A text processing method, apparatus, device and medium

Abstract

The application discloses a text processing method, device and equipment and medium. The method comprises the following steps: determining a target running log from at least two candidate running logs according to the recording time of the running log; performing feature extraction on the target running log based on a preset matching rule, determining a target vehicle function associated with each target running log, and obtaining a keyword group associated with the target vehicle function; determining a target comment text from the at least two candidate comment texts according to a semantic extraction result obtained by performing semantic extraction on the at least two candidate comment texts and the keyword group associated with the target vehicle function; and performing visual display on the target comment text according to the semantic extraction result of the target comment text. According to the technical scheme of the application, the comment text can be processed and the feature information thereof can be visualized according to the running log, so that relevant personnel can improve product quality.

Description

Technical Field

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

[0002] Vehicle operation logs and comment texts contain a wealth of valuable information. In-depth analysis of the text content and extraction of commentary viewpoints can provide guidance for product research, planning, development, as well as the analysis and early warning of frequent failures.

[0003] How to selectively filter comment texts based on operational logs and visualize their characteristic information so that relevant personnel can improve product quality in a targeted manner is a problem that urgently needs to be solved. Summary of the Invention

[0004] This invention provides a text processing method, apparatus, device, and medium that can process comment text in a targeted manner based on operation logs and visualize its feature information, making it easier for relevant personnel to improve product quality in a targeted way.

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

[0006] The target operation log is determined from at least two candidate operation logs based on the recording time of the operation log; the operation log is a log that records the usage of vehicle service functions during vehicle operation.

[0007] Based on preset matching rules, feature extraction is performed on the target operation logs to determine the target vehicle functions associated with each target operation log, and keyword groups associated with the target vehicle functions are obtained.

[0008] Based on the semantic extraction results obtained from semantic extraction of at least two candidate comment texts, and the keyword groups associated with the target vehicle function, the target comment text is determined from at least two candidate comment texts; the comment text is a text that comments on the vehicle service function.

[0009] Based on the semantic extraction results of the target comment text, the target comment text is visualized.

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

[0011] The log determination module is used to determine the target running log from at least two candidate running logs based on the recording time of the running log; the running log is a log that records the usage of vehicle service functions during vehicle operation;

[0012] The phrase acquisition module is used to extract features from the target operation logs based on preset matching rules, determine the target vehicle functions associated with each target operation log, and acquire the keyword phrases associated with the target vehicle functions.

[0013] The text determination module is used to determine the target comment text from at least two candidate comment texts based on the semantic extraction results obtained by semantic extraction of at least two candidate comment texts and the keyword group associated with the target vehicle function; the comment text is a text that comments on the vehicle service function;

[0014] The display module is used to visualize the target comment text based on the semantic extraction results of the target comment text.

[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 a target operation log from at least two candidate operation logs based on the recording time of the operation log. Based on preset matching rules, feature extraction is performed on the target operation log to determine the target vehicle function associated with each target operation log, and keyword groups associated with the target vehicle function are obtained. Based on the semantic extraction results obtained from semantic extraction of at least two candidate comment texts, and the keyword groups associated with the target vehicle function, a target comment text is determined from at least two candidate comment texts. Finally, the target comment text is visualized based on the semantic extraction results of the target comment text. In this way, comment texts can be processed in a targeted manner based on the operation logs, determining the comment text associated with the vehicle service function corresponding to the operation log, and visualizing its feature information, enabling relevant personnel to improve product quality in a targeted manner.

[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 flowchart of a text processing method provided in Embodiment 2 of the present invention;

[0025] Figure 3 This is a flowchart of a text processing method provided in Embodiment 3 of the present invention;

[0026] Figure 4 This is a structural diagram of the text processing device provided in Embodiment 4 of the present invention;

[0027] Figure 5 This is a schematic diagram of the structure of the electronic device provided in Embodiment 5 of the present invention. Detailed Implementation

[0028] 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.

[0029] 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.

[0030] Example 1

[0031] Figure 1 This is a flowchart of a text processing method provided in Embodiment 1 of the present invention. This embodiment is applicable to processing comment text about car service functions. 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:

[0032] S101. Determine the target running log from at least two candidate running logs based on the recording time of the running log.

[0033] The operation log records the usage of vehicle service functions during vehicle operation. Vehicle service functions refer to pre-configured functions on the vehicle, specifically including ambient lighting, fragrance, and entry / exit assistance functions. Entry / exit assistance functions control the steering wheel and seat to assist with getting in and out of the vehicle. Recording time refers to the time the operation log is recorded. Specifically, recording time can include the recording time of related information for each vehicle service function in the operation log. For example, for the ambient lighting function, the recording time can include the configuration time of related functions such as ambient lighting activation, activation area, color, and brightness selection. Candidate operation logs refer to logs from all time periods during vehicle operation. Target operation logs refer to the candidate operation logs whose recording time meets preset conditions.

[0034] Optionally, at least two logs recording the usage of vehicle service functions during vehicle operation can be obtained, i.e., at least two candidate operation logs can be obtained. These candidate logs are then matched against a preset time regular expression to determine the recording time of each candidate log. For example, the time regular expression could be "Time=re.log(r'date')".

[0035] Optionally, candidate logs whose recording times fall within a preset time range can be selected as the target running logs based on their recording times. In other words, the target running log is determined from at least two candidate running logs based on their recording times. The preset time range could be, for example, one month.

[0036] S102. Based on the preset matching rules, extract features from the target operation logs, determine the target vehicle functions associated with each target operation log, and obtain the keyword groups associated with the target vehicle functions.

[0037] The matching rule refers to the preset matching rules for feature extraction from the target operation log. The matching rule can be a preset regular expression used for feature matching. The target vehicle function refers to the vehicle service functions recorded in the target log that can represent user attention levels exceeding a certain threshold. A phrase can include at least one of the following: adjectives, verbs, and nouns. Specifically, a phrase can include at least one word.

[0038] Keyword groups refer to phrases that relate to the functions of a target vehicle. For example, for the ambient lighting function, keyword groups can include phrases that describe the activation area, color, and brightness of the ambient lighting; for the fragrance function, keyword groups can be phrases that describe the different fragrances and concentrations selected by the user, or phrases that describe user-defined fragrances; for the vehicle's entry and exit assistance function, keyword groups can be phrases that describe the steering wheel and seat-related actions when the user gets in and out of the vehicle, such as the steering wheel retracting and the seat moving backward when getting in and out of the vehicle, and the steering wheel and seat returning to their original positions after getting in.

[0039] Optionally, after determining the target operation log, features can be extracted from the relevant parameter information of the vehicle service functions recorded in the target operation log based on preset matching rules. Based on the extracted relevant parameter information, the target vehicle functions associated with each target operation log and the keyword groups associated with each target vehicle function can be determined.

[0040] S103. Based on the semantic extraction results obtained from semantic extraction of at least two candidate comment texts, and the keyword groups associated with the target vehicle function, determine the target comment text from at least two candidate comment texts.

[0041] The comment text refers to text that comments on vehicle service functions. Candidate comment text refers to comment text obtained in advance from automotive websites or forums. Target comment text refers to the comment text among the candidate comment texts that is associated with the target vehicle function. The semantic extraction results may include functional phrases and descriptive information extracted from the comment text.

[0042] Optionally, semantic extraction can be performed on each candidate comment text according to at least two pre-set semantic extraction rules to determine the functional phrases and descriptive information of the candidate comment text, and the functional phrases and descriptive information can be determined as the semantic extraction results of the candidate comment text.

[0043] Optionally, the semantic extraction results obtained by semantic extraction of at least two candidate comment texts can be obtained, and the similarity between the semantic extraction results and the keyword groups associated with the target vehicle function can be determined. If the similarity meets the preset conditions, the candidate comment text corresponding to the semantic extraction result is determined as the target comment text, that is, the target comment text is determined from at least two candidate comment texts.

[0044] Optionally, candidate comment text containing the keyword phrase can be directly identified as target comment text. Specifically, the order of words in the candidate comment text can be ignored; if all words contained in the keyword phrase are detected in the candidate comment text, then the candidate comment text is identified as the target comment text. For example, if the candidate comment text contains "connect bluetooth" and the keyword phrase contains "bluetooth connect", then the candidate comment text matches the keyword phrase, and in this case, the candidate comment text is identified as the target comment text.

[0045] Optionally, candidate comment texts containing keyword phrases and synonyms can also be included as target comment texts. The keyword phrases and synonyms can be pre-defined.

[0046] S104. Based on the semantic extraction results of the target comment text, visualize the target comment text.

[0047] Optionally, based on preset rules, the functional phrases and descriptive information in the semantic extraction results can be visualized. Specifically, based on the semantic extraction results of the target comment text, the target comment text can be visualized, including: determining the descriptive information and functional phrases of the target comment text based on the semantic extraction results of the target comment text; using the descriptive information as a label for the corresponding functional phrases, and visualizing the target comment text.

[0048] Optionally, the semantic extraction results of the target comment text can be extracted from the semantic extraction results obtained from semantic extraction of at least two candidate comment texts, and the descriptive information and functional phrases of the target comment text can be further determined based on the semantic extraction results of the target comment text.

[0049] It should be noted that the embodiments of the present invention can identify the vehicle service functions that need attention from the vehicle's operation log, further identify the text evaluating the vehicle service functions that need attention from the candidate comment text, and visualize the relevant information of the text. This helps relevant personnel (such as the designers of vehicle service functions) to understand the service functions that need to be added or improved during vehicle operation, and improve product quality in a targeted manner.

[0050] The technical solution of this invention involves determining a target operation log from at least two candidate operation logs based on the recording time of the operation log. Based on preset matching rules, feature extraction is performed on the target operation log to determine the target vehicle function associated with each target operation log, and keyword groups associated with the target vehicle function are obtained. Based on the semantic extraction results obtained from semantic extraction of at least two candidate comment texts, and the keyword groups associated with the target vehicle function, a target comment text is determined from at least two candidate comment texts. Finally, the target comment text is visualized based on the semantic extraction results of the target comment text. In this way, comment texts can be processed in a targeted manner based on the operation logs, determining the comment text associated with the vehicle service function corresponding to the operation log, and visualizing its feature information, enabling relevant personnel to improve product quality in a targeted manner.

[0051] Example 2

[0052] Figure 2 This is a flowchart of a text processing method provided in Embodiment 2 of the present invention. Based on the above embodiments, this embodiment further explains in detail the process of "extracting features from target operation logs based on preset matching rules to determine the target vehicle functions associated with each target operation log," as follows: Figure 2 As shown, the method includes:

[0053] S201. Determine the target running log from at least two candidate running logs based on the recording time of the running log.

[0054] S202. Based on preset matching rules, extract features from the target operation logs to determine the candidate vehicle functions associated with each target operation log.

[0055] Among them, candidate vehicle functions refer to all vehicle service functions recorded in the target operation log.

[0056] Optionally, based on preset matching rules, feature extraction is performed on the target operation logs to determine the candidate vehicle functions associated with each target operation log. This includes: based on preset matching rules, feature extraction is performed on the target operation logs to determine the function functions associated with the target operation logs; the application programming API interface corresponding to the function function is used as the function interface, and the candidate vehicle functions associated with each target operation log are determined according to the function interface and the preset one-to-one correspondence between the function interface and the vehicle service function.

[0057] Functional functions are used to instruct the execution of corresponding vehicle service functions. These functions can include sound effect setting functions, sound effect acquisition functions, and left / right balance setting functions, among others. A sound effect setting function can be represented as `setSoundEffectMode(int mode)`, a sound effect acquisition function as `int getSoundEffectMode()`, and a left / right balance setting function as `setBalance(int value)`. Different parameters in the functional functions result in different vehicle service executions. Different functional interfaces represent different vehicle service functions; these functions can be used to call functional interfaces to implement the corresponding vehicle service functions. Functional interfaces can be Application Programming Interfaces (APIs).

[0058] Optionally, features can be extracted from the target runtime log using a preset interface regular expression, such as "API=re.log(r'I')", and the extracted functional functions can be identified as the functional functions associated with the target runtime log. In other words, features are extracted from the target runtime log based on preset matching rules to determine the functional functions associated with the target runtime log.

[0059] S203. Based on the frequency of the candidate vehicle functions appearing in the target operation logs, determine the target vehicle functions from the candidate vehicle functions and obtain the keyword groups associated with the target vehicle functions.

[0060] The frequency with which a candidate vehicle function appears in the target operation log can characterize the frequency with which the candidate vehicle service function is used, that is, the user's attention to the candidate vehicle function.

[0061] Optionally, the frequency of each candidate vehicle function appearing in each target operation log can be counted. If the frequency of a candidate vehicle function is higher than a preset frequency threshold, then the candidate vehicle function is determined to be the target vehicle function.

[0062] Optionally, the target vehicle function is determined from the candidate vehicle functions based on their frequency of occurrence in each target operation log. This includes: ranking the candidate vehicle functions according to their frequency of occurrence and determining the candidate vehicle functions corresponding to the preset order as the target vehicle functions. For example, the five candidate vehicle functions with the highest frequency of occurrence can be determined as the target vehicle functions.

[0063] Optionally, after determining the target vehicle function, you can query the one-to-one correspondence between the pre-stored vehicle functions and their common keyword groups to determine the keyword group corresponding to the target vehicle function.

[0064] S204. Based on the semantic extraction results obtained from semantic extraction of at least two candidate comment texts, and the keyword groups associated with the target vehicle function, determine the target comment text from at least two candidate comment texts.

[0065] S205. Based on the semantic extraction results of the target comment text, visualize the target comment text.

[0066] The technical solution of this invention, after determining the target operation log, extracts features from the target operation log based on preset matching rules to determine candidate vehicle functions associated with each target operation log. Based on the frequency of occurrence of candidate vehicle functions in each target operation log, the target vehicle function is determined from the candidate vehicle functions, and the keyword groups associated with the target vehicle function are obtained. Finally, the target comment text is determined and visualized. This method provides an feasible way to determine the target vehicle function, accurately identifying the vehicle function with the highest attention and usage frequency from all candidate vehicle functions in the operation log, which helps in the subsequent screening of candidate comment text.

[0067] Example 3

[0068] Figure 3 This is a flowchart of a text processing method provided in Embodiment 3 of the present invention. Based on the above embodiments, this embodiment further explains in detail the process of "determining the target comment text from at least two candidate comment texts based on the semantic extraction results obtained from semantic extraction of at least two candidate comment texts and the keyword groups associated with the target vehicle function." Figure 3 As shown, the method includes:

[0069] S301. Determine the target running log from at least two candidate running logs based on the recording time of the running log.

[0070] S302. Based on preset matching rules, extract features from the target operation logs, determine the target vehicle functions associated with each target operation log, and obtain the keyword groups associated with the target vehicle functions.

[0071] S303. Obtain the semantic extraction results obtained by semantic extraction of at least two candidate comment texts, and determine the functional word groups and descriptive information of the functional word groups in the semantic extraction results of the candidate comment texts.

[0072] In this context, "functional phrases" refer to phrases in the commentary text that characterize the vehicle's functions. Functional phrases can be in the form of a single noun, two nouns, a verb + noun, or a noun + gerund, etc. Descriptive information refers to information that describes the vehicle's functions as characterized by the functional phrases.

[0073] Optionally, semantic extraction can be performed on at least two candidate comment texts according to preset semantic extraction rules to obtain semantic extraction results, and the functional word groups and descriptive information of each candidate comment text can be determined based on the semantic extraction results.

[0074] For example, for the candidate comment text "The skylight should be more wide", the function phrase "skylight" and the description "wide" can be determined based on the preset semantic extraction rule "noun + function phrase + demand word 'should be' + adjective + descriptive information". For the candidate comment text "Next update please add seat heating", the function phrase "seat heating" and the description "none" can be determined based on the preset semantic extraction rule "please add + function phrase + descriptive information". For the candidate comment text "I look forward to different scents", the function phrase "scents" and the description "different" can be determined based on the preset semantic extraction rule "look forward to + adjective description + noun function phrase". For the candidate comment text "I want to choose music locally while driving", the function phrase "choose music" and the description "locally" can be determined based on the preset semantic extraction rule "want to + (noun + verb, or verb + noun) function phrase + descriptive information".

[0075] S304. Based on the semantic similarity of functional phrases and keyword phrases, determine the target comment text from at least two candidate comment texts.

[0076] Optionally, based on preset rules, the semantic similarity value of functional phrases and keyword phrases can be determined. If the semantic similarity value is greater than the preset similarity threshold, the candidate comment text corresponding to the functional phrase is considered to correspond to the target vehicle function corresponding to the keyword phrase, and the candidate comment text corresponding to the functional phrase is determined to be the target comment text. Alternatively, some common similar phrases can be pre-stored. If the functional phrase and keyword phrase are a common similar phrase, the candidate comment text corresponding to the functional phrase can be directly determined to be the target comment text.

[0077] For example, description and review features are common similar phrases, addpanorama image and increase full-disk image are common similar phrases, and beautiful appearance and excellent aspect are common similar phrases.

[0078] Optionally, the target comment text is determined from at least two candidate comment texts based on the semantic similarity of the functional phrases and keyword phrases, including: determining the semantic similarity of the functional phrases and keyword phrases based on a vector space model and using a similarity measure based on cosine distance.

[0079] Among them, the vector space model (SVM) is used to convert functional phrases and keyword phrases into vector form.

[0080] Optionally, phrases and keyword groups in the comment text can be converted into vector form based on a vector space model.

[0081] Optionally, the inner product of the vectors of the functional phrases and the keyword phrases can be used to determine the semantic similarity between the functional phrases and the keyword phrases; alternatively, the cosine distance between the vectors of the functional phrases and the keyword phrases can be used to determine the semantic similarity between the functional phrases and the keyword phrases.

[0082] S305. Based on the semantic extraction results of the target comment text, visualize the target comment text.

[0083] The technical solution of this invention involves obtaining semantic extraction results from at least two candidate comment texts, determining the functional word groups and descriptive information of the functional word groups in the candidate comment texts, determining the target comment text from the at least two candidate comment texts based on the semantic similarity of the functional word groups and keyword groups, and finally visualizing the target comment text. By determining the target comment text from at least two candidate comment texts based on the keyword groups of the target vehicle function, the comment text corresponding to the vehicle function with the highest attention and most frequent use can be obtained, which helps relevant personnel to improve product quality in a targeted manner.

[0084] Example 4

[0085] Figure 4 This is a structural diagram of the text processing device provided in Embodiment 4 of the present invention; the text processing device provided in the embodiments 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.

[0086] like Figure 4 As shown, the device includes:

[0087] The log determination module 401 is used to determine the target running log from at least two candidate running logs based on the recording time of the running log; the running log is a log that records the usage of vehicle service functions during vehicle operation;

[0088] The phrase acquisition module 402 is used to extract features from the target operation logs based on preset matching rules, determine the target vehicle functions associated with each target operation log, and acquire the keyword phrases associated with the target vehicle functions.

[0089] The text determination module 403 is used to determine the target comment text from at least two candidate comment texts based on the semantic extraction results obtained by semantic extraction of at least two candidate comment texts and the keyword group associated with the target vehicle function; the comment text is a text that comments on the vehicle service function;

[0090] The display module 404 is used to visualize the target comment text based on the semantic extraction results of the target comment text.

[0091] The technical solution of this invention involves determining a target operation log from at least two candidate operation logs based on the recording time of the operation log. Based on preset matching rules, feature extraction is performed on the target operation log to determine the target vehicle function associated with each target operation log, and keyword groups associated with the target vehicle function are obtained. Based on the semantic extraction results obtained from semantic extraction of at least two candidate comment texts, and the keyword groups associated with the target vehicle function, a target comment text is determined from at least two candidate comment texts. Finally, the target comment text is visualized based on the semantic extraction results of the target comment text. In this way, comment texts can be processed in a targeted manner based on the operation logs, determining the comment text associated with the vehicle service function corresponding to the operation log, and visualizing its feature information, enabling relevant personnel to improve product quality in a targeted manner.

[0092] Furthermore, the phrase acquisition module 402 may include:

[0093] The candidate function determination unit is used to extract features from the target operation logs based on preset matching rules and determine the candidate vehicle functions associated with each target operation log.

[0094] The target function determination unit is used to determine the target vehicle function from the candidate vehicle functions based on the frequency of their occurrence in each target operation log.

[0095] Furthermore, the candidate function determination unit is specifically used for:

[0096] Based on preset matching rules, feature extraction is performed on the target operation log to determine the associated functional function; wherein, the functional function is used to instruct the execution of the corresponding vehicle service function;

[0097] The application programming API interface corresponding to the function is used as the function interface, and the candidate vehicle function associated with each target operation log is determined based on the function interface and the preset one-to-one correspondence between the function interface and the vehicle service function.

[0098] Furthermore, the target function determination unit is specifically used for:

[0099] Based on the frequency of occurrence of each candidate vehicle function, the candidate vehicle functions are ranked, and the candidate vehicle functions corresponding to the preset order are determined as the target vehicle functions.

[0100] Furthermore, the text determination module 403 may include:

[0101] The semantic information determination unit is used to obtain the semantic extraction results obtained by semantic extraction of at least two candidate comment texts, and to determine the functional word groups and descriptive information of the functional word groups in the semantic extraction results of the candidate comment texts;

[0102] The target text determination unit is used to determine the target comment text from at least two candidate comment texts based on the semantic similarity between the functional word group and the keyword group.

[0103] Furthermore, the text determination module 403 is also used for:

[0104] Based on the vector space model, the semantic similarity between the functional word group and the keyword group is determined using a similarity metric based on cosine distance.

[0105] Furthermore, the display module 404 is specifically used for:

[0106] Based on the semantic extraction results of the target comment text, the descriptive information and functional word groups of the target comment text are determined;

[0107] The descriptive information is used as a tag for the corresponding functional phrases to visualize the target comment text.

[0108] It should be noted that the acquisition, storage, and application of user personal 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.

[0109] Example 5

[0110] Figure 5 This is a schematic diagram of the structure of the electronic device provided in Embodiment 5 of the present invention. Figure 5 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.

[0111] like Figure 5As 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 may 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.

[0112] 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.

[0113] 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.

[0114] 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).

[0115] 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.

[0116] Computer programs used to implement the methods of the present invention can be written in any combination of one or more programming languages. These computer programs can 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 implemented. The computer programs can be executed entirely on a machine, partially on a machine, as a standalone software package partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0117] 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.

[0118] 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).

[0119] 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.

[0120] 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.

[0121] 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.

[0122] 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.

Claims

1. A text processing method characterized by, The method comprises the following steps: determining a target running log from at least two candidate running logs according to the recording time of the running log; the running log is a log recording the use of vehicle service functions during vehicle operation; based on the preset matching rule, the target running log is extracted, the target vehicle function associated with each target running log is determined, and the keyword group associated with the target vehicle function is obtained; determining a target comment text from at least two candidate comment texts according to the semantic extraction result obtained by performing semantic extraction on the at least two candidate comment texts; the comment text is a text commenting on the vehicle service function; visualizing the target comment text according to the semantic extraction result of the target comment text; based on the preset matching rule, the target running log is extracted, and the candidate vehicle function associated with each target running log is determined, comprising: based on the preset matching rule, the target running log is extracted, and the function function associated with the target running log is determined; wherein the function function is used to indicate the execution of the corresponding vehicle service function; the application programming API interface corresponding to the function function is taken as a function interface, and according to the function interface and the one-to-one correspondence between the preset function interface and the vehicle service function, the candidate vehicle function associated with each target running log is determined; determining a target comment text from at least two candidate comment texts according to the semantic extraction result obtained by performing semantic extraction on the at least two candidate comment texts, comprising: obtaining the semantic extraction result obtained by performing semantic extraction on the at least two candidate comment texts, and determining the function word group and the description information of the function word group of the candidate comment text in the semantic extraction result; determining a target comment text from at least two candidate comment texts according to the semantic similarity between the function word group and the keyword group; based on the vector space model, the semantic similarity between the function word group and the keyword group is determined by using the similarity measurement method based on cosine distance.

2. The method of claim 1, wherein, based on the preset matching rule, the target running log is extracted, and the target vehicle function associated with each target running log is determined, comprising: based on the preset matching rule, the target running log is extracted, and the candidate vehicle function associated with each target running log is determined; determining the target vehicle function from the candidate vehicle function according to the frequency of the candidate vehicle function appearing in each target running log.

3. The method of claim 2, wherein, determining the target vehicle function from the candidate vehicle function according to the frequency of the candidate vehicle function appearing in each target running log, comprising: ranking each candidate vehicle function according to the frequency of its appearance, and determining the candidate vehicle function corresponding to the preset order as the target vehicle function.

4. The method of claim 1, wherein, visualizing the target comment text according to the semantic extraction result of the target comment text, comprising: determining the description information and the function word group of the target comment text according to the semantic extraction result of the target comment text; The description information is taken as a label of a corresponding function phrase, and the target review text is visually displayed.

5. A text processing apparatus characterized by comprising: Comprise: The log determination module is used for determining the target running log from at least two candidate running logs according to the recording time of the running log; The running log is a log for recording the use of vehicle service functions during vehicle operation; The phrase acquisition module is used for extracting features of the target running log based on a preset matching rule, determining a target vehicle function associated with each target running log, and acquiring a keyword phrase associated with the target vehicle function; The text determination module is used for determining a target review text from at least two candidate review texts according to a semantic extraction result obtained by performing semantic extraction on the at least two candidate review texts and the keyword phrase associated with the target vehicle function; the review text is a text for commenting on the vehicle service function; The display module is used for visually displaying the target review text according to the semantic extraction result of the target review text; The phrase acquisition module comprises a candidate function determination unit; The candidate function determination unit is specifically used for: Based on a preset matching rule, the target running log is extracted, and the function function associated with the target running log is determined; wherein the function function is used to indicate the execution of the corresponding vehicle service function; The application programming API interface corresponding to the function function is taken as a function interface, and according to the function interface and a preset one-to-one correspondence between the function interface and the vehicle service function, the candidate vehicle function associated with each target running log is determined; The text determination module comprises: The semantic information determination unit is used for acquiring a semantic extraction result obtained by performing semantic extraction on at least two candidate review texts, and determining the function phrase and the description information of the function phrase of the candidate review text in the semantic extraction result; The target text determination unit is used for determining a target review text from at least two candidate review texts according to the semantic similarity of the function phrase and the keyword phrase; The text determination module is also used for: Based on the vector space model, the similarity measurement method based on the cosine distance is used to determine the semantic similarity of the function phrase and the keyword phrase.

6. An electronic device, comprising: The electronic device comprises: At least one processor; and The memory is connected in communication with the at least one processor; wherein The memory stores a computer program that can be executed by the at least one processor, and the computer program is executed by the at least one processor to enable the at least one processor to execute the text processing method in any one of claims 1-4.

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

Images