradient boosting decision tree model, uses sample data in the historical configuration case feature library to supervise the training of the gradient boosting decision tree model, and generates the parameter configuration risk prediction model. After the model training is completed, the model is deployed in the prediction engine of the server and an application program interface is provided for calling.

[0052] The core of the parameter configuration risk prediction model is to convert historical experience into quantifiable prediction knowledge. The input of the model is a feature vector processed through feature engineering, and the output is a risk probability value between 0 and 1. The closer the value is to 1, the higher the risk of causing device operation failure caused by this parameter configuration.

[0053] S211.6, fusing the similar case set and the risk probability value to generate the final risk prediction result, including the risk level, the prediction basis, and the modification suggestion generated when the risk probability value exceeds the threshold value.

[0054] Risk level: high, medium, and low risk levels divided according to the risk probability value.

[0055] Prediction basis: the top-N most similar historical cases extracted from the similar case set, especially the failure cases and their corresponding failure reasons.

[0056] Configuration suggestion: if the predicted risk probability exceeds the preset threshold value, a modification suggestion is automatically generated, and the modification suggestion includes the recommended safe parameter value range.

[0057] S212, if the predicted risk probability is higher than the risk threshold value, an early warning and a recommended value are issued on the Web interface.

[0058] Through the above process, the risk is estimated in advance, the early warning and the recommended value are given, and the relevant personnel can adjust the parameter configuration according to the needs, use the latest parameter configuration for subsequent steps, so as to reduce the probability of risk occurrence.

[0059] In some optional embodiments, the generation of the modification suggestion when the predicted risk probability is higher than the risk threshold value is realized through the following steps.

[0060] S211.61, obtaining the feature importance contribution degree of the parameter configuration risk prediction model to the current to-be-predicted feature vector, identifying one or more key parameters that cause the predicted risk probability to rise according to the feature importance contribution degree, and marking them as key risk factors.

[0061] The feature importance contribution degree refers to a quantitative measure of the influence degree or contribution size of an input feature (input variable) on the final prediction result when the model makes a prediction. Specifically, when the parameter configuration risk prediction model completes prediction, its internal mechanism can backtrack and analyze the decision path of the prediction result, thereby calculating the contribution degree of each feature dimension constituting the feature vector to be predicted to the output risk probability value.

[0062] For tree models, the contribution degree of features is preferably calculated using a splitting gain-based method, which can more accurately reflect the specific contribution of features in each split.

[0063] The feature importance contribution degree output by the model is usually a numerical list or a normalized percentage list. Each numerical value in the list corresponds to a feature in the feature vector to be predicted, and the size of the numerical value directly represents the positive contribution degree of the corresponding feature to the high-risk prediction result. A higher positive contribution degree value means that the presence of the feature value significantly increases the risk probability predicted by the model.

[0064] Specifically, the features correspond to the elements in the parameter configuration information. After the server obtains the feature importance contribution degree of the current prediction of the model, it traverses the contribution degree list and selects one or more features with the highest contribution degree. The parameter key corresponding to these high-contribution-degree features is the key risk factor that causes the risk probability of the current prediction to increase.

[0065] For example, if it is found that the feature corresponding to the "transaction timeout" parameter has a much higher contribution degree than other features, then regardless of its configuration value (60), it will be marked as a key risk factor. This indicates that modifying this parameter itself has a high risk, or that its current configuration value, in combination with other features such as the current device model, brand, etc., forms a high-risk pattern.

[0066] S211.62, for each key risk factor, determining the corresponding safe value range, including: taking the configured device static features as constraint conditions, retrieving all cases labeled as "success" from the historical configuration case feature library to form a success case set; extracting the parameter values corresponding to the key risk factor from the success case set to form a value distribution dataset of the parameter; performing statistical analysis on the value distribution dataset, and determining the main concentration interval of the corresponding parameter value using a kernel density estimation algorithm, and taking the upper and lower limits of the main concentration interval as the critical values of the recommended safe value range of the key risk factor.

[0067] Specifically, first, success case clustering retrieval is performed, and all cases with a label of "success" are retrieved from a historical configuration case feature library as constraint conditions to form a success case set. Then, key parameter value distribution analysis is performed, that is, parameter values corresponding to key risk factors in the success case set are extracted to form a value distribution dataset of the parameters. Finally, safety range calculation is performed, that is, a kernel density estimation algorithm is used to determine the main concentration interval of the parameter values to determine the critical value of the safety value range.

[0068] The above process accurately locates the key risk factors (that is, one or more specific parameters) that cause high risk prediction by using the feature importance contribution analysis function inherent in the machine learning model, so that the attention of the operation and maintenance personnel can be directly guided to the root cause of the problem. In addition, the generated modification suggestion (safety value range) is not based on fixed rules or subjective experience of experts, but is automatically learned and calculated from a large number of historical success cases by statistical methods. This is equivalent to generating an objective and quantitative safety benchmark for each key parameter based on its "historical best practice" data. The resulting suggestion avoids human bias and has high reliability.

[0069] In some optional embodiments, after the parameter modification description file and the corresponding parameter setting script are transmitted to the client after being encrypted, the following steps are further included.

[0070] S4, a post-configuration monitoring timer is started, and running state performance data of the target automatic device is continuously collected within a preset time window.

[0071] Specifically, the server starts a post-configuration monitoring timer for this configuration task immediately after confirming that the configuration instruction has been successfully issued, and sets a preset observation time window, for example, 24 hours. The length of the time window can be preset or dynamically adjusted according to the business importance and impact range of the modified parameters.

[0072] Within the time window, the server asynchronously collects running state performance data of the target self-service device. The running state performance data is a quantitative indicator collected for evaluating the configuration effect, including: Transaction flow records, such as total number of transactions, transaction success rate (number of successful transactions / total number of transactions), transaction failure type distribution, and average transaction processing time; Hardware fault logs, such as fault codes, fault occurrence times and frequencies of core modules such as card readers, printers, cash boxes, and password keypads; Application performance indicators, such as CPU average occupancy rate, memory occupancy rate, response time of specific application processes, and network connection status.

[0073] S5, after the end of the time window, based on the collected running state performance data, the performance evaluation algorithm generates a result label for this configuration operation, including: comparing the configured target indicators with the pre-configuration base indicators, and determining whether the indicator change exceeds the predetermined reasonable threshold range, if not, it is marked as a successful case, otherwise it is marked as a failure case.

[0074] S51, data preprocessing and indicator extraction.

[0075] The original performance data collected within the time window is cleaned, aggregated, and the target indicators for evaluation are calculated. For example, the "average transaction success rate within 24 hours after configuration" is calculated as a target indicator.

[0076] S52, obtain baseline data for comparison.

[0077] From the historical database of the server, the same performance data of the target device before parameter configuration modification and the same length is retrieved, and the corresponding base indicators are calculated. For example, "average transaction success rate within 24 hours before configuration".

[0078] S53, change analysis and threshold judgment.

[0079] The target indicators obtained in step S51 are compared with the base indicators obtained in step S52, and the change amount or change rate is calculated. Then, the change is compared with a predetermined reasonable threshold range. The threshold range can be pre-set according to historical experience, business requirements or statistical rules.

[0080] For example, assuming that the reasonable threshold range of "transaction success rate" is defined as "not more than 0.5% decrease". If the success rate after configuration decreases by 0.3% compared with before configuration, it is considered that the change is within the reasonable range; if it decreases by 1.0%, it is determined that it exceeds the reasonable range.

[0081] S54, generate result label.

[0082] If the changes of all key target indicators (such as transaction success rate, failure rate) do not exceed their respective reasonable threshold range, the performance evaluation algorithm determines that this parameter configuration does not have a negative impact on device operation, and automatically marks this configuration case as "successful case".

[0083] If the change of any key target indicator exceeds its reasonable threshold range, it is determined that this configuration may introduce problems, and it is automatically marked as "failure case".

[0084] The above steps S4 and S5 realize the post-effect verification of parameter configuration operation, and provide data support for operation and maintenance decision.

[0085] Figure 2 A bank self-service equipment application parameter configuration management method flowchart is provided for an embodiment of the present application. The method is executed by a client. The order of steps in the flowchart can be changed according to different needs, and some steps can be omitted.

[0086] As shown in the method includes the following steps. Figure 2

[0087] SS1, receiving an encrypted data packet from the server, the encrypted data packet containing an encrypted parameter modification description file, a parameter setting script and an additional digital signature.

[0088] Specifically, the client agent program continuously listens to the communication request of the server on a specific network port. When the server initiates a connection and transmits data, the client receives the complete encrypted data packet. The data packet is constructed by the server to ensure transmission security, and its content is processed by an encryption algorithm and an additional digital signature based on asymmetric encryption technology to ensure the legality of the instruction source, the integrity of the data and the tamper resistance.

[0089] SS2, decrypting the encrypted data packet using a preset decryption key.

[0090] After receiving the encrypted data packet, the client calls its local security module. The module stores the decryption key (for symmetric encryption) negotiated or preset with the server or the private key of the client (for asymmetric encryption). The key is used to decrypt the data packet to restore the original parameter modification description file, the plaintext content of the parameter setting script and the digital signature. Then, the client verifies the digital signature using the preset server public key. Only when the signature verification is passed, it is confirmed that the data is from a trusted server and has not been tampered with, and then the subsequent steps are executed. If decryption or signature verification fails, the process is terminated and an error message is returned to the server.

[0091] SS3, parsing the decrypted parameter modification description file to extract the target object of this parameter configuration, the specific parameter key-value pair to be modified, and the context information required for execution.

[0092] The client performs syntax analysis on the decrypted parameter modification description file (usually in JSON, XML or YAML format). Through analysis, the following key information is accurately extracted: Target object: confirm whether the device information (such as device number, IP address) is consistent with the identification in the description file, and ensure that the configuration instruction is sent to the device; ​Specific parameter key-value pairs to be modified: Obtain one or more parameter names (Key) and their corresponding target values (Value) that need to be modified. For example, {"SystemLogLevel": "DEBUG", "TransactionTimeout": 120}; Context information required for execution: May include working directory, log output path, execution timeout, and other auxiliary information required for script execution.

[0093] SS4, The parameter setting script is loaded into memory, and the parsed parameter key-value pairs are injected into the execution context of the parameter setting script in the form of command line parameters, environment variables, or configuration files.

[0094] The client prepares the execution environment. First, the decrypted parameter setting script is loaded from the file system into memory. Then, the parameter key-value pairs parsed in step SS3 are passed to the script in one or more of the following ways: Command line parameters: Format the parameter key-value pairs as command line parameters and pass them in when starting the script process. For example, execute the command: python config_script.py --LogLevel DEBUG --Timeout 120; Environment variables: Set the parameter key-value pairs as environment variables of the current process before starting the script process, and read the configuration values by reading environment variables inside the script; Configuration file: Dynamically generate a temporary configuration file with the parameter key-value pairs, and specify that the script reads the configuration from this temporary configuration file.

[0095] Through the above methods, the execution instruction and the specific configuration data are decoupled, so that the same script can complete different configuration tasks by receiving different inputs, enhancing the versatility and flexibility of the script.

[0096] SS5, The parameter setting script modifies the parameters of the target self-service device atomically by at least one of the following methods: calling the configuration interface of the device, modifying the Windows registry, updating a specific configuration file, or restarting a specific system service.

[0097] The client starts a separate process with elevated privileges to run the parameter setting script. The script performs specific modification operations according to its internal logic and received parameters.

[0098] Call the configuration interface of the device: Modify the parameters through the special API or SDK provided by the device manufacturer.

[0099] Modify the Windows registry (for Windows systems): Modify specific key values in the registry.

[0100] Update specific configuration files: directly modify the configuration files of the application, such as INI, JSON, YAML, XML files.

[0101] Restart specific system services: after modifying the configuration, restart the relevant system services to make the new configuration take effect.

[0102] "Atomic modification" means that the design of the script strives to achieve an "all-or-nothing" state, that is, either all modifications are successfully completed, or when any error is encountered, the modified part is rolled back to the state before execution as much as possible, and a clear failure code is returned, so as to avoid the device parameters in the intermediate state of partial effect, and to ensure the consistency and reliability of the configuration process.

[0103] Figure 3 A structure schematic diagram of a terminal 300 provided for an embodiment of the present application, comprising: a processor 310, a memory 320 and a communication unit 330. The processor 310 is used to realize the following steps when the bank self-service device application parameter configuration management program saved in the memory 320 is executed: Receiving parameter configuration information input by a user in a Web management interface, wherein the parameter configuration information contains target self-service device information; According to the target automatic device information, detecting whether there is a parameter setting script of the corresponding device in the database; if there is, constructing a parameter modification description file of each target self-service device according to the parameter configuration information, and calling the corresponding parameter setting script; Transmitting the encrypted parameter modification description file and the corresponding parameter setting script to the client.

[0104] The terminal 300 includes a processor 310, a memory 320 and a communication unit 330. These components communicate through one or more buses. Those skilled in the art can understand that the structure of the server shown in the figure does not constitute a limitation on the present application. It can be a bus structure, a star structure, or include more or fewer components than shown in the figure, or combine some components, or different component arrangements.

[0105] The memory 320 can be used to store the execution instructions of the processor 310, and the memory 320 can be implemented by any type of volatile or non-volatile storage terminal or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic storage, flash memory, magnetic disk or optical disk. When the execution instructions in the memory 320 are executed by the processor 310, the terminal 300 can execute part or all of the steps in the following method embodiments.

[0106] The processor 310 is the control center of the storage terminal, connects various parts of the entire electronic terminal through various interfaces and lines, executes the software programs and / or modules stored in the memory 320, and calls the data stored in the memory, so as to execute various functions of the electronic terminal and / or process data. The processor can be composed of an integrated circuit (IC), for example, can be composed of a single packaged IC, or can be composed of a plurality of packaged ICs with the same function or different functions. For example, the processor 310 can only include a central processing unit (CPU). In the embodiments of the application, the CPU can be a single operation core or can include multiple operation cores.

[0107] The communication unit 330 is used to establish a communication channel, so that the storage terminal can communicate with other terminals. Receive user data sent by other terminals or send user data to other terminals.

[0108] The application also provides a computer storage medium, and the storage medium can be a magnetic disk, an optical disk, a read-only memory (ROM) or a random access memory (RAM), etc.

[0109] The computer storage medium stores a bank self-service equipment application parameter configuration management program, and the bank self-service equipment application parameter configuration management program realizes the following steps when executed by the processor: Receive the parameter configuration information input by the user in the Web management interface, and the parameter configuration information includes target self-service equipment information; Detect whether there is a parameter setting script of the corresponding equipment in the database according to the target automatic equipment information; if there is, construct a parameter modification description file of each target self-service equipment according to the parameter configuration information, and call the corresponding parameter setting script; The parameter modification description file and the corresponding parameter setting script are encrypted and transmitted to the client.

[0110] Those skilled in the art can clearly understand that the technical solution in the embodiments of the present application can be realized by means of software on a general hardware platform. Based on such understanding, the technical solution in the embodiments of the present application can be embodied in the form of a software product, which is stored in a storage medium such as a U disk, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, and various storage media that can store program codes, and includes a plurality of instructions for causing a computer terminal (which can be a personal computer, a server, or a second terminal, a network terminal, etc.) to execute all or part of the steps of the method described in the embodiments of the present application.

[0111] In several embodiments provided by the present application, it should be understood that the disclosed system, device and method can be implemented in other manners. For example, the described device embodiments are merely schematic, and the division of units is merely a logical function division, and there can be another division manner in actual implementation. For example, a plurality of units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the displayed or discussed mutual couplings or direct couplings or communication connections between different units can be indirect couplings or communication connections through some interfaces, devices or units, and can be electrical, mechanical or in other forms.

[0112] The units described as separated components can or can not be physically separated, and the components displayed as units can or can not be physical units, i.e., can be located in one place, or can be distributed on a plurality of network units. In actual implementation, some or all of the units can be selected according to actual needs to achieve the purposes of the embodiments of the present application.

[0113] In addition, each functional unit in the embodiments of the present application can be integrated in one processing unit, or each unit can exist physically as a separate unit, or two or more units can be integrated in one unit.

[0114] The foregoing description of the disclosed embodiments enables a person skilled in the art to make or use the application. Modifications of these embodiments will occur to persons of skill in the art, and, while certain embodiments within the scope of the application are submitted as examples, it is the scope of the claims appended hereto that defines the true scope of the application.

Claims

1. A method for configuring and managing application parameters for bank self-service equipment, characterized in that, This method is executed by the server and includes the following steps: The web management interface receives parameter configuration information input by the user, which includes target self-service device information; The system checks whether a parameter setting script for the corresponding device exists in the target automated device information database. If it does, it constructs a parameter modification description file for each target self-service device based on the parameter configuration information and retrieves the corresponding parameter setting script. The parameter modification description file and the corresponding parameter setting script are encrypted and then transmitted to the client.

2. The method for configuring and managing application parameters of bank self-service equipment according to claim 1, characterized in that, Based on the parameter configuration information, construct parameter modification description files for each target self-service device, specifically including: Parse the parameter configuration information to obtain a list of target self-service devices and general parameter values ​​to be configured; the list of target self-service devices includes device identification information of at least two self-service devices; Based on the list of target self-service devices, retrieve the latest current parameter snapshot for each target self-service device from the database in sequence; Iterate through the list of target self-service devices. For each target self-service device in the list, create a parameter modification description file. Write the general parameter values, the device identification information of the target self-service device, and the device-specific information extracted from the corresponding latest current parameter snapshot into the created parameter modification description file to generate a description file containing incremental parameter modifications. Each parameter is modified in the description file and assigned a unique task serial number. The task serial number is then associated with and stored with the corresponding target self-service device.

3. The method for configuring and managing application parameters of bank self-service equipment according to claim 1, characterized in that, Before constructing the parameter modification description file for each target self-service device based on the parameter configuration information, the following steps are also included: Based on a machine learning model, the current parameter configuration is matched with historical configuration cases for similarity, and the risk probability is predicted based on the matching results. If the predicted risk probability is higher than the risk threshold, an alert and recommended value will be issued on the web interface.

4. The method for configuring and managing application parameters of bank self-service equipment according to claim 3, characterized in that, Based on a machine learning model, the current parameter configuration is compared with historical configuration cases in terms of similarity. The risk probability is predicted based on the matching results, specifically including: Historical configuration cases are extracted from the historical configuration record database, and each historical configuration case forms a data sample; feature engineering is performed on each data sample to extract and construct a feature vector; the feature vector includes the result label of the historical configuration case, which is used to identify success or failure; Parse the current parameter configuration information and transform it into a feature vector to be predicted using the same feature engineering process as the steps above. The similarity between the feature vector to be predicted and the feature vectors of historical configuration cases is calculated. Based on the calculation results, retrieve the K most similar historical cases to the current configuration to form a similar case set; The feature vector to be predicted is input into a pre-trained parameter configuration risk prediction model, which outputs a risk probability value. The final risk prediction result is generated by combining a set of similar cases and risk probability values, including the risk level, the basis for the prediction, and modification suggestions generated when the risk probability value exceeds the threshold.

5. The method for configuring and managing application parameters of bank self-service equipment according to claim 4, characterized in that, This method generates modification suggestions through the following steps: Obtain the feature importance contribution of the parameter configuration risk prediction model to the feature vector to be predicted, identify one or more key parameters that lead to an increase in the probability of risk in this prediction based on the feature importance contribution, and mark them as key risk factors; For each key risk factor, the corresponding safe value range is determined, including: using the static characteristics of the equipment configured this time as constraints, retrieving all cases labeled "success" from the historical configuration case feature library to form a set of successful cases; extracting the parameter values ​​corresponding to the key risk factor from the set of successful cases to form a value distribution dataset for the parameter; performing statistical analysis on the value distribution dataset, using a kernel density estimation algorithm to determine the main concentration interval of the corresponding parameter values, and using the upper and lower limits of the main concentration interval as the critical values ​​of the recommended safe value range for the key risk factor.

6. The method for configuring and managing application parameters of bank self-service equipment according to claim 4 or 5, characterized in that, The parameter configuration risk prediction model adopts a gradient boosting decision tree model.

7. The method for configuring and managing application parameters of bank self-service equipment according to claim 1, characterized in that, After encrypting the parameter modification description file and the corresponding parameter setting script and transmitting them to the client, the following steps are also included: After configuration is started, a monitoring timer is used to continuously collect the operating status and performance data of the target automated equipment within a preset time window; After the time window ends, based on the collected operational performance data, a performance evaluation algorithm is used to generate result labels for this configuration operation. These labels include: comparing the target indicators after configuration with the basic indicators before configuration, and determining whether the indicator changes exceed a predetermined reasonable threshold range. If not, the result is marked as a successful case; otherwise, it is marked as a failed case.

8. A method for configuring and managing application parameters for bank self-service equipment, characterized in that, This method is executed by the client and includes the following steps: Receive encrypted data packets from the server, which contain encrypted parameter modification description files, parameter setting scripts, and attached digital signatures; Use the preset decryption key to decrypt the encrypted data packet; The decrypted parameter modification description file is parsed to extract the target object of this parameter configuration, the specific parameter key-value pairs to be modified, and the context information required for execution. The parameter setting script is loaded into memory, and the parsed parameter key-value pairs are injected into the execution context of the parameter setting script as command-line arguments, environment variables, or configuration files; The parameter setting script atomically modifies the parameters of the target self-service device based on the received parameter key-value pairs by calling the device's configuration interface, modifying the operating system registry, updating a specific configuration file, or restarting a specific system service.

9. A terminal, characterized in that, include: Memory, used to store the configuration management program for application parameters of bank self-service equipment; A processor is configured to implement the steps of the bank self-service equipment application parameter configuration management method as described in any one of claims 1 to 7 when executing the bank self-service equipment application parameter configuration management program.

10. A computer-readable storage medium, characterized in that, The readable storage medium stores a bank self-service equipment application parameter configuration management program, which, when executed by a processor, implements the steps of the bank self-service equipment application parameter configuration management method as described in any one of claims 1 to 7.

Images