License plate number identification method, device and equipment based on entity extraction technology

Abstract

The invention provides a license plate number recognition method, device and equipment based on an entity extraction technology, and the method comprises the steps: carrying out the structural processing of a first text, so as to obtain a second text, and enabling the first text to be obtained through the text transliteration of a call record between a seat and a customer; character recognition and replacement are conducted on to-be-processed characters in the second text on the basis of a preset mapping dictionary to obtain a third text, the preset mapping dictionary is used for indicating the mapping relation between the to-be-processed characters and the target form characters, and the to-be-processed characters are homophonic characters or Chinese form numeric characters; the target form characters are determined based on license plate number naming rules; and performing matching processing on the third text based on a first regular expression to identify and determine a target character group, the first regular expression being constructed based on a license plate number naming rule. Therefore, the homophonic characters or Chinese-form numeric characters in the text can be effectively processed, so that the accuracy of license plate number recognition is effectively improved.

Description

Technical Field

[0001] This disclosure relates to the field of artificial intelligence technology, specifically to a method, apparatus, and device for license plate number recognition based on entity extraction technology. Background Technology

[0002] In the auto insurance industry, it's often necessary to extract license plate numbers from text messages to complete corresponding insurance transactions. Currently, extracting license plate number information from text primarily relies on rule-based regular expression matching or dictionary-based matching methods. However, these methods cannot effectively handle homophones and Chinese numeric characters in the text, affecting the accuracy of license plate number recognition. Summary of the Invention

[0003] This disclosure aims to at least partially address one of the technical problems in the related art.

[0004] Therefore, the purpose of this disclosure is to propose a license plate number recognition method, device, computer equipment, and storage medium based on entity extraction technology, which can effectively process homophones or Chinese numerical characters in text, thereby effectively improving the accuracy of license plate number recognition.

[0005] To achieve the above objectives, the license plate number recognition method based on entity extraction technology proposed in the first aspect of this disclosure includes:

[0006] The first text is structured to obtain the second text, wherein the first text is obtained by transcribing the recording of the call between the agent and the customer;

[0007] Based on a preset mapping dictionary, the characters to be processed in the second text are identified and replaced to obtain the third text. The preset mapping dictionary is used to indicate the mapping relationship between the characters to be processed and the target form characters. The characters to be processed are homophones or Chinese numeric characters. The target form characters are determined based on the license plate number naming rules.

[0008] The third text is matched based on a first regular expression to identify and determine the target character group, wherein the first regular expression is constructed based on the license plate number naming rules.

[0009] To achieve the above objectives, the license plate recognition device based on entity extraction technology proposed in the second aspect of this disclosure includes:

[0010] The first processing module is used to perform structured processing on the first text to obtain the second text, wherein the first text is obtained by transcribing the call recording between the agent and the customer.

[0011] The second processing module is used to perform character recognition and replacement on the characters to be processed in the second text based on a preset mapping dictionary to obtain a third text. The preset mapping dictionary is used to indicate the mapping relationship between the characters to be processed and the target form characters. The characters to be processed are homophones or Chinese numeric characters. The target form characters are determined based on the license plate number naming rules.

[0012] The third processing module is used to perform matching processing on the third text based on the first regular expression to identify and determine the target character group, wherein the first regular expression is constructed based on the license plate number naming rules.

[0013] The computer device proposed in the third aspect of this disclosure includes: a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the program, it implements the license plate number recognition method based on entity extraction technology proposed in the first aspect of this disclosure.

[0014] The fourth aspect of this disclosure provides a non-transitory computer-readable storage medium storing a computer program that, when executed by a processor, implements a license plate number recognition method based on entity extraction technology as proposed in the first aspect of this disclosure.

[0015] The fifth aspect of this disclosure provides a computer program product that, when executed by a processor, performs a license plate number recognition method based on entity extraction technology as proposed in the first aspect of this disclosure.

[0016] The license plate number recognition method, apparatus, computer equipment, and storage medium disclosed herein, based on entity extraction technology, obtain second text by performing structured processing on a first text, wherein the first text is obtained by transcribing a recorded call between a customer and an agent; character recognition and replacement are performed on the characters to be processed in the second text based on a preset mapping dictionary to obtain a third text, wherein the preset mapping dictionary indicates the mapping relationship between the characters to be processed and target form characters, the characters to be processed being homophones or Chinese numeric characters, and the target form characters being determined based on license plate number naming rules; and the third text is matched based on a first regular expression to identify and determine target character groups, wherein the first regular expression is constructed based on license plate number naming rules. Therefore, it is possible to effectively process homophones or Chinese numeric characters in the text, thereby effectively improving the accuracy of license plate number recognition.

[0017] Additional aspects and advantages of this disclosure will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of this disclosure. Attached Figure Description

[0018] The above and / or additional aspects and advantages of this disclosure will become apparent and readily understood from the following description of the embodiments taken in conjunction with the accompanying drawings, in which:

[0019] Figure 1 This is a flowchart illustrating a license plate number recognition method based on entity extraction technology proposed in an embodiment of this disclosure;

[0020] Figure 2 This is a flowchart illustrating a license plate number recognition method based on entity extraction technology proposed in another embodiment of this disclosure;

[0021] Figure 3 This is a schematic diagram of the structure of a license plate number recognition device based on entity extraction technology according to an embodiment of this disclosure;

[0022] Figure 4 A block diagram of an exemplary computer device suitable for implementing embodiments of the present disclosure is shown. Detailed Implementation

[0023] Embodiments of this disclosure are described in detail below, examples of which are illustrated in the accompanying drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and are used only to explain this disclosure, and should not be construed as limiting this disclosure. Rather, embodiments of this disclosure include all variations, modifications, and equivalents falling within the spirit and scope of the appended claims.

[0024] It should be noted that the information (including but not limited to user device information, user personal information, etc.), data (including but not limited to data used for analysis, data stored, data displayed, etc.) and signals involved in this disclosure are all authorized by the user or fully authorized by all parties, and the collection, use and processing of related data must comply with the relevant laws, regulations and standards of the relevant countries and regions.

[0025] Figure 1 This is a flowchart illustrating a license plate number recognition method based on entity extraction technology proposed in one embodiment of this disclosure.

[0026] It should be noted that the vehicle license plate recognition method based on entity extraction technology in this embodiment is executed by a vehicle license plate recognition device based on entity extraction technology. This device can be implemented by software and / or hardware. The device can be configured in a computer device, which may include, but is not limited to, a terminal, a server, etc. For example, the terminal may be a mobile phone, a PDA, etc.

[0027] like Figure 1 As shown, the license plate number recognition method based on entity extraction technology includes:

[0028] S101: Perform structured processing on the first text to obtain the second text, wherein the first text is obtained by transcribing the recording of the call between the agent and the customer.

[0029] The second text can refer to the text obtained after the first text has undergone structured processing.

[0030] Optionally, in some embodiments, when performing structured processing on the first text, timestamp characters in the first text can be identified and removed based on a second regular expression. This allows for the identification and removal of timestamp characters from the first text.

[0031] The second regular expression is a pre-configured regular expression used to identify and remove timestamp characters from the first text.

[0032] Optionally, in some embodiments, when performing structured processing on the first text, whitespace characters in the first text can be identified and removed based on a third regular expression. This allows for the identification and removal of whitespace characters in the first text.

[0033] The third regular expression refers to a pre-configured regular expression used to identify and remove whitespace characters in the first text.

[0034] It is understandable that the first text obtained after transcribing the call recording between the agent and the customer may contain a lot of useless information, which may affect the license plate recognition effect. Therefore, in this embodiment of the present disclosure, the first text can be structured to obtain the second text, thereby ensuring the practicality of the obtained second text.

[0035] S102: Based on a preset mapping dictionary, character recognition and replacement are performed on the characters to be processed in the second text to obtain the third text. The preset mapping dictionary is used to indicate the mapping relationship between the characters to be processed and the target form characters. The characters to be processed are homophones or Chinese numeric characters, and the target form characters are determined based on the license plate number naming rules.

[0036] The preset mapping dictionary can refer to a pre-configured dictionary used to map the conversion relationship between homophones or Chinese numeric characters and target characters.

[0037] Among them, homophones refer to the similar sounds of certain characters in daily life. For example, hook → J, cross → X, etc.

[0038] Among them, the Chinese-style numeric characters can refer to one, two, three, etc.

[0039] The target format characters can refer to the character format specified in the license plate number naming rules. For example, it can be Arabic numerals and uppercase letters.

[0040] In this embodiment of the disclosure, when the characters to be processed in the second text are identified and replaced based on a preset mapping dictionary to obtain the third text, the abnormal characters in the second text can be effectively processed, thereby effectively improving the robustness of license plate number recognition.

[0041] S103: Perform matching processing on the third text based on the first regular expression to identify and determine the target character group, wherein the first regular expression is constructed based on the license plate number naming rules.

[0042] The first regular expression can be a regular expression pre-constructed based on the naming rules for license plate numbers, used to identify license plate numbers in text.

[0043] The target character group can refer to the character group consisting of license plate numbers in the third text.

[0044] Optionally, in some embodiments, before matching the third text based on the first regular expression to identify and determine the target character group, the following may be further performed: First text segment in the third text is identified and determined based on a fourth regular expression, wherein the first text segment consists entirely of numeric characters, and the number of characters in the first text segment is greater than or equal to a first threshold; Second text segment in the third text is identified and determined based on a fifth regular expression, wherein the second text segment consists entirely of alphanumeric characters, and the number of characters in the second text segment is greater than or equal to the first threshold; The first and second text segments are marked as low-confidence segments. Thus, the identification and marking of continuous pure numeric character segments and continuous pure alphanumeric character segments can be achieved, thereby effectively avoiding interference from these segments in the subsequent license plate number recognition process.

[0045] The specific value of the first threshold can also be determined according to the license plate number naming rules. For example, it can be set to 5.

[0046] Optionally, in some embodiments, when performing matching processing on the third text based on the first regular expression to identify and determine the target character group, it may be as follows: performing matching processing on the third text based on the first regular expression to identify and determine candidate character groups; determining the matching result between the candidate character group and a preset character group library, wherein the preset character group library contains one or more character groups similar to license plate numbers; when the matching result indicates that the candidate character group does not belong to the preset character group library, determining the candidate character group as the target character group. This allows for secondary filtering of the obtained candidate character groups, thereby further improving the reliability of the obtained target character group.

[0047] The preset character group library can consist of object names that follow similar naming rules to license plate numbers. Examples include vehicle model numbers and engine oil names.

[0048] In other words, in this embodiment of the present disclosure, a first regular expression can be constructed based on the license plate number naming rules, and after obtaining the third text, the third text can be matched based on the first regular expression to identify and determine the target character group.

[0049] In this embodiment, a second text is obtained by structuring the first text, which is transcribed from a recorded call between an agent and a customer. A third text is obtained by character recognition and replacement of the characters to be processed in the second text based on a preset mapping dictionary. The preset mapping dictionary indicates the mapping relationship between the characters to be processed and the target characters. The characters to be processed are homophones or Chinese numeric characters, and the target characters are determined based on license plate number naming rules. The third text is then matched using a first regular expression to identify and determine the target character group. This first regular expression is constructed based on license plate number naming rules. Therefore, homophones or Chinese numeric characters in the text can be effectively processed, thereby significantly improving the accuracy of license plate number recognition.

[0050] Figure 2 This is a flowchart illustrating a license plate number recognition method based on entity extraction technology proposed in another embodiment of this disclosure.

[0051] like Figure 2 As shown, the license plate number recognition method based on entity extraction technology includes:

[0052] S201: Perform structured processing on the first text to obtain the second text, wherein the first text is obtained by transcribing the recording of the call between the agent and the customer.

[0053] S202: Based on a preset mapping dictionary, character recognition and replacement are performed on the characters to be processed in the second text to obtain the third text. The preset mapping dictionary is used to indicate the mapping relationship between the characters to be processed and the target form characters. The characters to be processed are homophones or Chinese numeric characters, and the target form characters are determined based on the license plate number naming rules.

[0054] S203: The third text is matched based on the first regular expression to identify and determine the target character group, wherein the first regular expression is constructed based on the license plate number naming rules.

[0055] The descriptions of S201-S203 can be found in the above embodiments, and will not be repeated here.

[0056] S204: Determine the position information of the target character group in the third text.

[0057] Among them, location information can be used to describe the position of the target character group in the third text.

[0058] S205: Based on the location information, the starting character of the license plate number, the characters inside the license plate number, and other characters in the third text are labeled to obtain the target text.

[0059] In other words, in this embodiment of the present disclosure, after determining the position information of the target character group in the third text, different labels can be used to label the starting character of the license plate number, the internal characters of the license plate number, and other characters in the third text, so that the obtained target text can clearly indicate the target character group therein.

[0060] S206: Construct training, validation, and test sets based on the target text.

[0061] The training set, validation set, and test set can refer to datasets constructed from multiple target texts used to train, validate, and test a pre-defined deep learning model.

[0062] Optionally, in some embodiments, when constructing training, validation, and test sets based on target text, the text length of the target text can be determined; if the text length is greater than a second threshold, the target text is truncated according to positional information, and the training, validation, and test sets are constructed based on the truncated target text; if the text length is less than or equal to the second threshold, the training, validation, and test sets are constructed based on the target text. This effectively improves the adaptability of the obtained training, validation, and test sets to the preset deep learning model.

[0063] The second threshold can refer to a threshold pre-configured for the text length.

[0064] S207: Train a pre-defined deep learning model based on the training set, validation set, and test set to obtain a target model, wherein the target model is used to predict the character label corresponding to each character in the input text.

[0065] That is to say, in the embodiments of the present disclosure, after determining the target character group, the position information of the target character group in the third text can be determined; according to the position information, the starting character of the license plate number, the internal characters of the license plate number, and other characters in the third text are respectively subjected to label marking processing to obtain the target text; a training set, a validation set, and a test set are constructed based on the target text; the preset deep learning model is trained based on the training set, the validation set, and the test set to obtain the target model, where the target model is used to predict the character label corresponding to each character in the input text. Thus, it can be ensured that the obtained target model can accurately identify the character label corresponding to each character in the input text, thereby realizing the automated processing of license plate number recognition.

[0066] In this embodiment, by determining the position information of the target character group in the third text; according to the position information, the starting character of the license plate number, the internal characters of the license plate number, and other characters in the third text are respectively subjected to label marking processing to obtain the target text; a training set, a validation set, and a test set are constructed based on the target text; the preset deep learning model is trained based on the training set, the validation set, and the test set to obtain the target model, where the target model is used to predict the character label corresponding to each character in the input text. Thus, it can be ensured that the obtained target model can accurately identify the character label corresponding to each character in the input text, thereby realizing the automated processing of license plate number recognition.

[0067] Combining the above embodiments, the present disclosure realizes the high-precision intelligent recognition and precise positioning of license plate numbers in the recorded and transcribed text through the method of constructing a multi-stage data preprocessing pipeline combined with deep learning model fine-tuning. The specific steps are as follows:

[0068] 1. Multi-level data preprocessing stage

[0069] The first layer: Dialogue structuring processing

[0070] Perform JSON format parsing on the input recorded and transcribed text to separate the dialogue content of the agent and the customer. Use the regular expression r'\[\d{2}:\d{2}-\d{2}:\d{2}\]' to remove the timestamp information, and use the r'\s+' regular expression to uniformly process various blank characters (including Chinese spaces, tab characters, line break characters), and format the processed dialogue content of the agent and the customer into the standard format of "Agent: XXX\nCustomer: YYY".

[0071] The second layer: Text standardization processing

[0072] Establish a mapping dictionary for Chinese numbers and homophonic characters, including number mappings (one → 1, two → 2, yao → 1, liang → 2, etc.) and letter homophonic mappings (hook → J, cross → X, etc.). Traverse each character in the text and perform character replacement according to the mapping dictionary to generate the standardized text.

[0073] 2. Intelligent Regular Expression Screening Phase

[0074] Continuous Character Detection Mechanism

[0075] Design a continuous character detection function. Use the regular expression r'\d{5,}' to detect 5 or more consecutive digits, and use r'[A-Za-z]{5,}' to detect 5 or more consecutive letters. When such an abnormal pattern is detected, mark the text segment as having low credibility to avoid misidentification.

[0076] Multi-pattern License Plate Number Sequence Matching

[0077] Construct two matching patterns according to the naming rules of license plate numbers: the six-character pattern r'(.)((?:[A-Za-z\d一二三四五六七八九十零幺两勾叉]+-?){6})' and the five-character pattern r'(..)((?:[A-Za-z\d一二三四五六七八九十零幺两勾叉]+-?){5})'. First, use the six-character pattern for matching. When no qualified result is found, then use the five-character pattern. Each pattern will additionally capture the leading characters to provide more context information.

[0078] Keyword Filtering Mechanism

[0079] Establish a negative keyword library to check the keywords of the matched candidate license plate numbers and exclude the mis-matched results that contain these keywords. For example: vehicle models and oil models that contain letters and numbers in their names.

[0080] 3. Location Positioning Phase​​​​​​​​​​​​​​​​​​​​The identified license plate number and its location information are converted into BIO (Begin-Inside-Outside) annotation format. Each character in the text is assigned a label: the starting character of the license plate number is labeled "B-LICENSE", the characters inside the license plate number are labeled "I-LICENSE", and other characters are labeled "O".

[0088] Dataset partitioning and validation

[0089] Implement a BIO annotation format verification mechanism to ensure that the "I-LICENSE" label must be preceded by either the "B-LICENSE" or "I-LICENSE" label. Divide the constructed dataset (intelligently truncated text) into training, validation, and test sets in a 7:1.5:1.5 ratio, and generate JSON data files to meet the model training requirements.

[0090] 5. Deep learning model fine-tuning stage

[0091] Pre-trained model adaptation

[0092] The BERT Chinese pre-trained model was chosen as the basic architecture, and a dedicated sequence labeling classification head was added to its top layer, with the output dimension set to 3 (corresponding to the three labels O, B-LICENSE, and I-LICENSE). BertTokenizerFast was used for text segmentation, with a maximum sequence length of 256, and padding and truncation strategies were employed to handle variable-length inputs.

[0093] Optimize training strategies

[0094] The AdamW optimizer is employed with a learning rate of 2e-5, and a linear learning rate scheduler is used to implement the warmup mechanism. During training, the cross-entropy loss function is used, and the loss calculation at padding positions is ignored through the attention_mask mechanism. Early stopping and a best-model preservation strategy are implemented, and the optimal model parameters are selected based on the validation set F1 score.

[0095] Model Evaluation and Deployment

[0096] The model performance was evaluated using metrics such as precision, recall, and F1 score, with particular attention paid to the recognition performance of B-LICENSE and I-LICENSE tags. After training, the model can perform character-level BIO tag prediction on newly input text, accurately locating the start and end positions of license plate numbers in the text by parsing consecutive "B-LICENSE" and "I-LICENSE" tag sequences.

[0097] Figure 3This is a schematic diagram of the structure of a license plate number recognition device based on entity extraction technology proposed in an embodiment of this disclosure.

[0098] like Figure 3 As shown, the license plate recognition device 30 based on entity extraction technology includes:

[0099] The first processing module 301 is used to perform structured processing on the first text to obtain the second text, wherein the first text is obtained by transcribing the call recording between the agent and the customer.

[0100] The second processing module 302 is used to perform character recognition and replacement on the characters to be processed in the second text based on a preset mapping dictionary to obtain the third text. The preset mapping dictionary is used to indicate the mapping relationship between the characters to be processed and the target form characters. The characters to be processed are homophones or Chinese numeric characters, and the target form characters are determined based on the license plate number naming rules.

[0101] The third processing module 303 is used to perform matching processing on the third text based on the first regular expression in order to identify and determine the target character group, wherein the first regular expression is constructed based on the license plate number naming rules.

[0102] It should be noted that the foregoing explanation of the license plate number recognition method based on entity extraction technology also applies to the license plate number recognition device based on entity extraction technology in this embodiment, and will not be repeated here.

[0103] In this embodiment, a second text is obtained by structuring the first text, which is transcribed from a recorded call between an agent and a customer. A third text is obtained by character recognition and replacement of the characters to be processed in the second text based on a preset mapping dictionary. The preset mapping dictionary indicates the mapping relationship between the characters to be processed and the target characters. The characters to be processed are homophones or Chinese numeric characters, and the target characters are determined based on license plate number naming rules. The third text is then matched using a first regular expression to identify and determine the target character group. This first regular expression is constructed based on license plate number naming rules. Therefore, homophones or Chinese numeric characters in the text can be effectively processed, thereby significantly improving the accuracy of license plate number recognition.

[0104] Figure 4 A block diagram of an exemplary computer device suitable for implementing embodiments of the present disclosure is shown. Figure 4 The computer device 12 shown is merely an example and should not be construed as limiting the functionality and scope of use of the embodiments disclosed herein.

[0105] like Figure 4As shown, the computer device 12 is represented in the form of a general-purpose computing device. The components of the computer device 12 may include, but are not limited to: one or more processors or processing units 16, system memory 28, and a bus 18 connecting different system components (including system memory 28 and processing unit 16).

[0106] Bus 18 represents one or more of several bus architectures, including a memory bus or memory controller, a peripheral bus, a graphics acceleration port, a processor, or a local bus using any of the various bus architectures. Examples of these architectures include, but are not limited to, the Industry Standard Architecture (ISA) bus, the Micro Channel Architecture (MAC) bus, the Enhanced ISA bus, the Video Electronics Standards Association (VESA) local bus, and the Peripheral Component Interconnect (PCI) bus.

[0107] Computer device 12 typically includes a variety of computer system readable media. These media can be any available media that can be accessed by computer device 12, including volatile and non-volatile media, removable and non-removable media.

[0108] Memory 28 may include computer system readable media in the form of volatile memory, such as random access memory (RAM) 30 and / or cache memory 32. Computer device 12 may further include other removable / non-removable, volatile / non-volatile computer system storage media. By way of example only, storage system 34 may be used to read and write non-removable, non-volatile magnetic media (…). Figure 4 Not shown; usually referred to as a "hard drive".

[0109] although Figure 4Not shown, a disk drive for reading and writing to a removable non-volatile disk (e.g., a "floppy disk") and an optical disc drive for reading and writing to a removable non-volatile optical disc (e.g., a Compact Disc Read-Only Memory (CD-ROM), a Digital Video Disc Read-Only Memory (DVD-ROM), or other optical media). In these cases, each drive may be connected to bus 18 via one or more data media interfaces. Memory 28 may include at least one program product having a set (e.g., at least one) of program modules configured to perform the functions of the embodiments of this disclosure.

[0110] A program / utility 40 having a set (at least one) of program modules 42 may be stored, for example, in memory 28. Such program modules 42 include, but are not limited to, an operating system, one or more application programs, other program modules, and program data. Each or some combination of these examples may include an implementation of a network environment. Program modules 42 typically perform the functions and / or methods described in the embodiments of this disclosure.

[0111] Computer device 12 can also communicate with one or more external devices 14 (e.g., keyboard, pointing device, display 24, etc.), and with one or more devices that enable human interaction with the computer device 12, and / or with any device that enables the computer device 12 to communicate with one or more other computing devices (e.g., network card, modem, etc.). This communication can be performed via input / output (I / O) interface 22. Furthermore, computer device 12 can also communicate with one or more networks (e.g., local area network (LAN), wide area network (WAN), and / or public networks, such as the Internet) via network adapter 20. As shown, network adapter 20 communicates with other modules of computer device 12 via bus 18. It should be understood that, although not shown in the figures, other hardware and / or software modules can be used in conjunction with computer device 12, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems.

[0112] The processing unit 16 executes various functional applications and data processing by running programs stored in the system memory 28, such as implementing the license plate number recognition method based on entity extraction technology mentioned in the foregoing embodiments.

[0113] To implement the above embodiments, this disclosure also proposes a non-transitory computer-readable storage medium storing a computer program that, when executed by a processor, implements the license plate number recognition method based on entity extraction technology as proposed in the foregoing embodiments of this disclosure.

[0114] To implement the above embodiments, this disclosure also proposes a computer program product that, when the instruction processor in the computer program product is executed, performs the license plate number recognition method based on entity extraction technology as proposed in the foregoing embodiments of this disclosure.

[0115] The collection, storage, use, processing, transmission, provision, and disclosure of user personal information involved in this disclosure all comply with the provisions of relevant laws and regulations and do not violate public order and good morals.

[0116] It should be noted that personal information collected from users should be used for legitimate and reasonable purposes and should not be shared or sold outside of these legitimate uses. Furthermore, such collection / sharing should only be conducted after receiving the user's informed consent, including but not limited to notifying the user to read the user agreement / user notice and sign an agreement / authorization that includes authorization of relevant user information before the user uses the function. In addition, any necessary steps must be taken to protect and safeguard access to such personal information data and ensure that others with access to personal information data comply with their privacy policies and procedures.

[0117] This disclosure is intended to provide implementation schemes for users to selectively prevent the use or access to their personal information data. Specifically, this disclosure is intended to provide hardware and / or software to prevent or block access to such personal information data. Once personal information data is no longer needed, risks can be minimized by restricting data collection and deleting data. Furthermore, where applicable, such personal information is de-identified to protect user privacy.

[0118] In the foregoing descriptions of the embodiments, the terms "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., refer to specific features, structures, materials, or characteristics described in connection with that embodiment or example, which are included in at least one embodiment or example of this disclosure. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples. Moreover, without contradiction, those skilled in the art can combine and integrate the different embodiments or examples described in this specification, as well as the features of different embodiments or examples.

[0119] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one of that feature. In the description of this disclosure, "a plurality of" means at least two, such as two, three, etc., unless otherwise explicitly specified.

[0120] Any process or method description in the flowchart or otherwise herein can be understood as representing a module, segment, or portion of code comprising one or more executable instructions for implementing custom logic functions or processes, and the scope of preferred embodiments of this disclosure includes additional implementations in which functions may be performed not in the order shown or discussed, including substantially simultaneously or in reverse order depending on the functions involved, as will be understood by those skilled in the art to which embodiments of this disclosure pertain.

[0121] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (such as a computer-based system, a processor-included system, or other system that can fetch and execute instructions from, an instruction execution system, apparatus, or device). For the purposes of this specification, "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transmit programs for use by, or in conjunction with, an instruction execution system, apparatus, or device. More specific examples (a non-exhaustive list) of computer-readable media include: an electrical connection having one or more wires (electronic device), a portable computer disk drive (magnetic device), random access memory (RAM), read-only memory (ROM), erasable and editable read-only memory (EPROM or flash memory), fiber optic devices, and portable optical disc read-only memory (CDROM). Alternatively, the computer-readable medium may be paper or other suitable media on which the program can be printed, since the program can be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, interpreting, or otherwise processing as necessary, and then stored in a computer memory.

[0122] It should be understood that various parts of this disclosure can be implemented using hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented using software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware as in another embodiment, it can be implemented using any one or a combination of the following techniques known in the art: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc.

[0123] Those skilled in the art will understand that all or part of the steps of the methods in the above embodiments can be implemented by a program instructing related hardware. The program can be stored in a computer-readable storage medium, and when executed, the program includes one or a combination of the steps of the method embodiments.

[0124] Furthermore, the functional units in the various embodiments of this disclosure can be integrated into a processing module, or each unit can exist physically separately, or two or more units can be integrated into a module. The integrated module can be implemented in hardware or as a software functional module. If the integrated module is implemented as a software functional module and sold or used as an independent product, it can also be stored in a computer-readable storage medium.

[0125] The storage medium mentioned above can be a read-only memory, a disk, or an optical disk, etc. Although embodiments of the present disclosure have been shown and described above, it is to be understood that the above embodiments are exemplary and should not be construed as limiting the present disclosure. Those skilled in the art can make changes, modifications, substitutions, and variations to the above embodiments within the scope of the present disclosure.

Claims

1. A license plate number recognition method based on entity extraction technology, characterized in that, include: The first text is structured to obtain the second text, wherein the first text is obtained by transcribing the recording of the call between the agent and the customer; Based on a preset mapping dictionary, the characters to be processed in the second text are identified and replaced to obtain the third text. The preset mapping dictionary is used to indicate the mapping relationship between the characters to be processed and the target form characters. The characters to be processed are homophones or Chinese numeric characters. The target form characters are determined based on the license plate number naming rules. The third text is matched based on a first regular expression to identify and determine the target character group, wherein the first regular expression is constructed based on the license plate number naming rules.

2. The method as described in claim 1, characterized in that, The structuring of the first text includes at least one of the following: The timestamp characters in the first text are identified and removed based on the second regular expression; The whitespace characters in the first text are identified and removed based on a third regular expression.

3. The method as described in claim 1, characterized in that, Before performing the matching process on the third text based on the first regular expression to identify and determine the target character group, the method further includes: The first text segment in the third text is identified based on the fourth regular expression, wherein the first text segment consists entirely of numeric characters, and the number of characters in the first text segment is greater than or equal to a first threshold. The second text segment in the third text is identified based on the fifth regular expression, wherein the second text segment consists entirely of alphabetic characters, and the number of characters in the second text segment is greater than or equal to the first threshold. The first and second text fragments are marked as low-confidence fragments.

4. The method as described in claim 1, characterized in that, The matching process based on the first regular expression to identify and determine the target character group includes: The third text is matched based on the first regular expression to identify and determine candidate character groups; Determine the matching result between the candidate character group and the preset character group library, wherein the preset character group library contains one or more character groups similar to license plate numbers; When the matching result indicates that the candidate character group does not belong to the preset character group library, the candidate character group is determined as the target character group.

5. The method as described in claim 1, characterized in that, The method further includes: Determine the position information of the target character group in the third text; Based on the location information, the starting character of the license plate number, the characters inside the license plate number, and other characters in the third text are labeled to obtain the target text; A training set, a validation set, and a test set are constructed based on the target text; The preset deep learning model is trained based on the training set, the validation set, and the test set to obtain the target model, wherein the target model is used to predict the character label corresponding to each character in the input text.

6. The method as described in claim 5, characterized in that, The construction of the training set, validation set, and test set based on the target text includes: Determine the text length of the target text; If the text length is greater than the second threshold, the target text is truncated according to the location information, and the training set, the validation set, and the test set are constructed based on the truncated target text. If the text length is less than or equal to the second threshold, then the training set, the validation set, and the test set are constructed based on the target text.

7. A license plate recognition device based on entity extraction technology, characterized in that, include: The first processing module is used to perform structured processing on the first text to obtain the second text, wherein the first text is obtained by transcribing the call recording between the agent and the customer. The second processing module is used to perform character recognition and replacement on the characters to be processed in the second text based on a preset mapping dictionary to obtain a third text. The preset mapping dictionary is used to indicate the mapping relationship between the characters to be processed and the target form characters. The characters to be processed are homophones or Chinese numeric characters. The target form characters are determined based on the license plate number naming rules. The third processing module is used to perform matching processing on the third text based on the first regular expression to identify and determine the target character group, wherein the first regular expression is constructed based on the license plate number naming rules.

8. A computer device, characterized in that, include: At least one processor; as well as A memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor to enable the at least one processor to perform the method of any one of claims 1-6.

9. A non-transitory computer-readable storage medium storing computer instructions, characterized in that, in, The computer instructions are used to cause the computer to perform the method according to any one of claims 1-6.

10. A computer program product, characterized in that, Includes a computer program that, when executed by a processor, implements the steps of the method according to any one of claims 1-6.

Images