A text processing method, apparatus, device and medium

Abstract

A text processing method, device, equipment and medium are disclosed. The method comprises: determining a plurality of groups of target recorded texts from at least two candidate recorded texts according to a vehicle model recording a recorded text; performing feature extraction on the target recorded texts according to a semantic extraction rule to determine candidate fault description information and a candidate fault level recorded by each target recorded text in each group of target recorded texts; determining a target fault level and target fault description information of each group of target recorded texts according to the number of target recorded texts of each candidate fault level in each group of target recorded texts and the candidate fault description information; and visually displaying the result of text processing according to the target fault level and target fault description information of each group of target recorded texts. The technical solution of the present application can accurately extract fault information of different vehicle models in recorded texts and perform visualization, which is helpful for subsequent analysis of potential risks of vehicles.

Description

Technical Field

[0001] This invention relates to the field of vehicles, and more particularly to a text processing method, apparatus, device, and medium. Background Technology

[0002] With the development of vehicle technology, the importance of automotive functional safety seems to be increasing. Different vehicle models may experience various types of malfunctions during operation, and their fault log texts contain a wealth of valuable information. In-depth analysis of the text content can provide guidance for product research, planning, development, as well as the analysis and early warning of frequent malfunctions.

[0003] Therefore, how to better process the text records after a vehicle malfunction, accurately extract valuable information from the text and visualize it so that relevant personnel can understand the potential risks of the product and improve vehicle safety in a targeted manner is an urgent problem to be solved. Summary of the Invention

[0004] This invention provides a text processing method, apparatus, device, and medium that can accurately extract and visualize fault information of different vehicle models from recorded text, which helps in subsequent analysis of potential vehicle risks.

[0005] According to one aspect of the present invention, a text processing method is provided, comprising:

[0006] Based on the vehicle model recorded in the recorded text, multiple sets of target recorded texts are determined from at least two candidate recorded texts; the recorded texts are texts that record the fault conditions that occurred in different vehicle models during historical operation;

[0007] Based on semantic extraction rules, feature extraction is performed on the target record text to determine the candidate fault description information and candidate fault level of each target record text in each group of target record texts;

[0008] Based on the candidate fault levels recorded in each target record text in each group, determine the target fault level and target fault description information of each group of target record texts;

[0009] Based on the target fault level and target fault description information of each group of target record texts, the results of text processing are visualized.

[0010] According to another aspect of the present invention, a text processing apparatus is provided, comprising:

[0011] The target text determination module is used to determine multiple sets of target record texts from at least two candidate record texts based on the vehicle model recorded in the record text; the record texts are texts recording the fault conditions that occurred in different vehicle models during historical operation;

[0012] The candidate information determination module is used to extract features from the target record text according to the semantic extraction rules, and determine the candidate fault description information and candidate fault level of each target record text in each group of target record texts;

[0013] The target information determination module is used to determine the target fault level and target fault description information of each group of target record texts based on the candidate fault levels of each target record text in each group of target record texts.

[0014] The visualization module is used to visualize the results of text processing based on the target fault level and target fault description information of each group of target record texts.

[0015] According to another aspect of the present invention, an electronic device is provided, the electronic device comprising:

[0016] At least one processor; and

[0017] A memory communicatively connected to the at least one processor; wherein,

[0018] The memory stores a computer program that can be executed by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to perform the text processing method according to any embodiment of the present invention.

[0019] According to another aspect of the present invention, a computer-readable storage medium is provided, the computer-readable storage medium storing computer instructions for causing a processor to execute and implement the text processing method described in any embodiment of the present invention.

[0020] The technical solution of this invention involves determining multiple sets of target recorded texts from at least two candidate recorded texts based on the vehicle model recorded in the text. According to semantic extraction rules, feature extraction is performed on the target recorded texts to determine the candidate fault description information and candidate fault level of each target recorded text in each set. Based on the number of target recorded texts with each candidate fault level in each set, and the candidate fault description information, the target fault level and target fault description information of each set of target recorded texts are determined. Finally, the results of the text processing are visualized based on the target fault level and target fault description information of each set of target recorded texts. This method allows for better text processing of recorded texts after vehicle malfunctions, accurately extracting and visualizing fault information for different vehicle models from the recorded texts. This enables relevant personnel to understand the potential risks of the product and to specifically improve the safety of the corresponding vehicle models.

[0021] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of the present invention, nor is it intended to limit the scope of the invention. Other features of the invention will become readily apparent from the following description. Attached Figure Description

[0022] To more clearly illustrate the technical solutions in the embodiments of the present invention, 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 the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0023] Figure 1 This is a flowchart of a text processing method provided in Embodiment 1 of the present invention;

[0024] Figure 2 This is a structural diagram of the text processing device provided in Embodiment 2 of the present invention;

[0025] Figure 3 This is a schematic diagram of the structure of the electronic device provided in Embodiment 3 of the present invention. Detailed Implementation

[0026] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0027] It should be noted that the terms "first," "second," "target," "candidate," etc., used in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0028] Example 1

[0029] Figure 1This is a flowchart of a text processing method provided in Embodiment 1 of the present invention. This embodiment is applicable to the processing of vehicle fault record text. The method can be executed by a text processing device, which can be implemented in software and / or hardware and can be integrated into an electronic device that implements text processing functions. Figure 1 As shown, the method includes:

[0030] S101. Based on the vehicle model recorded in the recorded text, determine multiple sets of target recorded texts from at least two candidate recorded texts.

[0031] The documented text consists of records of malfunctions that occurred during the historical operation of vehicles of different models. Candidate documented text includes records of malfunctions that occurred during the historical operation of multiple vehicle models. A target documented text is a set of texts recording malfunctions that occurred in vehicles of the same model.

[0032] Optionally, candidate record texts recording the same vehicle model can be grouped together based on the vehicle model recorded in the candidate record texts, that is, multiple groups of target record texts can be determined from at least two candidate record texts.

[0033] S102. Based on the semantic extraction rules, perform feature extraction on the target record text to determine the candidate fault description information and candidate fault level of each target record text in each group of target record texts.

[0034] Among them, semantic extraction rules refer to pre-defined rules for extracting key features (i.e., keyword groups) from the recorded text. Candidate fault description information refers to words and phrases in the target recorded text that describe the fault situation.

[0035] Candidate fault levels refer to levels that characterize the severity of the fault situation described in the target record text. Candidate fault levels can include a first fault level, a second fault level, a third fault level, and a fourth fault level. The first fault level is a no-harm level, which does not cause injury to the driver; the second fault level is a minor or limited harm level, which causes minor injury to the driver; the third fault level is a serious or life-threatening harm level, which the driver may survive; and the fourth fault level is a life-threatening or fatal harm level, which may result in the driver's death or even death.

[0036] The fault description information corresponding to the no-injury level may include at least one of the following: collision with roadside infrastructure, damage to non-critical components when entering / leaving a parking space, or no collision or rollover during driving; the fault description information corresponding to the minor injury level may include at least one of the following: side collision with a narrow stationary object, collision with another car traveling at low speed (within a preset low speed range), or frontal collision of the vehicle body without deformation of the passenger compartment; the fault description information corresponding to the serious injury level may include at least one of the following: frontal / rear collision with another bus traveling at low speed (within a preset low speed range), or collision of the vehicle itself with a pedestrian / bicycle at low speed (within a preset low speed range); the fault description information corresponding to the fatal injury level may include at least one of the following: collision with a tree at medium speed (within a preset medium speed range), frontal / rear collision with another vehicle traveling at medium speed (within a preset medium speed range), or frontal collision of the vehicle body causing deformation of the passenger compartment.

[0037] It should be noted that different vehicle models, due to their different configurations, will cause different electronic components (such as electronic controllers) to malfunction after a collision, thus resulting in different degrees of severity of consequences. Severity refers to the degree of injury caused to the driver / passenger or people near the vehicle. Based on the severity of the consequences caused by the malfunction, the candidate malfunction levels can be divided into the four levels mentioned above.

[0038] Optionally, based on semantic extraction rules, feature extraction is performed on the target record text to determine the candidate fault description information and candidate fault level of each target record text in each group of target record texts. This includes: for each target record text in each group of target record texts, determining whether it meets the preset semantic extraction rules; if so, feature extraction is performed on the target record text based on the semantic extraction rules met by each target record text to determine the candidate fault description information and candidate fault level of each target record text in each group of target record texts.

[0039] The semantic extraction rules can be preset keyword matching rules. Specifically, corresponding semantic extraction rules can be set for each candidate fault level.

[0040] Optionally, for each target record text in each group of target record texts, it can be matched with the preset semantic extraction rules for all fault levels to determine whether it meets the preset semantic extraction rules.

[0041] For example, the semantic extraction rules corresponding to the no-harm level may include at least one of the following:

[0042] (1) The semantic extraction rules for obstacle nouns plus collision verbs can be specifically represented as: (N) <barrier> +(V) <crash>, where (N) <barrier>Nouns representing obstacles encountered while driving, (V) <crash>This refers to a collision that occurs while driving. In such cases, the recorded text indicates that although a collision occurred, no injury was caused to the driver.

[0043] (2) Semantic extraction rules for vehicle non-critical component nouns plus destructive verbs, specifically, can be represented as: (N)<Non-critical parts> +(V) <break>, where (N)<Non-critical parts> The noun representing non-critical components of a vehicle during driving (V). <break>This refers to the act of causing damage. In this case, the recorded text indicates that a collision during driving caused damage to non-critical parts of the vehicle, but did not injure the driver.

[0044] (3) The semantic extraction rule for negative words plus collision verbs can be specifically represented as: (P) <privative> +(V) <crash>, of which (P) <privative>This refers to negative words, such as "NO" or "did not happen," which convey a negative meaning. (V) <crash>This refers to the action that resulted in a collision. In this case, the recorded text indicates that no collision occurred during driving, and the vehicle was being driven normally.

[0045] For example, the semantic extraction rules corresponding to the minor injury level may include at least one of the following:

[0046] (1) The semantic extraction rule of risk-free nouns plus low-risk adjectives plus collision verbs can be specifically represented as: (N)<free risk> +(ADJ)<low risk> +(V) <crash>, where (N)<free risk> A noun referring to something without risk (ADJ)<low risk> Adjectives describing low-risk components of a vehicle that are involved in a collision, such as the side of the vehicle, (V) <crash>This refers to the action of a collision. In this case, the recorded text indicates that in the collision, the damage to the colliding objects and the damaged parts of the vehicle was very minor, or even caused no injury to the driver.

[0047] (2) The semantic extraction rule for low-risk adjectives plus car nouns plus collision verbs can be specifically represented as: (ADJ)<low risk> +(N)<sedan car> +(V) <crash>Among them, (ADJ)<low risk> Adjectives describing low-risk driving conditions, such as "slightly deformed" or "minor," etc. (N)<sedan car> This refers to passenger cars, because passenger cars pose a lower risk in accidents than buses or coaches. (V) <crash>This refers to the action of a collision. The meaning represented by this recorded text is that when the two vehicles collided, the other vehicle was in a low-risk driving state, that is, the speed was within a preset low speed range, and it was also a vehicle of a relatively low risk level. Therefore, the injury to the driver after the collision was very minor or even non-existent.

[0048] (3) The semantic extraction rule of "collision verb + noun of key vehicle component + adjective of no harm" can be specifically represented as: (V) <crash>+(N)<critical parts> +(ADJ)<no damage> Among them, (V) <crash>The action that results in a collision. (N)<critical parts> Refers to key components or parts of a car. (ADJ)<no damage> This is an adjective describing a vehicle's critical components as undamaged. In this context, the text indicates that during a collision, while a collision occurred, critical parts of the vehicle, such as the driver's compartment and passenger side, remained undamaged. The vehicle itself sustained damage, but the driver or passenger suffered no injury or only minor damage.

[0049] Optionally, after determining the semantic extraction rules that each target record text satisfies, specifically, based on the semantic extraction rules satisfied by each target record text, feature extraction is performed on the target record text to determine the candidate fault description information and candidate fault level of each target record text in each group of target record texts, including: performing feature extraction on each target record text based on the semantic extraction rules satisfied by each target record text to determine the candidate fault description information of each target record text; and determining the candidate fault level of each target record text to be the fault level to which the semantic extraction rules it satisfies belong.

[0050] Optionally, feature extraction is performed on the target record text according to the semantic extraction rules satisfied by each target record text, including: if the fault level to which the semantic extraction rule satisfied by the target record text belongs is the first fault level, then the first keyword group in the target record text is extracted; if the fault level to which the semantic extraction rule satisfied by the target record text belongs is the second fault level, then the second keyword group in the target record text is extracted.

[0051] The first keyword group includes at least one of the following: obstacle nouns, collision verbs, non-critical vehicle component nouns, damage verbs, and negative words. Non-critical vehicle component nouns can include components that pose no safety hazard, such as sunroofs or windows. The second keyword group includes at least one of the following: risk-free nouns, low-risk adjectives, collision verbs, car nouns, critical vehicle component nouns, and harmless adjectives. Risk-free nouns can be nouns referring to pre-defined stationary objects, such as roadside barriers or trees.

[0052] Optionally, if the semantic extraction rule satisfied by the target record text is the semantic extraction rule of obstacle noun plus collision verb, then the fault level to which the semantic extraction rule satisfied by the target record text belongs can be determined as the first fault level. Furthermore, the first keyword group in the target record text can be extracted and parsed to determine the candidate fault description information of each target record text.

[0053] S103. Based on the number of target record texts for each candidate fault level in each group of target record texts, and the candidate fault description information, determine the target fault level and target fault description information for each group of target record texts.

[0054] The number of target record texts refers to the number of target record texts belonging to each candidate fault level within each group of target record texts. Each group of target record texts can determine one target fault level.

[0055] Optionally, based on the number of target record texts for each candidate fault level in each group of target record texts, and the candidate fault description information, the target fault level and target fault description information of each group of target record texts are determined, including: determining the ratio of target record texts for each candidate fault level to the total target record texts based on the number of target record texts for each candidate fault level in each group of target record texts; determining the target fault level of each group of target record texts based on the ratio; and integrating the candidate fault description information of each target record text in each group of target record texts as the target fault description information of that group of target record texts.

[0056] The total target record text refers to the total number of target record texts from all groups of target record texts. The proportional relationship refers to the ratio of the number of target record texts for each candidate fault level to the total number of target record texts in each group.

[0057] Optionally, for each group of target record texts, the number of target record texts for each candidate fault level can be determined, denoted as the first quantity, and the total number of target record texts in the group can be denoted as the second quantity. This allows the determination of multiple ratios between the first quantity and the second quantity, which in turn determines the maximum ratio among the ratios between the number of target record texts for each candidate fault level and the total number of target record texts in the group. The candidate fault level associated with the maximum ratio is then determined as the target fault level. For example, for a group of target record texts, if the ratio of the number of target record texts for the first fault level to the second quantity is 0.5, the ratio of the number of target record texts for the second fault level to the second quantity is 0.3, and the ratio of the number of target record texts for the third fault level to the second quantity is 0.2, then the target fault level for this group of target record texts can be determined as the first fault level.

[0058] S104. Based on the target fault level and target fault description information of each group of target record texts, visualize the results of text processing.

[0059] Optionally, the results of text processing can be visualized based on the target fault level and target fault description information of each group of target record texts, including: visualizing the results of text processing based on the target vehicle models associated with each group of target record texts, the target fault level and target fault description information of each group of target record texts.

[0060] It should be noted that each set of target record text is associated with the record information of a vehicle model. By visualizing the fault level and fault description information of each vehicle model, that is, by visualizing the severity of faults in different vehicle models, relevant personnel can understand the severity of faults in different vehicle models, thereby improving product quality in a targeted manner.

[0061] Optionally, after performing steps S101-S103 above, grouping the recorded text, and determining the target fault level and target fault description information for each group of target recorded text, the results of text processing can be visualized in a targeted manner through interaction with relevant personnel. Specifically, this includes: obtaining the vehicle model to be displayed, and determining the corresponding fault level and fault description information to be displayed for the vehicle model; and visualizing the results of text processing based on the vehicle model, fault level, and fault description information to be displayed.

[0062] Optionally, the vehicle model to be displayed can be obtained from the input of relevant personnel. After obtaining the vehicle model to be displayed, it can be matched with the vehicle models associated with each group of target record texts. The target fault level and target fault description information of the matched target record texts are used as the display fault level and display fault description information corresponding to the vehicle model.

[0063] It should be noted that this method allows relevant personnel to intuitively understand the severity of past malfunctions and related information of the target vehicle model.

[0064] The technical solution of this invention involves determining multiple sets of target recorded texts from at least two candidate recorded texts based on the vehicle model recorded in the text. According to semantic extraction rules, feature extraction is performed on the target recorded texts to determine the candidate fault description information and candidate fault level of each target recorded text in each set. Based on the number of target recorded texts with each candidate fault level in each set, and the candidate fault description information, the target fault level and target fault description information of each set of target recorded texts are determined. Finally, the results of the text processing are visualized based on the target fault level and target fault description information of each set of target recorded texts. This method allows for better text processing of recorded texts after vehicle malfunctions, accurately extracting and visualizing fault information for different vehicle models from the recorded texts. This enables relevant personnel to understand the potential risks of the product and to specifically improve the safety of the corresponding vehicle models.

[0065] Example 2

[0066] Figure 2 This is a structural diagram of the text processing device provided in Embodiment 2 of the present invention. The text processing device provided in this embodiment of the present invention can execute the text processing method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of executing the method.

[0067] like Figure 2 As shown, the device includes:

[0068] The target text determination module 201 is used to determine multiple sets of target record texts from at least two candidate record texts based on the vehicle model recorded in the record text; the record texts are texts that record the fault conditions that occurred in different vehicle models during historical operation.

[0069] The candidate information determination module 202 is used to extract features from the target record text according to the semantic extraction rules, and determine the candidate fault description information and candidate fault level of each target record text in each group of target record texts;

[0070] The target information determination module 203 is used to determine the target fault level and target fault description information of each group of target record texts based on the number of target record texts of each candidate fault level in each group of target record texts and the candidate fault description information.

[0071] The visualization module 204 is used to visualize the results of text processing based on the target fault level and target fault description information of each group of target record texts.

[0072] The technical solution of this invention involves determining multiple sets of target recorded texts from at least two candidate recorded texts based on the vehicle model recorded in the text. According to semantic extraction rules, feature extraction is performed on the target recorded texts to determine the candidate fault description information and candidate fault level of each target recorded text in each set. Based on the number of target recorded texts with each candidate fault level in each set, and the candidate fault description information, the target fault level and target fault description information of each set of target recorded texts are determined. Finally, the results of the text processing are visualized based on the target fault level and target fault description information of each set of target recorded texts. This method allows for better text processing of recorded texts after vehicle malfunctions, accurately extracting and visualizing fault information for different vehicle models from the recorded texts. This enables relevant personnel to understand the potential risks of the product and to specifically improve the safety of the corresponding vehicle models.

[0073] Furthermore, the candidate information determination module 202 may include:

[0074] The judgment unit is used to determine whether each target record text in each group of target record texts meets the preset semantic extraction rules.

[0075] The candidate information determination unit is used to extract features from the target record text according to the semantic extraction rules satisfied by each target record text, and determine the candidate fault description information and candidate fault level of each target record text in each group of target record texts.

[0076] Furthermore, the candidate information determination unit is specifically used for:

[0077] Based on the semantic extraction rules satisfied by each target record text, feature extraction is performed on each target record text to determine the candidate fault description information of each target record text;

[0078] The candidate fault level of each target record text is determined to be the fault level to which the semantic extraction rule it satisfies belongs.

[0079] Furthermore, the candidate information determination unit is also used for:

[0080] If the target record text satisfies the semantic extraction rule and the fault level is the first fault level, then the first keyword group in the target record text is extracted; the first keyword group includes at least one of the following: obstacle nouns, collision verbs, vehicle non-critical component nouns, damage verbs, and negation words;

[0081] If the target record text satisfies the semantic extraction rule and the fault level belongs to the second fault level, then the second keyword group in the target record text is extracted; the second keyword group includes at least one of the following: risk-free nouns, low-risk adjectives, collision verbs, car nouns, vehicle key component nouns, and harmless adjectives.

[0082] Furthermore, the target information determination module 203 is specifically used for:

[0083] Based on the number of target record texts for each candidate fault level in each group of target record texts, determine the ratio of target record texts for each candidate fault level to the total target record texts;

[0084] Based on the aforementioned proportional relationship, determine the target fault level of each group of target record texts;

[0085] The candidate fault description information of each target record text in each group is integrated to form the target fault description information of that group of target record texts.

[0086] Furthermore, the visualization module 204 is specifically used for:

[0087] Based on the target vehicle models associated with each group of target record texts, the target fault levels and target fault descriptions of each group of target record texts, the results of text processing are visualized.

[0088] Furthermore, the visualization module 204 is also used for:

[0089] Obtain the vehicle model to be displayed, and determine the corresponding fault level and fault description information to be displayed for the vehicle model;

[0090] Based on the vehicle model to be displayed, the fault level to be displayed, and the fault description information to be displayed, the results of text processing are visualized.

[0091] It should be noted that the acquisition, storage, and application of user personal information and vehicle record information involved in the technical solution disclosed herein comply with the provisions of relevant laws and regulations and do not violate public order and good morals.

[0092] Example 3

[0093] Figure 3 This is a schematic diagram of the structure of the electronic device provided in Embodiment 3 of the present invention. Figure 3 A schematic diagram of an electronic device 10 that can be used to implement embodiments of the present invention is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices (e.g., helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the invention described and / or claimed herein.

[0094] like Figure 3 As shown, the electronic device 10 includes at least one processor 11 and a memory, such as a read-only memory (ROM) 12 or a random access memory (RAM) 13, communicatively connected to the at least one processor 11. The memory stores computer programs executable by the at least one processor. The processor 11 can perform various appropriate actions and processes based on the computer program stored in the ROM 12 or loaded from storage unit 18 into the RAM 13. The RAM 13 can also store various programs and data required for the operation of the electronic device 10. The processor 11, ROM 12, and RAM 13 are interconnected via a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0095] Multiple components in electronic device 10 are connected to I / O interface 15, including: input unit 16, such as keyboard, mouse, etc.; output unit 17, such as various types of displays, speakers, etc.; storage unit 18, such as disk, optical disk, etc.; and communication unit 19, such as network card, modem, wireless transceiver, etc. Communication unit 19 allows electronic device 10 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0096] Processor 11 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. Processor 11 performs the various methods and processes described above, such as text processing methods.

[0097] In some embodiments, the text processing method may be implemented as a computer program tangibly contained in a computer-readable storage medium, such as storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or mounted on electronic device 10 via ROM 12 and / or communication unit 19. When the computer program is loaded into RAM 13 and executed by processor 11, one or more steps of the text processing method described above may be performed. Alternatively, in other embodiments, processor 11 may be configured to perform the text processing method by any other suitable means (e.g., by means of firmware).

[0098] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), payload-programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0099] Computer programs used to implement the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when executed by the processor, the computer programs cause the functions / operations specified in the flowcharts and / or block diagrams to be performed. The computer programs may be executed entirely on a machine, partially on a machine, or as a standalone software package, partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0100] In the context of this invention, a computer-readable storage medium can be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, apparatus, or device. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination thereof. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0101] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the electronic device. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0102] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or computing systems that include middleware components (e.g., application servers), or computing systems that include frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., communication networks). Examples of communication networks include local area networks (LANs), wide area networks (WANs), blockchain networks, and the Internet.

[0103] A computing system can include clients and servers. Clients and servers are generally located far apart and typically interact through communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or cloud host, which is a hosting product within the cloud computing service system to address the shortcomings of traditional physical hosts and VPS services, such as high management difficulty and weak business scalability.

[0104] It should be understood that the various forms of processes shown above can be used, with steps reordered, added, or deleted. For example, the steps described in this invention can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution of this invention can be achieved, and this is not limited herein.

[0105] The specific embodiments described above do not constitute a limitation on the scope of protection of this invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this invention should be included within the scope of protection of this invention.< / crash> < / crash> < / crash> < / crash> < / crash> < / crash> < / crash> < / privative> < / crash> < / privative> < / break> < / break> < / crash> < / barrier> < / crash> < / barrier>

Claims

1. A text processing method, characterized in that, include: Based on the vehicle model recorded in the recorded text, multiple sets of target recorded texts are determined from at least two candidate recorded texts; the recorded texts are texts that record the fault conditions that occurred in different vehicle models during historical operation; Based on semantic extraction rules, feature extraction is performed on the target record text to determine the candidate fault description information and candidate fault level of each target record text in each group of target record texts; wherein, the semantic extraction rules are preset matching rules for each candidate fault level; Based on the number of target record texts for each candidate fault level in each group of target record texts, and the candidate fault description information, determine the target fault level and target fault description information for each group of target record texts; Based on the target fault level and target fault description information of each group of target record texts, the results of text processing are visualized. The step of extracting features from the target record text according to semantic extraction rules to determine the candidate fault description information and candidate fault level of each target record text in each group of target record texts includes: For each target record text in each group of target record texts, determine whether it meets the preset semantic extraction rules; If so, then based on the semantic extraction rules satisfied by each target record text, feature extraction is performed on each target record text to determine the candidate fault description information of each target record text; The candidate fault level of each target record text is determined to be the fault level to which the semantic extraction rule it satisfies belongs; The step of extracting features from each target record text according to the semantic extraction rules satisfied by each target record text includes: If the target record text satisfies the semantic extraction rule and the fault level is the first fault level, then the first keyword group in the target record text is extracted; the first keyword group includes at least one of the following: obstacle nouns, collision verbs, vehicle non-critical component nouns, damage verbs, and negation words; If the target record text satisfies the semantic extraction rule and the fault level belongs to the second fault level, then the second keyword group in the target record text is extracted; the second keyword group includes at least one of the following: risk-free nouns, low-risk adjectives, collision verbs, car nouns, vehicle key component nouns, and harmless adjectives.

2. The method according to claim 1, characterized in that, Based on the number of target record texts for each candidate fault level in each group of target record texts, and the candidate fault description information, the target fault level and target fault description information for each group of target record texts are determined, including: Based on the number of target record texts for each candidate fault level in each group of target record texts, determine the ratio of target record texts for each candidate fault level to the total target record texts; Based on the aforementioned proportional relationship, determine the target fault level of each group of target record texts; The candidate fault description information of each target record text in each group is integrated to form the target fault description information of that group of target record texts.

3. The method according to claim 1, characterized in that, Based on the target fault level and target fault description information of each group of target record texts, the results of text processing are visualized, including: Based on the target vehicle models associated with each group of target record texts, the target fault levels and target fault descriptions of each group of target record texts, the results of text processing are visualized.

4. The method according to claim 3, characterized in that, Also includes: Obtain the vehicle model to be displayed, and determine the corresponding fault level and fault description information to be displayed for the vehicle model; Based on the vehicle model to be displayed, the fault level to be displayed, and the fault description information to be displayed, the results of text processing are visualized.

5. A text processing device, characterized in that, include: The target text determination module is used to determine multiple sets of target record texts from at least two candidate record texts based on the vehicle model recorded in the record text; the record texts are texts recording the fault conditions that occurred in different vehicle models during historical operation; The candidate information determination module is used to extract features from the target record text according to the semantic extraction rules, and determine the candidate fault description information and candidate fault level of each target record text in each group of target record texts; wherein, the semantic extraction rules are preset matching rules for each candidate fault level; The target information determination module is used to determine the target fault level and target fault description information of each group of target record texts based on the number of target record texts of each candidate fault level in each group of target record texts and the candidate fault description information. The visualization module is used to visualize the results of text processing based on the target fault level and target fault description information of each group of target record texts. The candidate information determination module includes: The judgment unit is used to determine whether each target record text in each group of target record texts meets the preset semantic extraction rules. The candidate information determination unit is used to extract features from the target record text according to the semantic extraction rules satisfied by each target record text if the condition is met, and to determine the candidate fault description information and candidate fault level of each target record text in each group of target record texts. Specifically, the candidate information determination unit is used for: Based on the semantic extraction rules satisfied by each target record text, feature extraction is performed on each target record text to determine the candidate fault description information of each target record text; The candidate fault level of each target record text is determined to be the fault level to which the semantic extraction rule it satisfies belongs; The step of extracting features from each target record text according to the semantic extraction rules satisfied by each target record text includes: If the target record text satisfies the semantic extraction rule and the fault level is the first fault level, then the first keyword group in the target record text is extracted; the first keyword group includes at least one of the following: obstacle nouns, collision verbs, vehicle non-critical component nouns, damage verbs, and negation words; If the target record text satisfies the semantic extraction rule and the fault level belongs to the second fault level, then the second keyword group in the target record text is extracted; the second keyword group includes at least one of the following: risk-free nouns, low-risk adjectives, collision verbs, car nouns, vehicle key component nouns, and harmless adjectives.

6. An electronic device, characterized in that, The electronic device includes: At least one processor; and A memory communicatively connected to the at least one processor; wherein, The memory stores a computer program that can be executed by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to perform the text processing method according to any one of claims 1-4.

7. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions that cause a processor to execute the text processing method according to any one of claims 1-4.

Images