Customer information intelligent input method and device, computer equipment and storage medium

Abstract

The embodiment of the invention belongs to the field of artificial intelligence, and relates to a customer information intelligent input method, which comprises the following steps of: performing OCR (Optical Character Recognition) picture recognition on acquired identity card and driving license pictures; judging whether the data recognized by the OCR picture is accurate or not; if the OCR picture recognition data are not accurate, ASR voice recognition is prompted to be carried out; calculating the distance between the OCR picture recognition data and the to-be-classified sample and the distance between the ASR voice recognition data and the to-be-classified sample; classifying the distance between the OCR picture recognition data and the to-be-classified sample and the distance between the ASR voice recognition data and the to-be-classified sample by adopting a KNN clustering algorithm; and optimizing the classification result by adopting a particle swarm algorithm, and inputting customer information by using the OCR picture recognition data and the ASR voice recognition data determined by the optimal classification result. The invention further provides an intelligent client information input device, computer equipment and a storage medium. According to the method, the information of the text can be recognized more accurately, and the working efficiency is greatly improved.

Description

Technical Field

[0001] The present application relates to the field of artificial intelligence technology, and in particular to a method, device, computer equipment and storage medium for intelligently entering customer information. Background Art

[0002] With the rise of Internet technology, the continuous development of big data technology and AI information technology, traditional auto insurance or non-auto insurance policy entry is done manually to enter customer identity information, phone information, vehicle information, including license plate number, frame number, and other information. It takes a lot of time to enter each order, and it is easy to make mistakes in entering information. The efficiency is extremely low, affecting the work efficiency of the seats and the customer experience. Therefore, it is particularly important to design an intelligent customer information entry method. Summary of the invention

[0003] The purpose of the embodiments of the present application is to propose a method, device, computer equipment and storage medium for intelligent entry of customer information, the main purpose of which is to achieve accurate recognition of text information and improve work efficiency.

[0004] In order to solve the above technical problems, the embodiment of the present application provides a method for intelligently entering customer information, which adopts the following technical solution:

[0005] A method for intelligently entering customer information comprises the following steps:

[0006] Obtain the customer's ID card and driver's license pictures, and perform OCR image recognition on the ID card and driver's license pictures;

[0007] Determine whether the OCR image recognition data is accurate;

[0008] If the OCR image recognition data is inaccurate, then a prompt is given to perform ASR speech recognition to obtain ASR speech recognition data;

[0009] Calculate the distance between the OCR image recognition data and the ASR speech recognition data and the sample to be classified;

[0010] Using the KNN clustering algorithm to classify the distances between the OCR image recognition data and the ASR speech recognition data and the samples to be classified;

[0011] The classification result is optimized by using a particle swarm algorithm to obtain an optimal classification result, and customer information is entered using the OCR image recognition data and the ASR voice recognition data determined by the optimal classification result.

[0012] Furthermore, the step of obtaining the customer's ID card and driver's license pictures and performing OCR image recognition on the ID card and driver's license pictures specifically includes:

[0013] Get pictures of the customer's ID card and driver's license;

[0014] Perform pre-processing operations such as grayscale, binarization, denoising, and tilt correction on the acquired customer ID card and driver's license images;

[0015] Segment the text in the customer ID card and driver's license images after preprocessing into individual characters or words;

[0016] Extract stroke, shape, and structural features from the segmented individual characters or words;

[0017] Machine learning or deep learning algorithms are used to classify and recognize the extracted strokes, shapes, and structural features, and convert individual characters or words into editable text.

[0018] Furthermore, the step of determining whether the OCR image recognition data is accurate specifically includes:

[0019] Retrieve the preset customer ID card image judgment standard and driver's license image judgment standard;

[0020] Compare the OCR image recognition data with the customer ID card image determination standard and the driver's license image determination standard;

[0021] If the comparison result is greater than a preset threshold, the OCR image recognition data is determined to be accurate and the OCR image recognition data is entered;

[0022] If the comparison result is less than or equal to the preset threshold, it is determined that the data of the OCR image recognition is inaccurate.

[0023] Furthermore, if the OCR image recognition data is inaccurate, the step of prompting ASR speech recognition to obtain the ASR speech recognition data specifically includes:

[0024] If the comparison result between the OCR image recognition data and the customer ID card image judgment standard and the driver's license image judgment standard is less than the preset threshold, an ASR voice recognition prompt is performed;

[0025] Prompt to enter voice message;

[0026] Pre-process the recorded speech signal to remove noise, reduce interference and digitize;

[0027] Extracting characteristic data of cepstral coefficients and Mel-frequency cepstral coefficients from the preprocessed speech signal;

[0028] The extracted feature data is classified and recognized using machine learning algorithms to convert speech into text.

[0029] Furthermore, the step of calculating the distance between the OCR picture recognition data and the ASR speech recognition data and the sample to be classified specifically includes:

[0030] The distances between the OCR image recognition data and the ASR speech recognition data and the n samples to be classified are calculated according to the following formula:

[0031]

[0032] In the formula, x i Represents the data of OCR image recognition, x j Represents the data of ASR speech recognition, x iu Indicates the distance between the OCR image recognition data and the sample to be classified, x ju Indicates the distance between the ASR speech recognition data and the sample to be classified.

[0033] Furthermore, the step of optimizing the classification result by using a particle swarm algorithm to obtain an optimal classification result, and entering customer information using the OCR image recognition data and ASR voice recognition data determined by the optimal classification result specifically includes:

[0034] Using a particle swarm algorithm to determine the optimal classification result of the distance between the OCR image recognition data and the sample to be classified, and to determine the optimal classification result of the distance between the ASR speech recognition data and the sample to be classified;

[0035] According to the optimal classification result of the distance data between the ASR speech recognition data and the samples to be classified and the optimal classification result of the distance data between the OCR image recognition data and the samples to be classified, it is obtained that the distance data between the ASR speech recognition data and the samples to be classified and the distance data between the OCR image recognition data and the samples to be classified are optimal as a whole.

[0036] The field texts in all the OCR image recognition data and ASR voice recognition data that have achieved the best overall are used as the determined OCR image recognition data and ASR voice recognition data for entering customer information.

[0037] Furthermore, the optimal classification result of the distance data between the ASR speech recognition data and the sample to be classified and the optimal classification result of the distance data between the OCR image recognition data and the sample to be classified are obtained according to the optimal classification result of the distance data between the ASR speech recognition data and the sample to be classified and the step of achieving the optimal distance between the ASR speech recognition data and the sample to be classified as a whole includes:

[0038] A dynamic threshold is set by the following formula;

[0039]

[0040] Represents the best solution generated in the current execution process, η j The meaning is the parameter of coefficient adjustment, Z j,k , k is a variable parameter in the range of [-1, 1];

[0041] Compare the optimal classification result of the distance data between the ASR speech recognition data and the sample to be classified and the optimal classification result of the distance data between the OCR picture recognition data and the sample to be classified with a standard threshold respectively;

[0042] If both exceed the standard threshold, it is considered that the distance data between the ASR speech recognition data and the sample to be classified and the distance data between the OCR image recognition data and the sample to be classified are optimal as a whole.

[0043] In order to solve the above technical problems, the embodiment of the present application also provides a customer information intelligent input device, which adopts the following technical solution:

[0044] A customer information intelligent input device, comprising:

[0045] An acquisition module is used to acquire pictures of a customer's ID card and driver's license, and perform OCR image recognition on the pictures of the ID card and driver's license;

[0046] A judgment module is used to judge whether the data of the OCR image recognition is accurate;

[0047] A prompt module, used for prompting ASR speech recognition to obtain ASR speech recognition data if the OCR image recognition data is inaccurate;

[0048] A calculation module, used to calculate the distance between the OCR image recognition data and the ASR speech recognition data and the sample to be classified;

[0049] A clustering module, used to classify the distances between the OCR image recognition data and the ASR speech recognition data and the samples to be classified by using a KNN clustering algorithm;

[0050] The optimization module is used to optimize the classification result by using a particle swarm algorithm to obtain an optimal classification result, and to input customer information using the OCR image recognition data and ASR voice recognition data determined by the optimal classification result.

[0051] In order to solve the above technical problems, the embodiment of the present application further provides a computer device, which adopts the following technical solution:

[0052] A computer device includes a memory and a processor, wherein the memory stores computer-readable instructions, and the processor implements the steps of the above-mentioned customer information intelligent entry method when executing the computer-readable instructions.

[0053] In order to solve the above technical problems, the embodiment of the present application further provides a computer-readable storage medium, which adopts the following technical solution:

[0054] A computer-readable storage medium stores computer-readable instructions, which, when executed by a processor, implement the steps of the method for intelligently entering customer information as described above.

[0055] Compared with the prior art, the embodiments of the present application mainly have the following beneficial effects: the present application collects the required useful information in real time through OCR image recognition and ASR voice recognition, performs automatic recognition, and automatically enters it into the system. This method can greatly reduce the time for entry, and if the data of OCR image recognition is inaccurate, it prompts to perform ASR voice recognition, double verification, and improves the recognition accuracy. Then, the KNN clustering algorithm is used to classify the distance between the OCR image recognition data and the ASR voice recognition data and the samples to be classified. Finally, the particle swarm algorithm is used to optimize the classification results to obtain the optimal classification results. The OCR image recognition data and the ASR voice recognition data determined by the optimal classification results are used to enter customer information, which can more accurately identify the text information and greatly improve work efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0056] In order to more clearly illustrate the scheme in the present application, a brief introduction is given below to the drawings required for use in the description of the embodiments of the present application. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0057] Figure 1 is an exemplary system architecture diagram to which the present application may be applied;

[0058] Figure 2 A flowchart of an embodiment of a method for intelligently entering customer information according to the present application;

[0059] Figure 3 yes Figure 2 A flowchart of a specific implementation of step S201;

[0060] Figure 4 yes Figure 2 A schematic diagram of a specific implementation of step S202;

[0061] Figure 5 yes Figure 2 A flowchart of a specific implementation of step S203;

[0062] Figure 6 yes Figure 2 A flowchart of a specific implementation of step S206;

[0063] Figure 7 It is a structural schematic diagram of an embodiment of a customer information intelligent entry device according to the present application;

[0064] Figure 8 It is a structural diagram of an embodiment of a computer device according to the present application. DETAILED DESCRIPTION

[0065] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by technicians in the technical field of the present application; the terms used in the specification of the application herein are only for the purpose of describing specific embodiments and are not intended to limit the present application; the terms "including" and "having" and any variations thereof in the specification and claims of the present application and the above-mentioned drawings are intended to cover non-exclusive inclusions. The terms "first", "second", etc. in the specification and claims of the present application or the above-mentioned drawings are used to distinguish different objects, not to describe a specific order.

[0066] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0067] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the accompanying drawings.

[0068] like Figure 1 As shown, the system architecture 100 may include terminal devices 101, 102, 103, a network 104 and a server 105. The network 104 is used to provide a medium for communication links between the terminal devices 101, 102, 103 and the server 105. The network 104 may include various connection types, such as wired, wireless communication links or optical fiber cables, etc.

[0069] Users can use terminal devices 101, 102, 103 to interact with server 105 through network 104 to receive or send messages, etc. Various communication client applications can be installed on terminal devices 101, 102, 103, such as web browser applications, shopping applications, search applications, instant messaging tools, email clients, social platform software, etc.

[0070] Terminal devices 101, 102, 103 can be various electronic devices with display screens and supporting web browsing, including but not limited to smart phones, tablet computers, e-book readers, MP3 players (Moving Picture Experts Group Audio Layer III), MP4 (Moving Picture Experts Group Audio Layer IV) players, laptop computers and desktop computers, etc.

[0071] The server 105 may be a server that provides various services, such as a background server that provides support for web pages displayed on the terminal devices 101 , 102 , and 103 .

[0072] It should be noted that the customer information intelligent entry method provided in the embodiment of the present application is generally executed by a server, and accordingly, the customer information intelligent entry device is generally set in a terminal device.

[0073] It should be understood that Figure 1 The number of terminal devices, networks and servers in the embodiment is only for illustration. Any number of terminal devices, networks and servers may be provided according to implementation requirements.

[0074] Continue to refer Figure 2 , shows a flow chart of an embodiment of a method for intelligently entering customer information according to the present application. The method for intelligently entering customer information comprises the following steps:

[0075] Step S201, obtaining the customer's ID card and driver's license pictures, and performing OCR image recognition on the ID card and driver's license pictures;

[0076] In this embodiment, the method for intelligently entering customer information is executed on an electronic device (eg Figure 1The server shown in the figure) can be connected by wired connection or wireless connection. It should be noted that the above wireless connection methods may include but are not limited to 3G / 4G / 5G connection, WiFi connection, Bluetooth connection, WiMA customer information intelligent entry connection, Zigbee connection, UWB (ultra wideband) connection, and other wireless connection methods currently known or to be developed in the future.

[0077] See also Figure 3 As shown, the steps of obtaining the customer's ID card and driver's license pictures and performing OCR image recognition on the ID card and driver's license pictures specifically include:

[0078] Step S2011, obtain the customer's ID card and driver's license pictures. The customer may send the ID card and driver's license pictures during the communication with the customer at the seat.

[0079] Step S2012, pre-processing operations such as grayscale, binarization, denoising, and tilt correction are performed on the obtained customer ID card and driver's license images.

[0080] Step S2013, segment the text in the customer's ID card and driver's license images after the preprocessing operation into single characters or words.

[0081] Step S2014, extracting strokes, shapes, and structural features from the segmented single characters or words.

[0082] Step S2015, using machine learning or deep learning algorithms, classify and recognize the extracted strokes, shapes, and structural features, and convert single characters or words into editable text.

[0083] The embodiment of the present application uses OCR image recognition to achieve high-precision text recognition and reduce the misrecognition rate.

[0084] Step S202, determining the OCR image recognition data, and if the OCR image recognition data is accurate, entering the OCR image recognition data.

[0085] See also Figure 4 As shown, step S202 specifically includes:

[0086] Step S2021, retrieve the preset customer ID card image judgment standard and driver's license image judgment standard.

[0087] The standard in this embodiment may be that an ID card picture should include: name, gender, ethnicity, date of birth, address, citizen identification number, issuing authority, validity period and other information; a driver's license picture should include certificate number, name, gender, nationality, address, date of birth, date of first license issuance, permitted vehicle type, validity period and other information.

[0088] Step S2022: If the comparison result is greater than a preset threshold, the OCR image recognition data is determined to be accurate and the OCR image recognition data is entered.

[0089] Step S2023, if the comparison result is greater than a preset threshold, the OCR image recognition data is determined to be accurate and the OCR image recognition data is entered, that is, if the comparison result contains the above information, it is indicated to be accurate.

[0090] Step S2024: If the comparison result is less than or equal to the preset threshold, it is determined that the OCR image recognition data is inaccurate. If the comparison result is greater than the preset threshold, it is determined that the OCR image recognition data is accurate and the OCR image recognition data is entered.

[0091] The embodiment of the present application can improve the accuracy and efficiency of OCR image recognition by retrieving preset customer ID card image judgment standards and driver's license image judgment standards for judgment.

[0092] Step S203: If the OCR image recognition data is inaccurate, ASR speech recognition is prompted to obtain ASR speech recognition data.

[0093] See also Figure 4 As shown, step S203 specifically includes:

[0094] Step S2031: If the OCR image recognition data is inaccurate, a prompt is given to enter voice information.

[0095] Step S2032, pre-processing the recorded voice signal to remove noise, reduce interference and digitize it.

[0096] Step S2033, extracting characteristic data of cepstral coefficients and Mel-frequency cepstral coefficients from the preprocessed speech signal.

[0097] Step S2034, using a machine learning algorithm to classify and identify the extracted feature data, and convert the speech into text.

[0098] In the embodiment of the present application, ASR speech recognition can realize automatic and real-time speech recognition, thereby improving the efficiency of the agents.

[0099] Step S204, calculating the distance between the OCR picture recognition data and the ASR speech recognition data and the sample to be classified;

[0100] In this embodiment, the sample to be classified may be one or more preset samples to be classified.

[0101] The distances between the OCR image recognition data and the ASR speech recognition data and the n samples to be classified are calculated according to the following formula:

[0102]

[0103] In the formula, x i Represents the data of OCR image recognition, x j Represents the data of ASR speech recognition, x iu Indicates the distance between the OCR image recognition data and the sample to be classified, x ju Indicates the distance between the ASR speech recognition data and the sample to be classified.

[0104] Step S205: Use the KNN clustering algorithm to classify the distances between the OCR image recognition data and the ASR speech recognition data and the samples to be classified.

[0105] In the embodiment of the present application, according to the principle of the KNN clustering algorithm, for each data, the k data points closest to it are found, the k data points are divided into a cluster, and then the category of the data is determined according to the category of the cluster to which the k data points belong.

[0106] Step S206, using a particle swarm algorithm to optimize the classification result to obtain an optimal classification result, and using the OCR image recognition data and ASR voice recognition data determined by the optimal classification result to enter customer information.

[0107] Particle Swarm Optimization (PSO) is an optimization algorithm based on swarm intelligence. It is inspired by the observation of group behavior such as bird flocks or fish schools. It simulates the flight behavior of particles in the search space and uses the historical experience of individuals and group information to search and optimize. The algorithm is simple to implement, has strong global search capabilities, and requires few parameter adjustments. It is widely used in many fields.

[0108] See also Figure 4 As shown, step S206 specifically includes:

[0109] Step S2061, using a particle swarm algorithm to determine the optimal classification result of the distance between the OCR image recognition data and the sample to be classified, and to determine the optimal classification result of the distance between the ASR speech recognition data and the sample to be classified.

[0110] Step S2062, based on the optimal classification result of the distance data between the ASR speech recognition data and the sample to be classified and the optimal classification result of the distance data between the OCR image recognition data and the sample to be classified, it is obtained that the distance data between the ASR speech recognition data and the sample to be classified and the distance data between the OCR image recognition data and the sample to be classified are optimal as a whole.

[0111] In the embodiment of the present application, a standard threshold can be set. When the optimal classification result of the distance data between the ASR speech recognition data and the sample to be classified and the optimal classification result of the distance data between the OCR image recognition data and the sample to be classified both exceed the standard threshold, it is considered that the overall optimization is achieved.

[0112] Step S2063: The field texts in all the OCR image recognition data and ASR voice recognition data that have achieved the best overall are used as the determined OCR image recognition data and ASR voice recognition data to enter the customer information.

[0113] The OCR image recognition data and ASR voice recognition data determined by the optimal classification result of the embodiment of the present application are used to enter customer information, which can more accurately identify text information and greatly improve work efficiency.

[0114] Wherein, step S2062 includes:

[0115] A dynamic threshold is set by the following formula;

[0116]

[0117] Represents the best solution generated in the current execution process, η j The meaning is the parameter of coefficient adjustment, Z j,k , k is a variable parameter in the range of [-1, 1];

[0118] Compare the optimal classification result of the distance data between the ASR speech recognition data and the sample to be classified and the optimal classification result of the distance between the OCR picture recognition data and the sample to be classified with the standard threshold respectively;

[0119] If both exceed the standard threshold, it is considered that the distance data between the ASR speech recognition data and the sample to be classified and the distance data between the OCR image recognition data and the sample to be classified are optimal as a whole.

[0120] The embodiment of the present application can enable the particle swarm algorithm to reach the optimal state by setting a dynamic threshold.

[0121] The present application collects the required useful information in real time through OCR image recognition and ASR voice recognition, performs automatic recognition, and automatically enters it into the system. This method can greatly reduce the time of input, and if the OCR image recognition data is inaccurate, it will prompt ASR voice recognition, double verification, and improve the recognition accuracy. Then, the KNN clustering algorithm is used to classify the distance between the OCR image recognition data and the ASR voice recognition data and the samples to be classified. Finally, the particle swarm algorithm is used to optimize the classification results to obtain the optimal classification results. The OCR image recognition data and ASR voice recognition data determined by the optimal classification results are used to enter customer information, which can more accurately identify the text information and greatly improve work efficiency.

[0122] The embodiment of the present application can collect useful information needed by the agent in real time, identify it, and then automatically enter it into the computer system. This method can greatly reduce the time it takes for the agent to enter information, greatly improving work efficiency. And when the customer needs to modify the vehicle information or personal identity information, it can also automatically identify the personal identity information filling fields such as: ID number, ID type, date of birth, gender, etc. The fields for automatically identifying vehicles to fill in are: license plate number, vehicle model name, brand model, approved number of seats, frame number, license plate number, initial registration date, tonnage, engine number, etc.

[0123] The embodiments of the present application can acquire and process relevant data based on artificial intelligence technology. Among them, artificial intelligence (AI) is the theory, method, technology and application system that uses digital computers or machines controlled by digital computers to simulate, extend and expand human intelligence, perceive the environment, acquire knowledge and use knowledge to obtain the best results.

[0124] AI basic technologies generally include sensors, dedicated AI chips, cloud computing, distributed storage, big data processing technology, operation / interaction systems, mechatronics, etc. AI software technologies mainly include computer vision technology, robotics technology, biometrics technology, speech processing technology, natural language processing technology, and machine learning / deep learning.

[0125] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiments can be implemented by instructing the relevant hardware through computer-readable instructions, and the computer-readable instructions can be stored in a computer-readable storage medium. When the program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, the aforementioned storage medium can be a non-volatile storage medium such as a disk, an optical disk, a read-only memory (ROM), or a random access memory (RAM).

[0126] It should be understood that, although the steps in the flowchart of the accompanying drawings are displayed in sequence as indicated by the arrows, these steps are not necessarily executed in sequence in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least a part of the steps in the flowchart of the accompanying drawings may include multiple sub-steps or multiple stages, and these sub-steps or stages are not necessarily executed at the same time, but can be executed at different times, and their execution order is not necessarily sequential, but can be executed in turn or alternately with other steps or at least a part of the sub-steps or stages of other steps.

[0127] Further references Figure 7 , as a response to the above Figure 2 The present application provides an embodiment of a customer information intelligent input device, and the device embodiment is similar to Figure 2 Corresponding to the method embodiment shown, the device can be specifically applied to various electronic devices.

[0128] like Figure 7 As shown, the customer information intelligent input device 700 of this embodiment includes: an acquisition module 701, a judgment module 702, a prompt module 703, a calculation module 704, a clustering module 705, and an optimization module 706. Among them:

[0129] The acquisition module 701 is used to acquire the customer's ID card and driver's license pictures, and perform OCR image recognition on the ID card and driver's license pictures.

[0130] The determination module 702 is used to determine whether the data of the OCR image recognition is accurate.

[0131] The prompt module 703 is used to prompt ASR speech recognition to be performed if the OCR picture recognition data is inaccurate, so as to obtain ASR speech recognition data.

[0132] The calculation module 704 is used to calculate the distance between the OCR picture recognition data and the ASR speech recognition data and the sample to be classified.

[0133] The clustering module 705 is used to classify the distances between the OCR image recognition data and the ASR speech recognition data and the samples to be classified by using the KNN clustering algorithm.

[0134] The optimization module 706 is used to optimize the classification result by using a particle swarm algorithm to obtain an optimal classification result, and to input customer information using the OCR image recognition data and ASR voice recognition data determined by the optimal classification result.

[0135] The present application collects the required useful information in real time through OCR image recognition and ASR voice recognition, performs automatic recognition, and automatically enters it into the system. This method can greatly reduce the time of input, and if the OCR image recognition data is inaccurate, it will prompt ASR voice recognition, double verification, and improve the recognition accuracy. Then, the KNN clustering algorithm is used to classify the distance between the OCR image recognition data and the ASR voice recognition data and the samples to be classified. Finally, the particle swarm algorithm is used to optimize the classification results to obtain the optimal classification results. The OCR image recognition data and ASR voice recognition data determined by the optimal classification results are used to enter customer information, which can more accurately identify the text information and greatly improve work efficiency.

[0136] To solve the above technical problems, the present application also provides a computer device. Figure 8 , Figure 8 This is a basic structural block diagram of the computer device in this embodiment.

[0137] The computer device 8 includes a memory 81, a processor 82, and a network interface 83 that are interconnected and communicated through a system bus. It should be noted that the figure only shows a computer device 8 with components 81-83, but it should be understood that it is not required to implement all the components shown, and more or fewer components can be implemented instead. Among them, those skilled in the art can understand that the computer device here is a device that can automatically perform numerical calculations and / or information processing according to pre-set or stored instructions, and its hardware includes but is not limited to microprocessors, application specific integrated circuits (Application Specific Integrated Circuit, ASIC), programmable gate arrays (Field-Programmable Gate Array, FPGA), digital processors (Digital Signal Processor, DSP), embedded devices, etc.

[0138] The computer device may be a computing device such as a desktop computer, a notebook, a PDA, a cloud server, etc. The computer device may interact with a user through a keyboard, a mouse, a remote controller, a touch pad, or a voice control device.

[0139] The memory 81 includes at least one type of readable storage medium, and the readable storage medium includes flash memory, hard disk, multimedia card, card-type memory (for example, SD or D customer information intelligent entry memory, etc.), random access memory (RAM), static random access memory (SRAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), programmable read-only memory (PROM), magnetic memory, disk, optical disk, etc. In some embodiments, the memory 81 can be an internal storage unit of the computer device 8, such as a hard disk or memory of the computer device 8. In other embodiments, the memory 81 can also be an external storage device of the computer device 8, such as a plug-in hard disk equipped on the computer device 8, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), etc. Of course, the memory 81 can also include both the internal storage unit of the computer device 8 and its external storage device. In this embodiment, the memory 81 is generally used to store the operating system and various application software installed on the computer device 8, such as computer-readable instructions of the customer information intelligent entry method, etc. In addition, the memory 81 can also be used to temporarily store various types of data that have been output or are to be output.

[0140] The processor 82 may be a central processing unit (CPU), a controller, a microcontroller, a microprocessor, or other data processing chips in some embodiments. The processor 82 is generally used to control the overall operation of the computer device 8. In this embodiment, the processor 82 is used to run the computer-readable instructions stored in the memory 81 or process data, such as running the computer-readable instructions of the customer information intelligent entry method.

[0141] The network interface 83 may include a wireless network interface or a wired network interface. The network interface 83 is generally used to establish a communication connection between the computer device 8 and other electronic devices.

[0142] The present application collects the required useful information in real time through OCR image recognition and ASR voice recognition, performs automatic recognition, and automatically enters it into the system. This method can greatly reduce the time of input, and if the OCR image recognition data is inaccurate, it will prompt ASR voice recognition, double verification, and improve the recognition accuracy. Then, the KNN clustering algorithm is used to classify the distance between the OCR image recognition data and the ASR voice recognition data and the samples to be classified. Finally, the particle swarm algorithm is used to optimize the classification results to obtain the optimal classification results. The OCR image recognition data and ASR voice recognition data determined by the optimal classification results are used to enter customer information, which can more accurately identify the text information and greatly improve work efficiency.

[0143] The present application also provides another embodiment, namely, providing a computer-readable storage medium, which stores computer-readable instructions, and the computer-readable instructions can be executed by at least one processor to enable the at least one processor to perform the steps of the customer information intelligent entry method as described above.

[0144] The present application collects the required useful information in real time through OCR image recognition and ASR voice recognition, performs automatic recognition, and automatically enters it into the system. This method can greatly reduce the time of input, and if the OCR image recognition data is inaccurate, it will prompt ASR voice recognition, double verification, and improve the recognition accuracy. Then, the KNN clustering algorithm is used to classify the distance between the OCR image recognition data and the ASR voice recognition data and the samples to be classified. Finally, the particle swarm algorithm is used to optimize the classification results to obtain the optimal classification results. The OCR image recognition data and ASR voice recognition data determined by the optimal classification results are used to enter customer information, which can more accurately identify the text information and greatly improve work efficiency.

[0145] The non-Company software tools or components appearing in the embodiments of this application are merely examples and do not represent actual use.

[0146] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present application, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk), and includes a number of instructions for a terminal device (which can be a mobile phone, computer, server, air conditioner, or network device, etc.) to execute the methods described in each embodiment of the present application.

[0147] Obviously, the embodiments described above are only some embodiments of the present application, rather than all embodiments. The preferred embodiments of the present application are given in the accompanying drawings, but they do not limit the patent scope of the present application. The present application can be implemented in many different forms. On the contrary, the purpose of providing these embodiments is to make the understanding of the disclosure of the present application more thorough and comprehensive. Although the present application is described in detail with reference to the aforementioned embodiments, for those skilled in the art, it is still possible to modify the technical solutions recorded in the aforementioned specific implementation methods, or to perform equivalent replacement of some of the technical features therein. Any equivalent structure made using the contents of the specification and drawings of this application, directly or indirectly used in other related technical fields, is similarly within the scope of patent protection of this application.

Claims

1. A method for intelligently entering customer information, characterized in that: The steps include: Obtain the customer's ID card and driver's license pictures, and perform OCR image recognition on the ID card and driver's license pictures; Determine whether the OCR image recognition data is accurate; If the OCR image recognition data is inaccurate, then a prompt is given to perform ASR speech recognition to obtain ASR speech recognition data; Calculate the distance between the OCR image recognition data and the ASR speech recognition data and the sample to be classified; Using KNN clustering algorithm to classify the distance between the OCR image recognition data and the ASR speech recognition data and the sample to be classified; The classification result is optimized by using a particle swarm algorithm to obtain an optimal classification result, and customer information is entered using the OCR image recognition data and the ASR voice recognition data determined by the optimal classification result.

2. The method for intelligently entering customer information according to claim 1, characterized in that: The step of obtaining the customer's ID card and driver's license pictures and performing OCR image recognition on the ID card and driver's license pictures specifically includes: Get pictures of the customer's ID card and driver's license; Perform pre-processing operations such as grayscale, binarization, denoising, and tilt correction on the acquired customer ID card and driver's license images; Segment the text in the customer ID card and driver's license images after preprocessing into individual characters or words; Extract stroke, shape, and structural features from the segmented individual characters or words; Machine learning or deep learning algorithms are used to classify and recognize the extracted strokes, shapes, and structural features, and convert individual characters or words into editable text.

3. The method for intelligently entering customer information according to claim 1, characterized in that: The step of determining whether the data recognized by the OCR image is accurate specifically includes: Retrieve the preset customer ID card image judgment standard and driver's license image judgment standard; Compare the OCR image recognition data with the customer ID card image determination standard and the driver's license image determination standard; If the comparison result is greater than a preset threshold, the OCR image recognition data is determined to be accurate and the OCR image recognition data is entered; If the comparison result is less than or equal to the preset threshold, it is determined that the data of the OCR image recognition is inaccurate.

4. The method for intelligently entering customer information according to claim 3, characterized in that: If the OCR image recognition data is inaccurate, the step of prompting to perform ASR speech recognition to obtain the ASR speech recognition data specifically includes: If the OCR image recognition data is inaccurate, a prompt is given to enter voice information; Pre-process the recorded speech signal to remove noise, reduce interference and digitize; Extracting characteristic data of cepstral coefficients and Mel-frequency cepstral coefficients from the preprocessed speech signal; The extracted feature data is classified and recognized using machine learning algorithms to convert speech into text.

5. The method for intelligently entering customer information according to claim 4, characterized in that: The step of calculating the distance between the OCR picture recognition data and the ASR speech recognition data and the sample to be classified specifically includes: The distances between the OCR image recognition data and the ASR speech recognition data and the n samples to be classified are calculated according to the following formula: In the formula, x i Represents the data of OCR image recognition, x j Represents the data of ASR speech recognition, x iu Indicates the distance between the OCR image recognition data and the sample to be classified, x ju Indicates the distance between the ASR speech recognition data and the sample to be classified.

6. The method for intelligently entering customer information according to claim 5, characterized in that: The step of optimizing the classification result by using a particle swarm algorithm to obtain an optimal classification result, and entering customer information using the OCR image recognition data and ASR voice recognition data determined by the optimal classification result specifically includes: Using a particle swarm algorithm to determine the optimal classification result of the distance between the OCR image recognition data and the sample to be classified, and to determine the optimal classification result of the distance between the ASR speech recognition data and the sample to be classified; According to the optimal classification result of the distance data between the ASR speech recognition data and the sample to be classified and the optimal classification result of the distance data between the OCR image recognition data and the sample to be classified, it is obtained that the distance data between the ASR speech recognition data and the sample to be classified and the distance data between the OCR image recognition data and the sample to be classified are optimal as a whole; The field texts in all the OCR image recognition data and ASR voice recognition data that have achieved the best overall are used as the determined OCR image recognition data and ASR voice recognition data for entering customer information.

7. The method for intelligently entering customer information according to claim 6, characterized in that: The optimal classification result of the distance data between the ASR speech recognition data and the sample to be classified and the optimal classification result of the distance data between the OCR image recognition data and the sample to be classified are obtained according to which the distance data between the ASR speech recognition data and the sample to be classified and the distance data between the OCR image recognition data and the sample to be classified are optimal as a whole, including: A dynamic threshold is set by the following formula; Represents the best solution generated in the current execution process, η j The meaning is the parameter of coefficient adjustment, Z j,k , k is a variable parameter in the range of [-1, 1]; Compare the optimal classification result of the distance data between the ASR speech recognition data and the sample to be classified and the optimal classification result of the distance data between the OCR picture recognition data and the sample to be classified with a standard threshold respectively; If both exceed the standard threshold, it is considered that the distance data between the ASR speech recognition data and the sample to be classified and the distance data between the OCR image recognition data and the sample to be classified are optimal as a whole.

8. A customer information intelligent input device, characterized in that: include: An acquisition module is used to acquire pictures of a customer's ID card and driver's license, and perform OCR image recognition on the pictures of the ID card and driver's license; A judgment module is used to judge whether the data of the OCR image recognition is accurate; A prompt module, used for prompting ASR speech recognition to obtain ASR speech recognition data if the OCR image recognition data is inaccurate; A calculation module, used to calculate the distance between the OCR image recognition data and the ASR speech recognition data and the sample to be classified; A clustering module, used to classify the distances between the OCR image recognition data and the ASR speech recognition data and the samples to be classified by using a KNN clustering algorithm; The optimization module is used to optimize the classification result by using a particle swarm algorithm to obtain an optimal classification result, and to input customer information using the OCR image recognition data and ASR voice recognition data determined by the optimal classification result.

9. A computer device comprising a memory and a processor, characterized in that: The memory stores computer-readable instructions, and when the processor executes the computer-readable instructions, the steps of the method for intelligently entering customer information according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer-readable instructions, and when the computer-readable instructions are executed by the processor, the steps of the customer information intelligent entry method according to any one of claims 1 to 7 are implemented.

Images