A text processing device and medium for civil aviation document review

Abstract

This application provides a text processing method for civil aviation document review, relating to the field of text processing. The method includes the following steps: obtaining a first semantic relevance between the target rule text to be reviewed and each superior rule text; if P1i≥Y1, then the i-th superior rule text is determined as the target superior rule text; otherwise, obtaining a second semantic relevance P2i between the target rule text to be reviewed and the first concatenated text corresponding to the i-th superior rule text; if P2i≥Y2, then the i-th superior rule text is determined as the target superior rule text; sorting the target superior rule texts according to a third semantic relevance between the target rule text to be reviewed and the second concatenated text corresponding to each target superior rule text, and outputting the target rule text to be reviewed and the sorted target superior rule texts to the review module; this application can effectively match highly abstract or generalized superior rule texts.

Description

Technical Field

[0001] This application relates to the field of text processing, and in particular to a text processing method, device and medium for civil aviation document review. Background Technology

[0002] When reviewing civil aviation documents (such as management documents formulated by civil aviation companies or airports), it is often necessary to quickly retrieve the relevant regulations of the relevant departments corresponding to each rule text in each civil aviation document, that is, the corresponding superior legal provisions, in order to assist human experts or review models in verifying the compliance of each rule in the civil aviation document.

[0003] Existing methods typically use semantic matching between rule text and related regulatory text and / or keyword retrieval to recall related regulatory text.

[0004] However, some relevant regulations are described in a highly abstract or general way, while the rules in actual civil aviation documents are specific implementation rules. For example, a relevant regulation might state, "If the carrier fails to transport passengers at the agreed time, it shall bear the responsibility," while a rule in civil aviation documents might state, "Flight changes of less than 15 minutes are not considered flight changes, and no refunds, alterations, or compensation will be provided." There is indeed a binding relationship between these two. When searching for the rule text, the aforementioned relevant regulations should also be retrieved. However, the semantic similarity between the two is extremely low. Simply using the semantic matching between the rule text and the relevant regulations for retrieval is essentially ineffective, and there are no shared keywords between them. This results in the inability to effectively retrieve the relevant regulations. Summary of the Invention

[0005] To address the aforementioned technical problem, the technical solution adopted in this application is as follows: A text processing method for civil aviation document review, the method comprising the following steps: S100, obtain the first semantic relevance between the target rule text to be reviewed and each superior rule text; the rule validity of the document to which the superior rule text belongs is higher than the rule validity of the civil aviation document; each superior rule text has a corresponding explanatory text and a domain term set; the total number of characters of the domain terms contained in the domain term set is less than the number of characters of its corresponding explanatory text; the target rule text to be reviewed is any one of the several rule texts to be reviewed contained in the civil aviation document; S200, if P1i≥Y1, then the i-th superior rule text is determined as the target superior rule text; otherwise, the second semantic relevance P2i between the target rule text to be reviewed and the first concatenated text corresponding to the i-th superior rule text is obtained; where P1i is the first semantic relevance between the target rule text to be reviewed and the i-th superior rule text, Y1 is the preset first semantic relevance threshold, and the first concatenated text corresponding to the i-th superior rule text is obtained by concatenating the i-th superior rule text and its corresponding explanatory text; the value of i is from 1 to n, and n is the number of superior rule texts; S300, if P2i≥Y2, then the i-th superordinate rule text is determined as the target superordinate rule text; Y2 is the preset second semantic relevance threshold; S400, the target superordinate rule text is sorted according to the third semantic relevance between the target rule text to be reviewed and the second concatenated text corresponding to each target superordinate rule text, and the target rule text to be reviewed and the sorted target superordinate rule text are output to the review module; the second concatenated text is obtained by concatenating the target superordinate rule text with its corresponding domain term set, and the review module is used to display the text and / or review the compliance of the target rule text to be reviewed.

[0006] In another aspect of this application, a non-transitory computer-readable storage medium is also provided, wherein at least one instruction or at least one program is stored in the non-transitory computer-readable storage medium, wherein the at least one instruction or the at least one program is loaded and executed by a processor to implement the above-described method.

[0007] In another aspect of this application, an electronic device is also provided, including a processor and the aforementioned non-transitory computer-readable storage medium.

[0008] This application has at least the following beneficial effects: This application provides a text processing method for civil aviation document review. When matching the target rule text to be reviewed with the superior rule text, if the first semantic relevance between the target rule text to be reviewed and the superior rule text is less than the first phonetic relevance threshold, the superior rule text and its corresponding explanatory text are concatenated and the second semantic relevance between the two is re-determined. In this way, the explanatory text is used to semantically supplement the superior rule text, thereby improving the recall rate of highly abstract superior rule texts.

[0009] On the other hand, after determining the target superordinate rule text, this application sorts the target superordinate rule text by the third semantic relevance, so that reviewers can quickly obtain highly relevant target superordinate rule texts in the subsequent review process, thereby reducing the workload of reviewers.

[0010] Meanwhile, in this application, since the explanatory texts are usually quite long, typically several hundred words or more, while the superordinate rule texts are usually only ten to thirty words, after concatenating the superordinate rule texts and their corresponding explanatory texts, most of the features in the semantic vectors will come from the explanatory texts. This means the explanatory texts may dilute the semantic features corresponding to the superordinate rule texts in the semantic feature vectors. When the rule text to be reviewed happens to be highly similar to the superordinate rule text, the semantic similarity between the semantic vector of the concatenated text and the semantic vector of the rule text to be reviewed will actually decrease. In this situation, if the first concatenated text is used for retrieval at the beginning, it is difficult to set the corresponding relevance threshold accurately. Setting it too high may result in missed retrievals, while setting it too low may lead to the recall of too many irrelevant superordinate rule texts.

[0011] To address this issue, this application first matches the target rule text to be reviewed with the parent rule text. Then, only parent rule texts with a first semantic relevance lower than the first semantic relevance threshold during the first matching process are matched a second time with the concatenated explanatory text. This avoids the aforementioned problem. Furthermore, the two thresholds can be set relatively independently, making it easier to set the ideal threshold.

[0012] Furthermore, since the explanatory text may dilute the semantic meaning of the superordinate rule text in the semantic feature vector, and the superordinate rule text may be highly abstract and generalized, it is inappropriate to use the superordinate rule text alone or the first concatenated text after sorting the determined target superordinate rule text. Therefore, this application uses the second concatenated text obtained by concatenating the target superordinate rule text with its corresponding domain term set (which has fewer characters than the explanatory text) for sorting, and uses highly relevant concrete domain terms as intermediate points for balancing, thereby avoiding the above problems.

[0013] On the other hand, the reason why the second concatenated text is not used in the second matching is that even if the actual meanings of some higher-level rule texts differ significantly, their corresponding concrete domain terms may be highly similar. If the second concatenated text is used in the second matching, it is easy to recall too many irrelevant higher-level rule texts. Therefore, in this application, the second concatenated text is only used to sort the target higher-level rule texts. Attached Figure Description

[0014] To more clearly illustrate the technical solutions in the embodiments of this application, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0015] Figure 1 This is a flowchart of a text processing method for civil aviation document review, provided as an embodiment of this application. Detailed Implementation

[0016] The technical solutions in the embodiments of this application will be clearly and completely described below. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0017] It is worth noting that in the following description, specific details such as particular system structures and techniques are set forth for illustrative purposes rather than for limiting purposes, in order to provide a thorough understanding of the embodiments of this application. However, those skilled in the art will understand that this application can also be implemented in other embodiments without these specific details. In other instances, detailed descriptions of well-known systems, apparatuses, circuits, and methods are omitted so as not to obscure the description of this application with unnecessary details.

[0018] It should be understood that in this application specification and the appended claims, the use of the terms "comprising," "including," "including but not limited to," "including but not limited to," "mainly composed of," or "mainly made of" indicates the presence of the described feature, integral, step, operation, element, and / or component, but does not exclude the presence or addition of one or more other features, integrals, steps, operations, elements, components, and / or collections thereof.

[0019] It should be understood that in this application specification and the appended claims, the use of the terms "consisting of" or "component of" indicates the presence of the described feature, integral, step, operation, element and / or component, but excludes the presence or addition of one or more other features, integrals, steps, operations, elements, components and / or collections thereof.

[0020] It should be understood that, in this specification and the appended claims, the term "and" indicates a combination in which multiple of the associated listed items exist simultaneously. For example, "A, B, C, and D" means a combination in which "A and B and C and D exist simultaneously".

[0021] It should be understood that in this application specification and the appended claims, the use of the term "or" indicates a combination in which one of the associated listed items exists alone. For example, "A, B, C or D" refers to the four combinations of "A alone", "B alone", "C alone", and "D alone".

[0022] It should be understood that, in this application specification and the appended claims, the term "and / or" indicates any combination of one or more of the associated listed items, as well as all possible combinations, and includes such combinations. For example, "A and / or B" refers to the three combinations of "A alone," "B alone," or "A and B simultaneously." For example, "A, B, and / or C" refers to the seven combinations of "A alone," "B alone," "C alone," "A and B simultaneously," "A and C simultaneously," "B and C simultaneously," and "A, B, and C simultaneously."

[0023] It should be understood that, in this specification and the appended claims, the term "if" is used to indicate, depending on the context, "in the case of," "when," "once," "in response to determination," or "in response to detection." Similarly, the phrase "if determined" or "if [the described condition or event] is detected" can be interpreted, depending on the context, as "once determined," "in response to determination," "once [the described condition or event] is detected," or "in response to detection of [the described condition or event]."

[0024] It should be understood that in this application specification and the appended claims, the terms "greater than", "less than", "exceeding", etc. are understood to exclude the number itself; and the terms "above", "below", "within", etc. are understood to include the number itself.

[0025] It should be understood that in this application specification and the appended claims, the terms "the," "the," "the," "the," "the," "the described," "the mentioned," etc., may be understood, depending on the context, to refer to the content mentioned above.

[0026] It should be understood that in this application specification and the appended claims, the terms "first," "second," "third," etc., are used only for distinguishing descriptions and should not be construed as indicating or implying relative importance, nor are they used to describe a specific order or sequence.

[0027] It should be understood that in this application specification and appended claims, the designations such as "S100," "S200," and "S300" are used only for distinguishing descriptions and should not be construed as indicating or implying a specific order or sequence of execution of steps or processes. For example, "S100, acquire data A; S200, acquire data B; S300, acquire C based on A and B;" is merely an example providing a feasible execution order, not a necessary one. Those skilled in the art can determine the actual and feasible execution order based on the function and internal logic of each step. For example, "step S100 is executed before step S200, then step S300 is executed," "step S200 is executed before step S100, then step S300 is executed," or "steps S100 and S200 are executed in parallel, then step S300 is executed."

[0028] It should be understood that in this application specification and appended claims, if numbering or quantity in the form of “f(i); i=1, 2, ..., n;” is used, the specific value corresponding to the term “f(i)” should be understood as a value that changes with the value of i, and not as a fixed value. For example, in different practical scenarios, “f(1)” and “f(2)”, “f(1)” may be equal to “f(2)” or may not be equal to “f(2)”, and unless otherwise specified, there is no necessary size relationship between “f(1)” and “f(2)”.

[0029] It should be understood that in this application specification and appended claims, if numbers or symbols in the form of superscript are used, and the context or other corresponding locations provide a specific interpretation of them, they should be understood according to their corresponding explanatory description, and cannot be directly and simply understood as concepts such as "exponent" in mathematics or "atomic number" in chemistry. Similarly, if numbers or symbols in the form of subscript are used, they should be understood in the same way, without further explanation.

[0030] It should be understood that in the description of this application and the appended claims, if terms such as "A=(...)" are used, unless otherwise specifically interpreted, they should be understood as "A includes...", and not as "A is composed of...". Furthermore, unless otherwise specifically interpreted, the parentheses "(" and ")" are only used in conjunction with "=" to indicate what items or data A includes, and do not refer to any specific data structure, nor do they limit the type of its elements, whether the number of elements is fixed, whether the elements are ordered, whether the elements are repeatable, what query method is required to query its elements, or what access order is required to access its elements.

[0031] It should be understood that in the description of this application and the appended claims, if common processing functions such as "max(...)", "min(...)", and "avg(...)" are used, the context or other corresponding locations should provide a specific interpretation of these terms. If no specific interpretation exists, those skilled in the art should use relevant technical terms from computer science and technology for connection. For example, "max(...)" refers to a function for determining the maximum value, "min(...)" refers to a function for determining the minimum value, and "avg(...)" refers to a function for determining the average value.

[0032] In one exemplary embodiment of this application, a text processing method for civil aviation document review is provided, the method comprising the following steps: S100, obtain the first semantic relevance between the target rule text to be reviewed and each superior rule text.

[0033] The rule validity of the document to which the superior rule text belongs is higher than that of the civil aviation document; each superior rule text has a corresponding explanatory text and a domain term set; the total number of characters of the domain terms contained in the domain term set is less than the number of characters of its corresponding explanatory text; the target rule text to be reviewed is any one of the several rule texts to be reviewed contained in the civil aviation document.

[0034] Specifically, the explanatory text can be obtained by compiling relevant official interpretation documents. This compilation process can be done manually or through a specific large language model. The domain term set contains at least one corresponding superordinate rule text containing actual terms that may exist in the relevant domain during practical application. The domain term set can be obtained manually, by performing word frequency statistics on relevant explanatory documents or texts, or by compiling features through a large language model. The rule validity of the document to which the superordinate rule text belongs is higher than that of the civil aviation document. This can be understood as meaning that the rules corresponding to each rule text stipulated in the civil aviation document should not violate the rules stipulated in each superordinate rule text.

[0035] S200, if P1i≥Y1, then the i-th superior rule text is determined as the target superior rule text; otherwise, the second semantic relevance P2i between the target rule text to be reviewed and the first concatenated text corresponding to the i-th superior rule text is obtained.

[0036] Where P1i is the first semantic relevance between the target rule text to be reviewed and the i-th superior rule text, Y1 is the preset first semantic relevance threshold, and the first concatenated text corresponding to the i-th superior rule text is obtained by concatenating the i-th superior rule text and its corresponding explanatory text; the value of i is from 1 to n, and n is the number of superior rule texts. S300, if P2i≥Y2, then the i-th superordinate rule text is determined as the target superordinate rule text. Y2 is a preset second semantic relevance threshold. Otherwise, the i-th superordinate rule text is not determined as the target superordinate rule text, and the next superordinate rule text is processed.

[0037] S400: Sort the target superordinate rule texts according to the third semantic relevance between the target rule text to be reviewed and the second concatenated text corresponding to each target superordinate rule text, and output the target rule text to be reviewed and the sorted target superordinate rule texts to the review module.

[0038] The second concatenated text is obtained by concatenating the target higher-level rule text with its corresponding domain term set. The review module is used to display the text and / or review the compliance of the target rule text to be reviewed.

[0039] Specifically, in this embodiment, each semantic relevance (such as the first, second, third, and fourth semantic relevance) can be obtained by semantically extracting the corresponding text content using a semantic extraction algorithm to obtain a corresponding semantic vector. The semantic relevance is then obtained by comparing the semantic relevance between the semantic vectors. Further, the semantic extraction algorithm can be the bag-of-words model algorithm, term frequency-inverse document frequency algorithm, topic model algorithm, BERT algorithm, Word2Vec algorithm, Sentence-BERT algorithm, etc. Preferably, this embodiment uses the Sentence-BERT algorithm, which has been specifically fine-tuned for the legal text domain. Semantic relevance can be obtained using cosine distance algorithm, Euclidean distance algorithm, or Mahalanobis distance algorithm, etc. Preferably, this embodiment uses the cosine distance algorithm to calculate the relevance between semantic vectors. It should be noted that since a larger cosine distance indicates a smaller text semantic relevance, in this embodiment, the actual semantic relevance used should be 1 minus the cosine distance.

[0040] In this embodiment of the application, the review module may be a display module for displaying text content, so that staff can review the compliance of the target rule text to be reviewed based on the displayed target rule text to be reviewed and each target superior rule text.

[0041] Alternatively, an automated review model can be built using large language models such as GPT-4 / GPT-4o / GPT-3.5 / Gemini / Qwen / DeepSeek-V3.2 / DeepSeek-R1. If a large language model is used, corresponding prompts can be set to allow the model to perform compliance checks on the target rule text to be reviewed. The matching process described above can be understood as the RAG mechanism in the working mechanism of the large language model. This involves recalling the target superordinate rule text and concatenating it into keywords, enabling the large language model to review the compliance of the target rule text based on the superordinate rule text, thereby reducing the illusion problem of the large language model.

[0042] This application provides a text processing method for civil aviation document review. When matching the target rule text to be reviewed with the superior rule text, if the first semantic relevance between the target rule text to be reviewed and the superior rule text is less than the first phonetic relevance threshold, the superior rule text and its corresponding explanatory text are concatenated and the second semantic relevance between the two is re-determined. In this way, the explanatory text is used to semantically supplement the superior rule text, thereby improving the recall rate of highly abstract superior rule texts.

[0043] On the other hand, after determining the target superordinate rule text, this application sorts the target superordinate rule text by the third semantic relevance, so that reviewers can quickly obtain highly relevant target superordinate rule texts in the subsequent review process, thereby reducing the workload of reviewers.

[0044] Meanwhile, in this application, since the explanatory texts are usually quite long, typically several hundred words or more, while the superordinate rule texts are usually only ten to thirty words, after concatenating the superordinate rule texts and their corresponding explanatory texts, most of the features in the semantic vectors will come from the explanatory texts. This means the explanatory texts may dilute the semantic features corresponding to the superordinate rule texts in the semantic feature vectors. When the rule text to be reviewed happens to be highly similar to the superordinate rule text, the semantic similarity between the semantic vector of the concatenated text and the semantic vector of the rule text to be reviewed will actually decrease. In this situation, if the first concatenated text is used for retrieval at the beginning, it is difficult to set the corresponding relevance threshold accurately. Setting it too high may result in missed retrievals, while setting it too low may lead to the recall of too many irrelevant superordinate rule texts.

[0045] To address this issue, this application first matches the target rule text to be reviewed with the parent rule text. Then, only parent rule texts with a first semantic relevance lower than the first semantic relevance threshold during the first matching process are matched a second time with the concatenated explanatory text. This avoids the aforementioned problem. Furthermore, the two thresholds can be set relatively independently, making it easier to set the ideal threshold.

[0046] Furthermore, since the explanatory text may dilute the semantic meaning of the superordinate rule text in the semantic feature vector, and the superordinate rule text may be highly abstract and generalized, it is inappropriate to use the superordinate rule text alone or the first concatenated text after sorting the determined target superordinate rule text. Therefore, this application uses the second concatenated text obtained by concatenating the target superordinate rule text with its corresponding domain term set (which has fewer characters than the explanatory text) for sorting, and uses highly relevant concrete domain terms as intermediate points for balancing, thereby avoiding the above problems.

[0047] On the other hand, the reason why the second concatenated text is not used in the second matching is that even if the actual meanings of some higher-level rule texts differ significantly, their corresponding concrete domain terms may be highly similar. If the second concatenated text is used in the second matching, it is easy to recall too many irrelevant higher-level rule texts. Therefore, in this application, the second concatenated text is only used to sort the target higher-level rule texts.

[0048] In one exemplary embodiment of this application, Y1 > Y2.

[0049] Because the explanatory text dilutes the semantics of the higher-level rule text and is relatively long, while the target rule text to be reviewed is relatively short and its semantics are relatively sparse, if Y2 is set to be greater than or equal to Y1, there may be cases of missed recalls. Therefore, in this application, Y1 > Y2.

[0050] In one exemplary embodiment of this application, prior to step S400, the method further includes the following steps: S001, obtain the fourth semantic relevance between the target rule text to be reviewed and each application example text; each application example text corresponds to at least one superior rule text; at least some application example texts correspond to duplicate superior rule texts, that is, there may be two or more partial application example texts that correspond to the same or several application example texts at the same time.

[0051] S002, if P4j≥Y4, then each superior rule text corresponding to the j-th application example text is determined as the target superior rule text; P4j is the fourth semantic relevance between the target rule text to be reviewed and the j-th application example text, and Y4 is the preset fourth semantic relevance threshold.

[0052] Furthermore, before step S400, before step S300, and after S002, the method further includes the following steps: S401, perform deduplication processing on the target superordinate rule text.

[0053] In some cases, if the wording of the rule text to be reviewed is not accurate enough or the circumstances it stipulates are extremely specific, even using explanatory texts may not achieve effective recall. Therefore, this application adds a separate application example text for additional recall, and sorts the recalled target superordinate rule texts using the same third semantic relevance as the target superordinate rule texts recalled by the aforementioned method, thereby effectively supplementing the recall and reducing the occurrence of missed recalls.

[0054] In this application, the example text can be obtained by organizing the rule texts that appear in historically reviewed civil aviation documents and then expanding them using a large language model or manually.

[0055] In this application embodiment, a non-transitory computer-readable storage medium is also provided. This non-transitory computer-readable storage medium can be disposed in an electronic device to store at least one instruction or at least one program related to implementing the method provided in any embodiment of this application. The at least one instruction or the at least one program is loaded and executed by a processor to implement the method provided in any embodiment of this application, and can achieve the same technical effect. To avoid repetition, further details are omitted here.

[0056] Examples of non-transitory computer-readable storage media include: computer read-only memory (ROM), random access memory (RAM), erasable programmable read-only memory (EPROM), compact disc read-only memory (CD-ROM), flash memory, magnetic disk, optical disk, portable computer disk, hard disk and / or solid-state drive, etc.

[0057] In this application embodiment, an electronic device is also provided, the electronic device including a processor and the non-transitory computer-readable storage medium. The processor loads and executes at least one instruction or at least one program stored in the non-transitory computer-readable storage medium related to implementing the method provided in any embodiment of this application, so as to implement the method provided in the embodiment of this application.

[0058] For example, the electronic device may be a mobile electronic device or a non-mobile electronic device that also includes other functions such as a personal digital assistant and / or music player. Further, the mobile electronic device may be any one of a mobile phone, tablet computer, laptop computer, PDA, in-vehicle electronic device, wearable device, ultra-mobile personal computer (UMPC), netbook, or personal digital assistant (PDA); the non-mobile electronic device includes any one of a server, network attached storage (NAS), personal computer (PC), television (TV), ATM, or self-service machine. No specific limitations are made in the embodiments of this application.

[0059] For example, the processor can be a processor in any electronic device.

[0060] Exemplary embodiments of this application also provide a feasible structure for an electronic device. For example, the electronic device may include a processor, an external memory interface, internal memory, a universal serial bus (USB) interface (hereinafter referred to as a USB interface), a charging management module, a power management module, a battery, a first antenna, a second antenna, a mobile communication module, a wireless communication module, an audio module, a speaker, a receiver, a microphone, a headphone jack, a sensor module, buttons, a motor, an indicator, a camera, a display screen, and a subscriber identification module (SIM) card interface (hereinafter referred to as a SIM card interface), etc. The sensor module may include pressure sensors, gyroscope sensors, barometric pressure sensors, magnetic sensors, accelerometers, distance sensors, proximity sensors, fingerprint sensors, temperature sensors, touch sensors, ambient light sensors, and / or bone conduction sensors, etc.

[0061] It should be understood that the exemplary structures of the embodiments of this application do not constitute a specific limitation on the electronic device. In other embodiments of this application, the electronic device may include more or fewer components than the structure described herein, or combine some components, or split some components, or have different component arrangements. The components may be implemented in hardware, software, or a combination of software and hardware.

[0062] For example, the processor may include one or more processing units, wherein the processing units include: an application processor (AP), a modem processor, a graphics processing unit (GPU), an image signal processor (ISP), a controller, a video codec, a digital signal processor (DSP), a baseband processor, and / or a neural network processing unit (NPU). Different processing units may be independent devices or integrated into one or more processors. The controller may generate operation control signals based on instruction opcodes and timing signals to control instruction fetching and execution.

[0063] For example, the processor may further include a memory for storing instructions and data. In some embodiments of this application, the memory in the processor is a cache memory. The memory can store instructions or data that the processor has just used or that are used repeatedly. If the processor needs to use the instructions or data again, it can directly retrieve them from the memory.

[0064] For example, the processor may also include one or more interfaces. These interfaces include: an inter-integrated circuit (I2C) interface, an inter-integrated circuit sound (I2S) interface, a pulse code modulation (PCM) interface, a universal asynchronous receiver / transmitter (UART) interface, a mobile industry processor interface (MIPI), a general-purpose input / output (GPIO) interface, a SIM card interface, and / or a USB interface, etc.

[0065] The integrated circuit interface is a bidirectional synchronous serial bus, which includes a serial data line (SDA) and a serial clock line (SCL).

[0066] Integrated circuits with built-in audio interfaces can be used for audio communication. In some embodiments of this application, the processor may include multiple sets of integrated circuit-based audio interfaces. The processor can couple with an audio module through the integrated circuit-based audio interface to achieve communication between the processor and the audio module.

[0067] The pulse code modulation interface can also be used for audio communication, specifically for sampling, quantizing, and encoding analog signals. In some embodiments of this application, the audio module and the wireless communication module can be coupled through the pulse code modulation interface.

[0068] A Universal Asynchronous Receiver / Transmitter (UART) is a universal serial data bus interface used for asynchronous communication. This bus can be a bidirectional communication bus interface. It converts the data to be transmitted between serial and parallel communication. In some embodiments of this application, the processor and the wireless communication module can be connected via the UART.

[0069] Mobile industry processor interfaces can be used to connect processors to peripheral devices such as displays and cameras.

[0070] General purpose input / output interfaces can be configured via software.

[0071] Furthermore, the general-purpose input / output interface can be configured as a control signal or a data signal. In some embodiments of this application, the general-purpose input / output interface can be used to connect the processor to a camera, display screen, wireless communication module, audio module, sensor module, etc.

[0072] A USB interface is an interface that conforms to the USB standard specification, specifically including Mini USB, Micro USB, and USB Type-C interfaces. USB interfaces can be used to connect chargers to charge electronic devices, and also for transferring data between electronic devices and peripheral devices.

[0073] It should be understood that the interface connection relationships between the modules illustrated in the embodiments of this application are merely illustrative and do not constitute a limitation on the structure of the electronic device. In other embodiments of this application, the electronic device may also employ different interface connection methods or a combination of multiple interface connection methods as described in the embodiments.

[0074] The charging management module receives charging input from a charger, which can be either a wireless or wired charger. In some wired charging embodiments, the charging management module receives charging input from the wired charger via a USB interface. In some wireless charging embodiments, the charging management module receives wireless charging input via the wireless charging coil of the electronic device. While charging the battery, the charging management module can also supply power to various parts of the electronic device via the power management module.

[0075] The power management module is used to connect the battery, the charging management module, and the processor.

[0076] Wireless communication functionality in electronic devices can be achieved through a first antenna, a second antenna, a mobile communication module, a wireless communication module, a modem processor, and a baseband processor.

[0077] Mobile communication modules can enable wireless communication solutions, including 2G / 3G / 4G / 5G, for use in electronic devices.

[0078] A modem processor may include a modulator and a demodulator. The modulator modulates a low-frequency baseband signal to be transmitted into a mid-to-high frequency signal. The demodulator demodulates a received electromagnetic wave signal into a low-frequency baseband signal. The demodulator then transmits the demodulated low-frequency baseband signal to a baseband processor for processing. After processing by the baseband processor, the low-frequency baseband signal is transmitted to an application processor. The application processor outputs sound signals through audio devices (not limited to speakers, receivers, etc.) or displays images or videos on a display screen. In some embodiments of this application, the modem processor may be a separate device. In other embodiments, the modem processor may be independent of the processor and housed within the same device as the mobile communication module or other functional modules.

[0079] Wireless communication modules can enable solutions for wireless communication applications in electronic devices, including wireless local area networks (WLAN) (such as wireless fidelity (Wi-Fi) networks), Bluetooth (BT), global navigation satellite system (GNSS), frequency modulation (FM), near field communication (NFC), and infrared (IR) technologies.

[0080] In some embodiments of this application, the first antenna of the electronic device is coupled to the mobile communication module, and the second antenna is coupled to the wireless communication module, enabling the electronic device to communicate with networks and other devices via wireless communication technology.

[0081] Electronic devices utilize GPUs, displays, and application processors to achieve their display functions. A GPU is a microprocessor for image processing, connecting the display and the application processor. GPUs perform mathematical and geometric calculations and are used for graphics rendering. A processor may include one or more GPUs, which execute program instructions to generate or modify display information.

[0082] The display screen is used to display images, videos, etc. The display screen includes a display panel. The display panel can be a liquid crystal display (LCD), or a display panel made of materials selected from organic light-emitting diodes (OLEDs), active-matrix organic light-emitting diodes (AMOLEDs), flexible light-emitting diodes (FLEDs), minimized, microLEDs, micro-OLEDs, or quantum dot light-emitting diodes (QLEDs). In some embodiments of this application, the electronic device may include one or more display screens. In some embodiments of this application, the display screen may also integrate touch functionality and may also be referred to as a touch screen.

[0083] Electronic devices can achieve shooting functions through ISPs, cameras, video codecs, GPUs, displays, and application processors.

[0084] External storage interfaces can be used to connect external memory cards, such as Micro SD cards, to expand the storage capacity of electronic devices.

[0085] Internal memory can be used to store executable program code for a computer, which includes instructions. The processor executes the instructions stored in internal memory to perform various functional applications and data processing of electronic devices.

[0086] Electronic devices can implement audio functions through audio modules, speakers, receivers, microphones, headphone jacks, and application processors. Examples include music playback and recording.

[0087] The audio module converts digital audio information into analog audio signals for output, and also converts analog audio input into digital audio signals. The speaker, also called a "horn," converts audio electrical signals into sound signals. The receiver, also called a "handset," converts audio electrical signals into sound signals. The microphone, also called a "microphone" or "voice transducer," converts sound signals into electrical signals. The headphone jack is used to connect wired headphones.

[0088] Pressure sensors are used to sense pressure signals and convert them into electrical signals. In some embodiments of this application, the pressure sensor can be located on the display screen. A gyroscope sensor can be used to determine the motion posture of the electronic device. A barometric pressure sensor is used to measure air pressure. In some embodiments of this application, the electronic device calculates altitude using the air pressure value measured by the barometric pressure sensor, assisting in positioning and navigation. An accelerometer can detect the magnitude of acceleration of the electronic device in various directions (generally three axes). A distance sensor is used to measure distance. A fingerprint sensor is used to collect fingerprints. A touch sensor, also known as a "touch panel," can be located on the display screen, forming a touchscreen, also known as a "touch screen." A bone conduction sensor can acquire vibration signals. In some embodiments of this application, a bone conduction sensor can acquire vibration signals from vibrating bone fragments in the human vocal cords. A bone conduction sensor can also contact the human pulse to receive blood pressure signals.

[0089] The buttons include a power button and volume buttons. A motor can generate vibration alerts. Indicators can be indicator lights, used to show charging status, battery level changes, messages, missed calls, notifications, etc. A SIM card slot is used to connect a SIM card.

[0090] Embodiments of this application also provide a computer program product including program code that, when the program product is run on an electronic device, causes the electronic device to perform the steps of the methods described in this specification according to various exemplary embodiments of this application.

[0091] This application also provides a chip, which includes a processor and a communication interface. The communication interface is used to receive signals and transmit the signals to the processor. The processor processes the signals so that the methods described in the various exemplary embodiments of this application are executed.

[0092] While specific embodiments of this application have been described in detail by way of examples, those skilled in the art should understand that the examples are for illustrative purposes only and not intended to limit the scope of this application. Those skilled in the art should also understand that various modifications can be made to the embodiments without departing from the scope and spirit of this application. The scope of this application is defined by the appended claims.

Claims

1. A text processing method for civil aviation document review, characterized in that, The method includes the following steps: S100, obtain the first semantic relevance between the target rule text to be reviewed and each superior rule text; the rule validity of the document to which the superior rule text belongs is higher than the rule validity of the civil aviation document; each superior rule text has a corresponding explanatory text and a domain term set; the total number of characters of the domain terms contained in the domain term set is less than the number of characters of its corresponding explanatory text; the target rule text to be reviewed is any one of the several rule texts to be reviewed contained in the civil aviation document; S200, if P1i≥Y1, then the i-th superior rule text is determined as the target superior rule text; otherwise, the second semantic relevance P2i between the target rule text to be reviewed and the first concatenated text corresponding to the i-th superior rule text is obtained; where P1i is the first semantic relevance between the target rule text to be reviewed and the i-th superior rule text, Y1 is the preset first semantic relevance threshold, and the first concatenated text corresponding to the i-th superior rule text is obtained by concatenating the i-th superior rule text and its corresponding explanatory text; the value of i is from 1 to n, and n is the number of superior rule texts; S300, if P2i≥Y2, then the i-th superordinate rule text is determined as the target superordinate rule text; Y2 is the preset second semantic relevance threshold; S400, the target superordinate rule text is sorted according to the third semantic relevance between the target rule text to be reviewed and the second concatenated text corresponding to each target superordinate rule text, and the target rule text to be reviewed and the sorted target superordinate rule text are output to the review module; the second concatenated text is obtained by concatenating the target superordinate rule text with its corresponding domain term set, and the review module is used to display the text and / or review the compliance of the target rule text to be reviewed.

2. The method according to claim 1, characterized in that, Prior to step S400, the method further includes the following steps: S001, obtain the fourth semantic relevance between the target rule text to be reviewed and each application example text; each application example text corresponds to at least one superior rule text; S002, if P4j≥Y4, then each superior rule text corresponding to the j-th application example text is determined as the target superior rule text; P4j is the fourth semantic relevance between the target rule text to be reviewed and the j-th application example text, and Y4 is the preset fourth semantic relevance threshold.

3. The method according to claim 2, characterized in that, Before step S400, before step S300, and after S002, the method further includes the following steps: S401, perform deduplication processing on the target superordinate rule text.

4. The method according to claim 1, characterized in that, At least some of the example application texts correspond to duplicate higher-level rule texts.

5. The method according to claim 1, characterized in that, Y1 > Y2.

6. The method according to claim 1, characterized in that, The review module is a large language model.

7. A non-transitory computer-readable storage medium, characterized in that, The non-transitory computer-readable storage medium stores at least one instruction or at least one program segment, which is loaded and executed by a processor to implement the method as described in any one of claims 1-6.

8. An electronic device, characterized in that, Includes a processor and the non-transitory computer-readable storage medium as described in claim 7.

Images