Customer performance analysis method, device and equipment and storage medium

Abstract

The invention relates to the technical field of information processing, in particular to a customer performance analysis method, device and equipment and a storage medium, which ensure the comprehensiveness and accuracy of data by collecting voice data of customers from different channels and cleaning the voice data, classify the cleaned data, calculate key performance indicators according to the classified data, and improve the performance of the customer. The key performance indicators are analyzed, the image-text report is generated according to the analysis result and the classified data, data viewing of different dimensions is supported, management personnel can conveniently and rapidly obtain customer performance information, customized access authority is provided for users of different levels, information management is clearer, and user experience is improved. The image-text report is encrypted by using the public key in the preset key pair, and the private key in the key pair is sent to the user side with the access permission based on the user access permission, so that the user side decrypts the encrypted report by using the private key, the risk of information leakage is reduced, and the degree of information security is improved.

Description

Technical Field

[0001] The present invention relates to the field of information processing technology, and in particular to a customer performance analysis method, device, equipment and storage medium. Background Art

[0002] At present, with the development of e-commerce, the demand for logistics and distribution services is growing. In order to improve service quality, many logistics companies are seeking effective means to track and manage customer voices in order to understand customer needs in a timely manner and make corresponding adjustments. Many companies only rely on traditional telephone customer service systems to collect customer feedback, but ignore the direct feedback information from customers after door-to-door delivery, resulting in incomplete data and failure to accurately reflect the real needs of customers. For the large amount of customer voice data collected, there is a lack of effective cleaning, classification and analysis methods, making it difficult to quickly calculate key performance indicators and unable to provide timely and accurate basis for corporate decision-making. Data display and query are not flexible enough, and do not support data viewing in different dimensions. In addition, the existing information security and authority management are imperfect. In the process of data sharing and access, there is a risk of information leakage. At the same time, the access rights of users at different levels are unclear, resulting in chaotic information management. Summary of the invention

[0003] In order to overcome the shortcomings of the prior art, the purpose of the present invention is to provide a customer performance analysis method, device, equipment and storage medium that ensures the comprehensiveness and accuracy of data, provides customized access rights for users of different levels, makes information management clearer, reduces the risk of information leakage, improves information security, supports data viewing in different dimensions, and facilitates managers to quickly obtain customer performance information.

[0004] The first aspect of the present invention provides a method for analyzing customer performance, comprising: collecting voice data of customers from different channels, the voice data including telephone contact records and feedback information after home delivery, cleaning the voice data to obtain cleaned data; classifying the cleaned data to obtain classified data, calculating key performance indicators based on the classified data, the key performance indicators including telephone contact rate and door-to-door rate; analyzing the key performance indicators to obtain analysis results, generating graphic reports based on the analysis results and the classified data; customizing and configuring different levels of user access rights, encrypting the graphic reports using the public key in a preset key pair to obtain an encrypted report; sending the private key in the key pair to a user terminal with access rights based on the user access rights, so that the user terminal uses the private key to decrypt the encrypted report.

[0005] Optionally, in a first implementation method of the first aspect of the present invention, the voice data of customers is collected from different channels, and the voice data includes telephone contact records and feedback information after home delivery, and the voice data is cleaned to obtain cleaned data, including: obtaining the customer's call record information in real time and creating a listener; using the listener to listen to the voice information feedback from the customer after home delivery, and when the listener listens to the voice information, obtaining the current voice information; using voice recognition technology to convert the call record information and the sound content in the voice information into text format to obtain voice data, using a data deduplication algorithm to remove duplicate data of the voice data to obtain deduplicated data; using regular expressions to correct erroneous data in the deduplicated data to obtain corrected data, and supplementing the missing values ​​of the corrected data by interpolation to obtain cleaned data.

[0006] Optionally, in a second implementation method of the first aspect of the present invention, the cleaning data is classified to obtain classified data, and key performance indicators are calculated based on the classified data, wherein the key performance indicators include a call rate and a door-to-door rate, including: classifying the cleaning data to obtain classified data, wherein the classified data includes telephone consultation category data, telephone complaint category data, telephone suggestion category data, satisfactory feedback category data, dissatisfied feedback category data and neutral feedback category data; counting the total number of the telephone consultation category data, the telephone complaint category data and the telephone suggestion category data in the classified data to obtain telephone contact record quantity information; counting the total number of the satisfactory feedback category data, the dissatisfied feedback category data and the neutral feedback category data in the classified data to obtain successful door-to-door delivery order quantity information; obtaining total customer quantity information and total order quantity information; calculating the call rate based on the telephone contact record quantity information and the total customer quantity information, and calculating the door-to-door rate based on the successful door-to-door delivery order quantity information and the total order quantity information.

[0007] Optionally, in a third implementation method of the first aspect of the present invention, the key performance indicators are analyzed to obtain analysis results, and a graphic report is generated based on the analysis results and the classified data, including: analyzing the key performance indicators to obtain analysis results; using a data visualization tool to generate the classified data into charts, the charts including bar charts, line charts and pie charts; calling a preset report template, filling the analysis results into the report template to obtain a text report, the text report including a data summary table, a detailed data table and an analysis report; merging the chart and the text report to obtain a graphic report.

[0008] Optionally, in a fourth implementation method of the first aspect of the present invention, the customized configuration of different levels of user access rights uses a public key in a preset key pair to encrypt the graphic report to obtain an encrypted report, including: obtaining a preset user authority setting table; configuring different levels of user access rights according to the user authority setting table; and encrypting the graphic report using a public key in a preset key pair to obtain an encrypted report.

[0009] Optionally, in a fifth implementation manner of the first aspect of the present invention, the private key in the key pair is sent to a user terminal with access rights based on the user access rights, so that the user terminal uses the private key to decrypt the encrypted report, including: pairing user terminals according to the mapping relationship of the user access rights; verifying the validity and legality of the user terminals; when the verification passes, sending the private key in the key pair to the user terminal, so that the user terminal uses the private key to decrypt the encrypted report.

[0010] Optionally, in a sixth implementation method of the first aspect of the present invention, after sending the private key in the key pair to a user terminal with access rights based on the user access rights so that the user terminal uses the private key to decrypt the encrypted report, it also includes: obtaining a timestamp from a timestamp service platform based on the report query time decrypted by the user terminal using the private key to obtain a user query timestamp; identifying the user ID of the user terminal, associating the user ID with the user query timestamp to obtain associated information; and uploading the associated information to the blockchain.

[0011] The second aspect of the present invention provides a customer performance analysis device, including: a collection and cleaning module, which is used to collect customer voice data from different channels, the voice data including telephone contact records and feedback information after home delivery, and clean the voice data to obtain cleaned data; a classification and calculation module, which is used to classify the cleaned data to obtain classified data, and calculate key performance indicators based on the classified data, and the key performance indicators include telephone contact rate and door-to-door rate; an analysis and generation module, which is used to analyze the key performance indicators to obtain analysis results, and generate graphic reports based on the analysis results and the classified data; a configuration encryption module, which is used to customize the configuration of different levels of user access rights, and use the public key in a preset key pair to encrypt the graphic report to obtain an encrypted report; a sending module, which is used to send the private key in the key pair to a user terminal with access rights based on the user access rights, so that the user terminal uses the private key to decrypt the encrypted report.

[0012] Optionally, in a first implementation method of the second aspect of the present invention, the collection and cleaning module includes: an acquisition and creation unit, which is used to acquire the customer's call record information in real time and create a listener; a monitoring and acquisition unit, which is used to use the listener to monitor the voice information feedback from the customer after home delivery, and when the listener monitors the voice information, it obtains the current voice information; a conversion and removal unit, which is used to use voice recognition technology to convert the sound content in the call record information and the voice information into a text format to obtain sound data, and use a data deduplication algorithm to remove duplicate data from the sound data to obtain deduplicated data; a correction and supplement unit, which is used to use a regular expression to correct the erroneous data in the deduplicated data to obtain corrected data, and supplement the missing values ​​of the corrected data by interpolation to obtain cleaned data.

[0013] Optionally, in a second implementation of the second aspect of the present invention, the classification calculation module includes: a classification unit, used to classify the cleaned data to obtain classified data, the classified data including telephone consultation category data, telephone complaint category data, telephone suggestion category data, satisfactory feedback category data, dissatisfied feedback category data and neutral feedback category data; a first statistical unit, used to count the total number of the telephone consultation category data, the telephone complaint category data and the telephone suggestion category data in the classified data to obtain telephone contact record quantity information; a second statistical unit, used to count the total number of the satisfactory feedback category data, the dissatisfied feedback category data and the neutral feedback category data in the classified data to obtain successful door-to-door delivery order quantity information; a first acquisition unit, used to acquire total customer quantity information and total order quantity information; a calculation unit, used to calculate the call rate based on the telephone contact record quantity information and the total customer quantity information, and calculate the door-to-door rate based on the successful door-to-door delivery order quantity information and the total order quantity information.

[0014] Optionally, in a third implementation of the second aspect of the present invention, the analysis generation module includes: an analysis unit, used to analyze the key performance indicators and obtain analysis results; a generation unit, used to use a data visualization tool to generate the classified data into charts, wherein the charts include bar charts, line charts and pie charts; a calling filling unit, used to call a preset report template, fill the analysis results into the report template, and obtain a text report, wherein the text report includes a data summary table, a detailed data table and an analysis report; a merging unit, used to merge the chart and the text report to obtain a graphic report.

[0015] Optionally, in a fourth implementation of the second aspect of the present invention, the configuration encryption module includes: a second acquisition unit, used to obtain a preset user authority setting table; a configuration unit, used to configure different levels of user access rights according to the user authority setting table; an encryption unit, used to encrypt the graphic report using the public key in a preset key pair to obtain an encrypted report.

[0016] Optionally, in a fifth implementation of the second aspect of the present invention, the sending module includes: a pairing unit, used to pair the user terminal according to the mapping relationship of the user access rights; a verification unit, used to verify the validity and legality of the user terminal; and a sending unit, used to send the private key in the key pair to the user terminal when the verification is passed, so that the user terminal uses the private key to decrypt the encrypted report.

[0017] Optionally, in a sixth implementation manner of the second aspect of the present invention, it also includes: an acquisition module, used to obtain a timestamp from a timestamp service platform based on the report query time decrypted by the user terminal using the private key, to obtain a user query timestamp; an identification association module, used to identify the user ID of the user terminal, associate the user ID with the user query timestamp, and obtain association information; an upload module, used to upload the association information to the blockchain.

[0018] The third aspect of the present invention provides a customer performance analysis device, which includes: a memory and at least one processor, wherein the memory stores instructions; at least one of the processors calls the instructions in the memory to enable the customer performance analysis device to perform each step of the customer performance analysis method described above.

[0019] A fourth aspect of the present invention provides a computer-readable storage medium having instructions stored thereon, and when the instructions are executed by a processor, the various steps of any of the above-mentioned customer performance analysis methods are implemented.

[0020] In the technical solution of the present invention, voice data of customers are collected from different channels, the voice data is cleaned to ensure the comprehensiveness and accuracy of the data, the cleaned data is classified, key performance indicators are calculated based on the classified data, the key performance indicators are analyzed, and graphic reports are generated based on the analysis results and the classified data. Data viewing in different dimensions is supported, which facilitates managers to quickly obtain customer performance information, provides customized access rights for users of different levels, and makes information management clearer. The public key in a preset key pair is used to encrypt the graphic report, and the private key in the key pair is sent to the user end with access rights based on the user's access rights, so that the user end uses the private key to decrypt the encrypted report, thereby reducing the risk of information leakage and improving information security. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] Figure 1 A first flow chart of a method for analyzing customer contract performance provided by an embodiment of the present invention;

[0022] Figure 2 A second flow chart of the method for analyzing customer contract performance provided by an embodiment of the present invention;

[0023] Figure 3 A third flow chart of the customer performance analysis method provided by an embodiment of the present invention;

[0024] Figure 4 A fourth flow chart of the customer performance analysis method provided by an embodiment of the present invention;

[0025] Figure 5 A schematic diagram of the structure of a device for analyzing customer contract performance provided by an embodiment of the present invention;

[0026] Figure 6 Another structural schematic diagram of a customer performance analysis device provided by an embodiment of the present invention;

[0027] Figure 7 A schematic diagram of the structure of a customer fulfillment analysis device provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0028] The present invention provides a customer performance analysis method, device, equipment and storage medium, which ensures the comprehensiveness and accuracy of data, provides customized access rights for users of different levels, makes information management clearer, reduces the risk of information leakage, improves information security, supports data viewing in different dimensions, and facilitates managers to quickly obtain customer performance information.

[0029] The terms "first", "second", "third", "fourth", etc. (if any) in the specification 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 data used in this way can be interchanged where appropriate, so that the embodiments described herein can be implemented in an order other than that illustrated or described herein. In addition, the terms "including" or "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0030] For ease of understanding, the specific process of the embodiment of the present invention is described below. Figure 1 An embodiment of the method for analyzing customer contract performance in an embodiment of the present invention includes:

[0031] 101. Collect customer voice data from different channels, including telephone contact records and feedback information after door-to-door delivery, and clean the voice data to obtain cleaned data;

[0032] In this embodiment, multiple channels for collecting sound data are determined, such as telephone contact records and feedback information after home delivery. Telephone contact records are conversations between customers and support personnel collected through customer service hotlines, automatic voice systems, etc. Feedback information after home delivery is to obtain customer satisfaction and suggestions through online voice communication. Speech-to-text technology is used to remove irrelevant background noise and non-customer feedback content from telephone records, retain valuable information, filter out unnecessary pauses, repeated sentences or invalid answers, convert the call content into an analyzable text format for subsequent processing, remove redundant information, ensure the accuracy and validity of the analyzed data, process incomplete, irrelevant or noisy data, improve data quality, check and delete duplicate records, ensure that each feedback information is unique, identify and correct entry errors, such as spelling errors, inconsistent formats, etc., and manually or automatically correct recognition errors in the speech-to-text process.

[0033] 102. Classify the cleaned data to obtain classified data, and calculate key performance indicators based on the classified data. The key performance indicators include telephone connection rate and door-to-door rate;

[0034] In this embodiment, classification standards are formulated according to business needs and analysis objectives. For example, customer feedback can be classified according to content, service type, satisfaction level, etc. to generate a classification data set, which includes category labels and related information of each customer feedback, such as call time, service type, satisfaction score, etc. Key performance indicators (KPIs) are calculated based on the classification data. The calculation formula for the telephone contact rate is the number of telephone contact records divided by the total number of customers, and the calculation formula for the door-to-door rate is the number of orders successfully delivered to the door divided by the total number of orders.

[0035] 103. Analyze key performance indicators, obtain analysis results, and generate graphic reports based on the analysis results and classified data;

[0036] In this embodiment, the key performance indicators are analyzed in layers according to different dimensions (such as service type and customer satisfaction level), the impact of different service types and customer satisfaction on the key performance indicators is observed, potential problems and improvement opportunities are identified, the key performance indicators of each dimension are compared, and areas of excellent performance and areas for improvement are found. The main findings are summarized and quantified. For example, the telephone call rate of telephone service is significantly higher than that of door-to-door service, indicating that telephone contact is more effective. The door-to-door rate of high-satisfaction customers is significantly higher than that of medium-satisfaction customers, indicating that customer experience is closely related to service quality. The report structure is designed, including a cover part, a directory part, an introduction part, a key performance indicator analysis result part, a chart display part, and a conclusion and suggestion part. Data visualization tools (such as Excel, Tableau, Power BI, etc.) are used to generate charts. For example, a bar chart shows the telephone call rate and door-to-door rate of different service types, a line chart shows the trend of telephone call rate and door-to-door rate over time, and a pie chart shows the distribution of customer satisfaction and its corresponding door-to-door rate. The calculation results, charts and related data are integrated into the report, and a text description of each part is written to clearly explain the meaning and inference behind the data.

[0037] 104. Customize and configure different levels of user access rights, and use the public key in the preset key pair to encrypt the graphic report to obtain the encrypted report;

[0038] In this embodiment, different user roles are defined according to the organizational structure and business needs. The scope of authority of each role should be clear to ensure information security and data privacy. Corresponding access rights are configured for each user role. For example, administrators can access all data and functions, including creating, editing and deleting reports. Data analysts can access and edit specific data sets, generate and view reports. Ordinary users can only view generated reports and have no editing rights. Authentication mechanisms (such as user name and password, two-factor authentication, etc.) are used to ensure that only authorized users can access the system. A role authority management module is configured to ensure that corresponding access rights are assigned by role. A pair of keys is generated using a cryptographic algorithm (such as RSA). After the generated graphic report is completed, the graphic report is converted into an encryptable format (such as PDF, TXT), the report content is encrypted using the public key, and an encrypted report file is generated. The encrypted report is stored in a secure data storage system to ensure that only users with private keys can decrypt it.

[0039] 105. Sending the private key in the key pair to the user end with the access permission based on the user access permission, so that the user end can decrypt the encrypted report using the private key;

[0040] In this embodiment, it is ensured that only audited users can obtain private keys, private key distribution rules are defined, and encrypted communication protocols (such as TLS / SSL) are used to protect the security of private keys during transmission to prevent man-in-the-middle attacks. Before transmission, the private key is encrypted using a symmetric encryption algorithm (such as AES) and then sent to the user through the above-mentioned secure communication channel. When a user requests a private key, multi-factor authentication (such as a mobile phone verification code, hardware token, etc.) is required to verify the user's identity to ensure that it is an authorized user requesting the private key. After receiving the encrypted private key, the user needs to use the corresponding decryption key (for example, a password known only to the user) to decrypt the private key. The scope of use and time limit of the private key are clearly defined to avoid abuse or long-term exposure of the private key.

[0041] In an embodiment of the present invention, voice data of customers is collected from different channels, the voice data is cleaned to ensure the comprehensiveness and accuracy of the data, the cleaned data is classified, key performance indicators are calculated based on the classified data, the key performance indicators are analyzed, and graphic reports are generated based on the analysis results and the classified data. Data viewing in different dimensions is supported, which facilitates management personnel to quickly obtain customer performance information, provides customized access rights for users of different levels, and makes information management clearer. The public key in a preset key pair is used to encrypt the graphic report, and the private key in the key pair is sent to the user end with access rights based on the user's access rights, so that the user end uses the private key to decrypt the encrypted report, thereby reducing the risk of information leakage and improving information security.

[0042] See also Figure 2 The second embodiment of the method for analyzing customer contract performance in the embodiment of the present invention includes:

[0043] 201. Obtain the customer's call record information in real time and create a listener;

[0044] In this embodiment, the call record information of the customer is obtained in real time, and a listener program is written to create a listener.

[0045] 202. Using a monitor to monitor the voice information fed back by the customer after the delivery, when the monitor monitors the voice information, the current voice information is obtained;

[0046] In this embodiment, the permissions of the input device are verified to ensure that the application can access the microphone, and the listener is started to monitor the audio input. The listener is used to monitor and capture the voice information fed back by the customer after the delivery. The logic is implemented in the callback function to trigger the corresponding operation when the audio signal is detected. In the callback function, audio processing technology (such as energy threshold) is used to determine when there is voice input to ensure that the voice information and background noise can be distinguished to reduce misjudgment. Once a valid audio signal is detected, the current voice data stream is captured, and the captured audio data is saved to a buffer for further processing, and the acquired audio data is converted into a format suitable for subsequent processing.

[0047] 203. Use voice recognition technology to convert the sound content in the call record information and the voice information into a text format to obtain sound data, and use a data deduplication algorithm to remove duplicate data from the sound data to obtain deduplicated data;

[0048] In this embodiment, an audio file is extracted from the call record, ensuring that the audio file format (such as WAV, MP3, etc.) is compatible with the speech recognition tool, the audio is preprocessed, such as adjusting the volume and removing noise to improve the recognition accuracy, the audio data is input into the selected speech recognition tool or API, the recognition parameters (such as language options, model selection, etc.) are set, the speech-to-text process is started, the text results returned by the speech recognition are received, and metadata such as the timestamp and speaker are recorded, the obtained text data is preliminarily sorted, meaningless marks or noise (such as filler words "hmm", "ah", etc.) are deleted, and the text format is ensured to be standardized, the sorted text data is input into the deduplication algorithm, and the comparison and deduplication operation is started. According to the set threshold, the repeated text content is identified and marked, the unique text data after deduplication is extracted, and the relevant metadata is recorded.

[0049] 204. Correct the erroneous data in the deduplicated data using a regular expression to obtain corrected data, and supplement the missing values ​​of the corrected data using an interpolation method to obtain cleaned data;

[0050] In this embodiment, the types of errors that may occur in the deduplicated data are identified, such as inconsistent formats, spelling errors, and extra spaces or special characters. According to the characteristics of the erroneous data, a suitable regular expression is written, and the regular expression is used to match and replace the data that does not conform to the standard format. The regular expression is used to remove unnecessary characters, and the regular expression is applied to the deduplicated data for batch replacement and correction. In the corrected data, the location of the missing values ​​is first identified, and the appropriate interpolation method is selected according to the nature of the data. The interpolation function in the programming tool (such as the Pandas library) is used to fill the missing values ​​to obtain the cleaned data.

[0051] 205. Classify the cleaned data to obtain classified data, where the classified data includes telephone consultation category data, telephone complaint category data, telephone suggestion category data, satisfactory feedback category data, unsatisfactory feedback category data, and neutral feedback category data;

[0052] In this embodiment, classification categories are defined, and preliminary classification is performed based on keywords in the cleaned data text content (such as "consultation", "complaint", "suggestion", "satisfaction", "dissatisfaction", etc.), and natural language processing technology is used to train classification models (such as naive Bayes, support vector machines, etc.) to automatically classify data to obtain classified data. The classified data includes telephone consultation category data, telephone complaint category data, telephone suggestion category data, satisfactory feedback category data, dissatisfied feedback category data, and neutral feedback category data.

[0053] 206. Count the total number of telephone consultation category data, telephone complaint category data and telephone suggestion category data in the classified data to obtain telephone contact record quantity information;

[0054] In this embodiment, data belonging to the categories of "telephone consultation", "telephone complaint" and "telephone suggestion" are extracted from the data set, the number of records in each category is counted, and the numbers of the three categories are added together to obtain the total number of telephone contact records.

[0055] 207. Count the total number of satisfactory feedback category data, unsatisfactory feedback category data, and neutral feedback category data in the classified data to obtain the number of successful home delivery orders;

[0056] In this embodiment, order records of successful home delivery are filtered out from the data set, and data of satisfied, dissatisfied, and neutral feedback are extracted from the orders that are successfully delivered to the door. The number of each category is counted, and the number of the three types of feedback is added together to obtain the total number of feedback for the orders that are successfully delivered to the door.

[0057] 208. Obtain the total number of customers and the total number of orders;

[0058] In this embodiment, it is confirmed that the data set contains necessary fields, such as customer ID, order ID, etc., for subsequent statistics. The total number of customers is obtained by calculating the number of unique customer IDs, and the total number of orders is obtained by calculating the number of unique order IDs, and the information of the total number of customers and the total number of orders is output.

[0059] 209. Calculate the telephone contact rate based on the number of telephone contact records and the total number of customers, and calculate the door-to-door rate based on the number of successful door-to-door delivery orders and the total number of orders;

[0060] In this embodiment, the telephone contact rate is calculated based on the number of telephone contact records and the total number of customers. The calculation formula of the telephone contact rate is the number of telephone contact records divided by the total number of customers. The door-to-door rate is calculated based on the number of successful door-to-door delivery orders and the total number of orders. The calculation formula of the door-to-door rate is the number of successful door-to-door delivery orders divided by the total number of orders.

[0061] In the embodiment of the present invention, by acquiring call records and customer feedback in real time, the system can respond quickly to customer needs and provide timely service improvements. By using voice recognition and deduplication algorithms, voice information is converted into text, making data easier to process and analyze, and improving the accuracy of information. The data is corrected and supplemented by regular expressions and interpolation methods to ensure the integrity and reliability of the data, thereby laying a good foundation for subsequent analysis. The cleaned data is carefully classified to fully understand all aspects of customer feedback, thereby providing support for corporate decision-making. By counting and calculating key indicators such as telephone connection rate and door-to-door rate, it helps companies evaluate service quality and customer satisfaction, and then optimize operational strategies. The real-time monitoring and feedback mechanism enables companies to quickly adjust services and improve customer satisfaction and loyalty. Through systematic data analysis, companies can make more accurate market and operational decisions based on actual data to enhance their competitiveness.

[0062] See also Figure 3 A third embodiment of the method for analyzing customer contract performance in the embodiment of the present invention includes:

[0063] 301. Analyze the key performance indicators and obtain the analysis results;

[0064] In this embodiment, the key performance indicators of different time periods, such as monthly, quarterly and annual, are compared to observe the trend changes, and then the telephone contact rate and door-to-door rate are analyzed. For example, a 20% telephone contact rate indicates that only one-fifth of the customers are contacted, which may mean that the calling strategy needs to be improved or the quality of the contact method needs to be improved. By comparing historical data, if the telephone contact rate decreases, the reasons must be further analyzed, such as whether it is due to inaccurate customer information or improper call time selection. The 72% door-to-door rate shows that the delivery service is relatively efficient, but 28% of the orders are still not successfully delivered. The reasons for non-delivery (such as customer absence, wrong address, etc.) need to be investigated, and the cases of failed delivery are analyzed to find common problems and develop solutions.

[0065] 302. Use data visualization tools to generate charts from categorical data, including bar charts, line charts, and pie charts;

[0066] In this embodiment, use the data visualization tool to select the "bar chart" type, set "month" as the X-axis, set "telephone contact rate" and "door-to-door visit rate" as the series of the Y-axis, select different colors for each rate to distinguish them, use the data visualization tool to select the "line chart" type, set "month" as the X-axis, set "telephone contact rate" and "door-to-door visit rate" as the Y-axis series, draw two lines, representing the telephone contact rate and door-to-door visit rate respectively, add data points to enhance readability, select a specific month (such as April) as the benchmark, calculate the ratio, and set it as the parts of the pie chart, and integrate all charts in one report.

[0067] 303. Calling a preset report template, filling the analysis result into the report template, and obtaining a text report, which includes a data summary table, a detailed data table, and an analysis report;

[0068] In this embodiment, a preset report template is called to summarize the key indicators of the entire analysis cycle, list detailed data for each month, including the number of customers successfully and unsuccessfully contacted, analyze the data, point out trends, outliers and possible causes, provide suggestions and improvement measures, and fill the analysis results into the report template to obtain a text report, which includes a data summary table, a detailed data table and an analysis report.

[0069] 304. Combine the chart and text report to obtain a graphic report;

[0070] In this embodiment, the chart and text report are combined into one PDF file, or a Word document containing the chart and text is created to obtain a graphic and text report.

[0071] 305. Obtain a preset user authority setting table;

[0072] In this embodiment, the usage scenarios of the user permission setting table are determined, such as system management, data access or function control, and all possible user roles in the system (such as administrators, ordinary users, visitors, etc.) and the permissions required for each role are listed. The permissions are divided into different categories, and a permission setting table is created using a spreadsheet tool, and the collected information is filled in the corresponding positions.

[0073] 306. Configure different levels of user access rights according to the user authority setting table;

[0074] In this embodiment, each user role and its corresponding permissions, including read, write, delete, and manage permissions, are confirmed, permissions are divided into different levels, a suitable access control model is selected according to needs, and user roles consistent with the permission setting table are created in the system. For example, "administrator", "ordinary user" and "visitor" roles are added to the user management system. According to the permission setting table, corresponding access rights are assigned to each role to ensure that the permission configuration of each role is accurate.

[0075] 307. Encrypt the graphic report using the public key in the preset key pair to obtain an encrypted report;

[0076] In this embodiment, a reliable encryption algorithm (such as RSA, ECC, etc.) is used to generate a key pair, ensuring that a public key and a private key have been generated, and a suitable encryption library (such as OpenSSL, CryptoJS, etc.) is used to read the graphic report to be encrypted, determine its format, convert the report data into a format suitable for encryption, such as a byte array, encrypt the report data using a preset public key, save the encrypted data as a new file, select a suitable format (such as an encrypted binary file), and obtain an encrypted report.

[0077] In an embodiment of the present invention, through the analysis of key performance indicators, the system can deeply understand business performance and help identify improvement opportunities. The data visualization tool converts complex data into easy-to-understand charts, making information communication clearer and facilitating quick decision-making. The analysis results are filled into preset templates to form standardized text reports, ensuring the consistency and professionalism of the reports and facilitating effective communication. The merging of graphic and text reports provides a comprehensive perspective to help users understand data from multiple dimensions and enhance the value of reports. Different levels of access rights are configured according to user authority settings to ensure data security and ensure that relevant personnel obtain the required information. Public key encryption technology is used to protect sensitive data, enhance the security of reports, prevent information leakage, and ensure compliance. Comprehensive reporting and security guarantees enable management to make more informed decisions in a transparent and secure environment and improve overall operational efficiency.

[0078] See also Figure 4The fourth embodiment of the method for analyzing customer contract performance in the embodiment of the present invention includes:

[0079] 401. Pairing the user terminal according to the mapping relationship of the user access rights;

[0080] In this embodiment, user roles and their corresponding permissions are identified to ensure that the resources and operations that each role can access are clear. Basic information of all users, including user names, roles, and other relevant attributes, is extracted from the user management system to ensure that a user authentication mechanism is in place to prevent unauthorized user access. Users are matched with corresponding permissions based on their roles, and a mapping table or data structure is created to associate user IDs with their corresponding permission lists. Access verification logic is implemented in the system to ensure that users check their permissions when accessing resources.

[0081] 402, verify the validity and legitimacy of the user terminal;

[0082] In this embodiment, the user is required to provide two or more identity authentication factors, such as a password plus a mobile phone verification code, to enhance security and prevent unauthorized access. When a user requests access to a resource, the system needs to check the permissions corresponding to his or her role.

[0083] 403. When the verification is passed, the private key in the key pair is sent to the user end, so that the user end uses the private key to decrypt the encrypted report;

[0084] In this embodiment, when the verification is passed, a strong encryption protocol (such as TLS) is used to send the private key in the key pair to the user end, ensuring that only authenticated users can request and receive the private key, preventing unauthorized users from obtaining the private key. The user end uses the private key to decrypt the encrypted report.

[0085] 404. Obtain a timestamp from the timestamp service platform based on the report query time decrypted by the user using the private key to obtain a user query timestamp;

[0086] In this embodiment, after decrypting the report, the user initiates a request to the timestamp service platform, carries the necessary query information, and uses a secure transmission protocol (such as HTTPS) to send the query request to the timestamp service platform to protect the security of the information during transmission. After receiving the request, the timestamp service platform first verifies the legitimacy of the request, including the user's identity and the integrity of the request. After confirming that the request is valid, the timestamp service platform generates a timestamp of the current system time, associates it with the data requested by the user, and returns the generated timestamp to the user end in a secure format (for example, digital signature) to obtain the user query timestamp.

[0087] 405. Identify the user ID of the user terminal, associate the user ID with the user query timestamp, and obtain associated information;

[0088] In this embodiment, when a user initiates a report query request, the system should first verify the user's identity. Once the user's identity is verified, the system will obtain the user's unique identifier (user ID) from the database or identity management service, associate the user ID with the user query timestamp, and obtain associated information.

[0089] 406. Upload the associated information to the blockchain;

[0090] In this embodiment, the associated information is formatted in a data structure suitable for the blockchain, and a suitable blockchain platform (such as Ethereum, Hyperledger Fabric, EOS, etc.) is selected according to project requirements. A smart contract is developed on the selected platform, and its functions are defined to receive and store the associated information. The contract is fully tested to avoid security vulnerabilities and logical errors, and to ensure the correctness and security of data stored on the chain. The associated information is uploaded to the blockchain by sending a transaction request using a blockchain client or API. Once the transaction is sent, it is necessary to wait for the blockchain network to confirm the transaction. After the transaction is confirmed, the associated information just uploaded can be queried through a blockchain browser or a corresponding API to verify whether it is stored correctly.

[0091] In the embodiment of the present invention, by mapping and validating the user access rights, it is ensured that only authorized users can obtain sensitive information, thereby reducing the risk of data leakage, and the private key in the key pair is sent directly to the user end to ensure that the user can safely decrypt the report and maintain the integrity and confidentiality of the information. By obtaining the query timestamp, a time basis is provided for the user's operation, which is helpful for subsequent auditing and data tracking, and improves transparency. The user ID is associated with the query timestamp to form a detailed operation record, which is helpful for analyzing user behavior and improving the controllability of the system. The associated information is uploaded to the blockchain to ensure that the data cannot be tampered with and is traceable, enhance the trust mechanism, and improve the integrity and reliability of the data.

[0092] The above describes the method for analyzing customer contract performance in an embodiment of the present invention. The following describes the device for analyzing customer contract performance in an embodiment of the present invention. Figure 5 In one embodiment of the present invention, a device for analyzing customer contract performance includes:

[0093] The collection and cleaning module 501 is used to collect voice data of customers from different channels, the voice data including telephone contact records and feedback information after door-to-door delivery, and clean the voice data to obtain cleaned data;

[0094] The classification calculation module 502 is used to classify the cleaned data to obtain classified data, and calculate key performance indicators according to the classified data. The key performance indicators include telephone connection rate and door-to-door rate;

[0095] The analysis and generation module 503 is used to analyze the key performance indicators, obtain analysis results, and generate graphic reports based on the analysis results and classification data;

[0096] Configuration encryption module 504, used to customize and configure different levels of user access rights, and encrypt the graphic report using the public key in the preset key pair to obtain an encrypted report;

[0097] The sending module 505 is used to send the private key in the key pair to the user terminal with the access permission based on the user access permission, so that the user terminal uses the private key to decrypt the encrypted report.

[0098] In this embodiment, voice data of customers is collected from different channels, the voice data is cleaned to ensure the comprehensiveness and accuracy of the data, the cleaned data is classified, key performance indicators are calculated based on the classified data, the key performance indicators are analyzed, and graphic reports are generated based on the analysis results and the classified data. Data viewing in different dimensions is supported, which facilitates managers to quickly obtain customer performance information, and customized access rights are provided for users of different levels. Information management is clearer, and graphic reports are encrypted using the public key in a preset key pair. Based on the user's access rights, the private key in the key pair is sent to the user end with access rights, so that the user end uses the private key to decrypt the encrypted report, thereby reducing the risk of information leakage and improving information security.

[0099] See also Figure 6 Another embodiment of the customer performance analysis device in the embodiment of the present invention includes:

[0100] The collection and cleaning module 501 is used to collect voice data of customers from different channels, the voice data including telephone contact records and feedback information after door-to-door delivery, and clean the voice data to obtain cleaned data;

[0101] A classification calculation module 502 is used to classify the cleaned data to obtain classified data, and calculate key performance indicators based on the classified data. The key performance indicators include telephone connection rate and door-to-door rate;

[0102] The analysis and generation module 503 is used to analyze the key performance indicators, obtain analysis results, and generate graphic reports based on the analysis results and classification data;

[0103] Configuration encryption module 504, used to customize and configure different levels of user access rights, and encrypt the graphic report using the public key in the preset key pair to obtain an encrypted report;

[0104] A sending module 505, configured to send the private key in the key pair to a user terminal with access rights based on the user access rights, so that the user terminal uses the private key to decrypt the encrypted report;

[0105] In this embodiment, the collection and cleaning module 501 includes: an acquisition creation unit 5011, which is used to acquire the customer's call record information in real time and create a listener; a monitoring acquisition unit 5012, which is used to use the listener to monitor the voice information fed back by the customer after home delivery, and when the listener monitors the voice information, the current voice information is acquired; a conversion and removal unit 5013, which is used to use voice recognition technology to convert the sound content in the call record information and the voice information into a text format to obtain sound data, and use a data deduplication algorithm to remove duplicate data of the sound data to obtain deduplicated data; a correction and supplement unit 5014, which is used to use a regular expression to correct the erroneous data in the deduplicated data to obtain corrected data, and supplement the missing values ​​of the corrected data by interpolation to obtain cleaned data.

[0106] In this embodiment, the classification calculation module 502 includes: a classification unit 5021, which is used to classify the cleaned data to obtain classified data, and the classified data includes telephone consultation category data, telephone complaint category data, telephone suggestion category data, satisfactory feedback category data, dissatisfied feedback category data and neutral feedback category data; a first statistical unit 5022, which is used to count the total number of telephone consultation category data, telephone complaint category data and telephone suggestion category data in the classified data to obtain telephone contact record quantity information; a second statistical unit 5023, which is used to count the total number of satisfactory feedback category data, dissatisfied feedback category data and neutral feedback category data in the classified data to obtain successful home delivery order quantity information; a first acquisition unit 5024, which is used to obtain total customer quantity information and total order quantity information; a calculation unit 5025, which is used to calculate the telephone connection rate based on the telephone contact record quantity information and the total customer quantity information, and calculate the door-to-door rate based on the successful home delivery order quantity information and the total order quantity information.

[0107] In this embodiment, the analysis generation module 503 includes: an analysis unit 5031, which is used to analyze the key performance indicators and obtain analysis results; a generation unit 5032, which is used to use data visualization tools to generate classified data into charts, and the charts include bar charts, line charts and pie charts; a calling and filling unit 5033, which is used to call a preset report template, fill the analysis results into the report template, and obtain a text report, and the text report includes a data summary table, a detailed data table and an analysis report; a merging unit 5034, which is used to merge the chart and the text report to obtain a graphic report.

[0108] In this embodiment, the configuration encryption module 504 includes: a second acquisition unit 5041, used to obtain a preset user authority setting table; a configuration unit 5042, used to configure different levels of user access rights according to the user authority setting table; an encryption unit 5043, used to encrypt the graphic report using the public key in the preset key pair to obtain an encrypted report.

[0109] In this embodiment, the sending module 505 includes: a pairing unit 5051, used to pair the user terminal according to the mapping relationship of the user access rights; a verification unit 5052, used to verify the validity and legality of the user terminal; a sending unit 5053, used to send the private key in the key pair to the user terminal when the verification is passed, so that the user terminal uses the private key to decrypt the encrypted report.

[0110] In this embodiment, it also includes: an acquisition module 506, which is used to obtain a timestamp from a timestamp service platform based on the report query time decrypted by the user terminal using a private key, and obtain a user query timestamp; an identification and association module 507, which is used to identify the user ID of the user terminal, associate the user ID with the user query timestamp, and obtain associated information; an upload module 508, which is used to upload the associated information to the blockchain.

[0111] above Figure 5 and Figure 6 The customer fulfillment analysis device in the embodiment of the present invention is described in detail from the perspective of modular functional entities. The customer fulfillment analysis device in the embodiment of the present invention is described in detail from the perspective of hardware processing.

[0112] Figure 7 6 is a schematic diagram of the structure of a customer performance analysis device provided by an embodiment of the present invention. The customer performance analysis device 600 may have relatively large differences due to different configurations or performances, and may include one or more processors (central processing units, CPU) 610 (for example, one or more processors) and a memory 620, and one or more storage media 630 (for example, one or more mass storage devices) storing application programs 633 or data 632. Among them, the memory 620 and the storage medium 630 can be short-term storage or permanent storage. The program stored in the storage medium 630 may include one or more modules (not shown in the figure), and each module may include a series of instruction operations in the customer performance analysis device 600. Furthermore, the processor 610 may be configured to communicate with the storage medium 630, and execute a series of instruction operations in the storage medium 630 on the customer performance analysis device 600 to implement the steps of the customer performance analysis method provided by the above-mentioned method embodiments.

[0113] The customer performance analysis device 600 may also include one or more power supplies 640, one or more wired or wireless network interfaces 650, one or more input and output interfaces 660, and / or one or more operating systems 631, such as Windows Server, Mac OS X, Unix, Linux, FreeBSD, etc. It will be appreciated by those skilled in the art that Figure 7 The structure of the customer performance analysis device shown does not constitute a limitation on the customer performance analysis device, and may include more or fewer components than shown in the figure, or a combination of certain components, or a different arrangement of components.

[0114] The present invention also provides a computer-readable storage medium, which may be a non-volatile computer-readable storage medium or a volatile computer-readable storage medium. Instructions are stored in the computer-readable storage medium, and when the instructions are executed on a computer, the computer executes the steps of the customer performance analysis method.

[0115] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working process of the above-described system, device, or unit can refer to the corresponding process in the aforementioned method embodiment and will not be repeated here.

[0116] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product. The computer software product is stored in a storage medium, including a number of instructions to enable a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM), random access memory (RAM), disk or optical disk and other media that can store program codes.

[0117] Finally, it should be noted that the above description is only a preferred example of the present invention and is not intended to limit the present invention. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art can still modify the technical solutions described in the aforementioned embodiments or replace some of the technical features therein by equivalents. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A method for analyzing customer performance, characterized in that: include: Collecting customer voice data from different channels, the voice data including telephone contact records and feedback information after home delivery, and cleaning the voice data to obtain cleaned data; Classifying the cleaned data to obtain classified data, and calculating key performance indicators according to the classified data, wherein the key performance indicators include a telephone connection rate and a door-to-door visit rate; Analyze the key performance indicators to obtain analysis results, and generate graphic reports based on the analysis results and the classification data; Customize different levels of user access rights and use the public key in the preset key pair to encrypt the graphic report to obtain the encrypted report; The private key in the key pair is sent to a user terminal having access rights based on the user access rights, so that the user terminal uses the private key to decrypt the encrypted report.

2. The method for analyzing customer performance according to claim 1, characterized in that: The voice data of customers are collected from different channels, and the voice data includes telephone contact records and feedback information after door-to-door delivery. The voice data is cleaned to obtain cleaned data, including: Obtain customer call record information in real time and create a listener; The monitor is used to monitor the voice information fed back by the customer after the goods are delivered to the door, and when the monitor monitors the voice information, the current voice information is obtained; Using speech recognition technology to convert the sound content in the call record information and the voice information into text format to obtain sound data, and using a data deduplication algorithm to remove duplicate data from the sound data to obtain deduplicated data; Regular expressions are used to correct erroneous data in the deduplicated data to obtain corrected data, and missing values ​​of the corrected data are supplemented by interpolation to obtain cleaned data.

3. The method for analyzing customer performance according to claim 1, characterized in that: The cleaning data is classified to obtain classified data, and key performance indicators are calculated according to the classified data. The key performance indicators include telephone connection rate and door-to-door rate, including: Classifying the cleaned data to obtain classified data, wherein the classified data includes telephone consultation category data, telephone complaint category data, telephone suggestion category data, satisfactory feedback category data, unsatisfactory feedback category data, and neutral feedback category data; Counting the total number of the telephone consultation category data, the telephone complaint category data and the telephone suggestion category data in the classified data to obtain telephone contact record quantity information; Counting the total number of the satisfactory feedback category data, the unsatisfactory feedback category data and the neutral feedback category data in the classified data to obtain the number of successful home delivery orders; Get total customer quantity information and total order quantity information; The telephone contact rate is calculated based on the telephone contact record quantity information and the total customer quantity information, and the door-to-door rate is calculated based on the successful door-to-door delivery order quantity information and the total order quantity information.

4. The method for analyzing customer contract performance according to claim 1, characterized in that: The key performance indicators are analyzed to obtain analysis results, and graphic reports are generated according to the analysis results and the classification data, including: Analyze the key performance indicators to obtain analysis results; Using a data visualization tool to generate the categorized data into charts, the charts including bar charts, line charts and pie charts; Calling a preset report template, filling the analysis result into the report template, and obtaining a text report, wherein the text report includes a data summary table, a detailed data table, and an analysis report; The chart and the text report are combined to obtain a graphic and text report.

5. The method for analyzing customer performance according to claim 1, characterized in that: The customized configuration of different levels of user access rights uses the public key in the preset key pair to encrypt the graphic report to obtain an encrypted report, including: Get the preset user permission setting table; Configure different levels of user access rights according to the user authority setting table; Use the public key in the preset key pair to encrypt the graphic report to obtain an encrypted report.

6. The method for analyzing customer performance according to claim 1, characterized in that: The step of sending the private key in the key pair to a user terminal with access rights based on the user access rights, so that the user terminal uses the private key to decrypt the encrypted report, includes: Pairing the user terminals according to the mapping relationship of the user access rights; Verify the validity and legitimacy of the user terminal; When the verification is successful, the private key in the key pair is sent to the user terminal, so that the user terminal uses the private key to decrypt the encrypted report.

7. The method for analyzing customer contract performance according to claim 1, characterized in that: After sending the private key in the key pair to a user terminal with access rights based on the user access rights so that the user terminal uses the private key to decrypt the encrypted report, the method further includes: Obtaining a timestamp from a timestamp service platform based on the report query time decrypted by the user end using the private key to obtain a user query timestamp; Identify the user ID of the user terminal, associate the user ID with the user query timestamp, and obtain association information; The associated information is uploaded to the blockchain.

8. A customer performance analysis device, characterized in that: include: A collection and cleaning module is used to collect voice data of customers from different channels, wherein the voice data includes telephone contact records and feedback information after door-to-door delivery, and clean the voice data to obtain cleaned data; A classification calculation module, used to classify the cleaned data to obtain classified data, and calculate key performance indicators according to the classified data, wherein the key performance indicators include a telephone connection rate and a door-to-door rate; An analysis and generation module, used to analyze the key performance indicators, obtain analysis results, and generate graphic reports based on the analysis results and the classification data; Configure the encryption module to customize different levels of user access rights, and use the public key in the preset key pair to encrypt the graphic report to obtain an encrypted report; The sending module is used to send the private key in the key pair to a user terminal with access rights based on the user access rights, so that the user terminal uses the private key to decrypt the encrypted report.

9. A customer performance analysis device, characterized in that: The customer performance analysis device comprises: a memory and at least one processor, wherein instructions are stored in the memory; At least one of the processors calls the instructions in the memory to enable the customer fulfillment analysis device to perform each step of the customer fulfillment analysis method as described in any one of claims 1-7.

10. A computer-readable storage medium having instructions stored thereon, characterized in that: When the instructions are executed by the processor, the various steps of the customer performance analysis method as described in any one of claims 1-7 are implemented.

Images