A method and device for obtaining comments on a car model fault function of user concern

Abstract

The application discloses a method and device for obtaining user-concerned vehicle model fault function comment. The method for obtaining user-concerned vehicle model fault function comment comprises the following steps: obtaining fault function information and fault category information; obtaining fault function search words and fault category search words; obtaining a fault function comment database, wherein the fault function comment database comprises a plurality of fault function comment description information; and obtaining one or more fault function comment description information in the fault function comment database as user-concerned vehicle model fault function comment information according to the fault function search words and the fault category search words. The application is user-comment-oriented, and the corresponding function is matched by searching for API through the vehicle machine log. Different user-concerned vehicle model fault function comment information is obtained through different vehicle models, and the comment is searched through two dimensions of the fault function information and the fault category information, so that the obtained user-concerned vehicle model fault function comment information is more accurate.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of vehicle fault function maintenance optimization, and particularly relates to a method for obtaining fault function comments of a user-concerned vehicle model and a device for obtaining fault function comments of a user-concerned vehicle model. BACKGROUND

[0002] With the rapid development of the Internet in the 21st century, the number of automobile-related websites and forums has been rapidly increased in an explosive manner, and has become a part of reference for people before purchasing a car in daily life, and also has great commercial space and economic profits and prospects brought by the industrial chain. Before a user decides whether to use or purchase a certain car, the user will carefully measure whether the product can meet their standards and achieve the expected effect. How to more effectively meet the preferences of most users to update and iterate, improve and solve the problems of existing vehicle models, and develop user-satisfactory vehicle models has become a problem that automobile designers focus on.

[0003] Meanwhile, for some fault phenomena and fault functions in different configurations, they are also one of the directions that designers need to focus on, because the higher the configuration of a vehicle model, the more additional functions it has, which means that there are more possible fault phenomena. Therefore, the selection of the vehicle configuration by the user is also considered by the designer, and therefore a method is needed to help the designer analyze and easily obtain comments on the fault function from the vast comments, so as to solve the problem of manual selection by the designer.

[0004] Therefore, it is desirable to have a technical solution to solve or at least alleviate the above-mentioned deficiencies of the prior art. SUMMARY

[0005] The present application aims to provide a method for obtaining fault function comments of a user-concerned vehicle model to at least solve the above-mentioned technical problem.

[0006] In one aspect of the present application, a method for obtaining fault function comments of a user-concerned vehicle model is provided, which comprises:

[0007] obtaining fault function information and fault category information;

[0008] obtaining fault function search terms according to the fault function information;

[0009] obtaining fault category search terms according to the fault category information;

[0010] obtaining a fault function comment database, wherein the fault function comment database comprises a plurality of fault function comment description information;

[0011] According to the fault function keywords and the fault category keywords, one or more fault function comment description information in the fault function comment database is obtained as the user concerned vehicle fault function comment information.

[0012] Optionally, the fault function information obtaining includes:

[0013] A user operation log database is obtained, and the user operation log database includes user operation logs of different users.

[0014] According to the user operation logs of different users, API information that has occurred faults in the user operation logs is obtained.

[0015] According to each obtained API information, corresponding execution action information of each API is obtained.

[0016] A function comparison library is obtained, and the function comparison library includes at least one preset execution action information and fault function information, and one fault function information corresponds to at least one preset execution action information.

[0017] Fault function information corresponding to the preset execution action information same as the execution action information corresponding to each API is obtained.

[0018] Optionally, the fault category information obtaining includes:

[0019] The obtained fault function information is clustered to obtain at least one fault category information.

[0020] Optionally, before the similar information in the multiple fault function comment description information is removed according to the fault function keywords and the fault category keywords to obtain the required fault function comment description information, the method for obtaining the user concerned vehicle fault function comment includes:

[0021] The fault function comment database includes each fault function comment description information is cleaned to delete useless information to obtain cleaned fault function comment description information.

[0022] Optionally, the fault function comment database includes each fault function comment description information is cleaned to delete useless information to obtain cleaned fault function comment description information includes:

[0023] Each fault function comment description information is segmented to obtain a comment sentence.

[0024] It is judged whether each to-be-analyzed sentence meets a preset condition, if yes, then

[0025] The to-be-analyzed sentence meeting the preset condition is obtained as the to-be-analyzed sentence.

[0026] Optionally, the obtaining one or more fault function comment description information in the fault function comment database as the user concerned vehicle model fault function comment information according to the fault function search word and the fault category search word comprises:

[0027] In a keyword matching manner, each to-be-analyzed single sentence is judged according to the fault function search word and the fault category search word, to determine whether the to-be-analyzed single sentence has at least one same word information as the fault function search word and the fault category search word, if yes, the to-be-analyzed single sentence is keyword similar user concerned vehicle model fault function comment information.

[0028] Optionally, the obtaining one or more fault function comment description information in the fault function comment database as the user concerned vehicle model fault function comment information according to the fault function search word and the fault category search word further comprises:

[0029] In a synonym matching manner, each to-be-analyzed single sentence is judged according to the fault function search word and the fault category search word, to determine whether the to-be-analyzed single sentence has at least one synonym word information as the fault function search word and the fault category search word, if yes, the to-be-analyzed single sentence is synonym user concerned vehicle model fault function comment information.

[0030] Optionally, the obtaining one or more fault function comment description information in the fault function comment database as the user concerned vehicle model fault function comment information according to the fault function search word and the fault category search word further comprises:

[0031] In a semantic similarity manner, each to-be-analyzed single sentence is judged according to the fault function search word and the fault category search word, to determine whether at least one word vector of the fault function search word and the fault category search word in the to-be-analyzed single sentence has a similarity exceeding a preset similarity threshold, if yes, the to-be-analyzed single sentence is semantic similar user concerned vehicle model fault function comment information.

[0032] Optionally, the keyword similar user concerned vehicle model fault function comment information, the synonym user concerned vehicle model fault function comment information, and the semantic similar user concerned vehicle model fault function comment information constitute the user concerned vehicle model fault function comment information.

[0033] The method for obtaining user concerned vehicle model fault function comment further comprises:

[0034] Obtaining a vehicle configuration table, the vehicle configuration table comprising at least one vehicle model and preset function information of each vehicle model;

[0035] According to the preset function information, the user-concerned vehicle model fault function comment information is classified, so that the user-concerned vehicle model fault function comment information is at least associated with one vehicle.

[0036] The application further provides a device for obtaining user-concerned vehicle model fault function comments, which comprises:

[0037] a fault function information obtaining module, configured to obtain fault function information;

[0038] a fault category information obtaining module, configured to obtain fault category information;

[0039] a fault function search term obtaining module, configured to obtain a fault function search term according to the fault function information;

[0040] a fault category search term obtaining module, configured to obtain a fault category search term according to the fault category information;

[0041] a database obtaining module, configured to obtain a fault function comment database, wherein the fault function comment database comprises a plurality of fault function comment description information;

[0042] a comment information obtaining module, configured to obtain one or more fault function comment description information in the fault function comment database as user-concerned vehicle model fault function comment information according to the fault function search term and the fault category search term.

[0043] Advantages

[0044] The method for obtaining user-concerned vehicle model fault function comments provided by the application is user comment oriented, API is found through the vehicle machine log to match corresponding functions, different user-concerned vehicle model fault function comment information is obtained through different vehicle models, and the comment is retrieved through two dimensions of fault function information and fault category information, so that the obtained user-concerned vehicle model fault function comment information is more accurate. BRIEF DESCRIPTION OF DRAWINGS

[0045] Figure 1 FIG. 1 is a flowchart of the method for obtaining user-concerned vehicle model fault function comments according to an embodiment of the application.

[0046] Figure 2 FIG. 3 is a schematic diagram of an electronic device capable of implementing the method for obtaining user-concerned vehicle model fault function comments according to an embodiment of the application.

[0047] Figure 3is a clustering algorithm schematic diagram in a method for obtaining user-concerned vehicle model fault function comment according to an embodiment of the present application.

[0048] Figure 4 is a matching and screening algorithm schematic diagram in a vehicle model benchmarking function reference method according to an embodiment of the present application. DETAILED DESCRIPTION

[0049] In order to make the purpose, technical solutions and advantages of the present application clearer, the technical solutions in the embodiments of the present application will be described in more detail below with reference to the drawings. In the drawings, the same or similar notations represent the same or similar elements or elements with the same or similar functions throughout. The described embodiments are some of the embodiments of the present application, not all the embodiments. The embodiments described below with reference to the drawings are exemplary and are intended to explain the present application, and cannot be understood as a limitation of the present application. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative labor fall within the scope of protection of the present application. The embodiments of the present application will be described in detail below with reference to the drawings.

[0050] Figure 1 is a flowchart schematic diagram of a method for obtaining user-concerned vehicle model fault function comment according to an embodiment of the present application.

[0051] As shown in Figure 1 the method for obtaining user-concerned vehicle model fault function comment includes:

[0052] Step 1: obtaining fault function information and fault category information;

[0053] Step 2: obtaining fault function search terms according to the fault function information;

[0054] Step 3: obtaining fault category search terms according to the fault category information;

[0055] Step 4: obtaining a fault function comment database, the fault function comment database including a plurality of fault function comment description information;

[0056] Step 5: obtaining one or more fault function comment description information in the fault function comment database as user-concerned vehicle model fault function comment information according to the fault function search terms and the fault category search terms.

[0057] The method for obtaining comments on faults of a vehicle model focused on by a user provided by the present application is user comment oriented, and finds an API through a vehicle log to match a corresponding function, and obtains different comments on faults of a vehicle model focused on by a user through different vehicle models, and searches for comments through two dimensions of fault function information and fault category information, so that the obtained comments on faults of a vehicle model focused on by a user are more accurate.

[0058] In the present embodiment, obtaining fault function information comprises:

[0059] A user operation log database is obtained, and the user operation log database comprises user operation logs of different users;

[0060] According to the user operation logs of different users, API information that has appeared in the user operation logs is obtained;

[0061] According to each obtained API information, execution action information corresponding to each API is obtained;

[0062] A function matching library is obtained, and the function matching library comprises at least one preset execution action information and fault function information, and one fault function information corresponds to at least one preset execution action information;

[0063] Fault function information corresponding to the preset execution action information that is the same as the execution action information corresponding to each API is obtained.

[0064] For example, when a designer focuses on a function of a vehicle model, it is more necessary to focus on whether a fault function of a vehicle log is used by a user, a time of use, and a frequency of use, etc. If a function is added and not used by a user, development resources and communication costs with various professionals will be wasted. Therefore, we need to analyze a use condition of a user during driving, and thus, we first obtain log information of different users to see which fault function is used.

[0065] Referring to Figure 3 , Figure 3 As an example of a log, it can be seen that the log information comprises each interface information, time information, and frequency information. Each interface represents a function, and parameters are different, and corresponding function meanings are also different. Therefore, we need to extract a corresponding API through a log, and also save a time point. Regular expressions are used to extract:

[0066] API = re.log(r'I')

[0067] Time = re.log(r'date')

[0068] Then, we match a function in a function table through the API, as shown in Table 1:

[0069]

[0070] From the above table, it can be seen that the setting sound effect, obtaining sound effect and setting left-right balance are all preset execution action information.

[0071] The obtaining function reference library (for example, Table 2 below) includes at least one preset execution action information and fault function information, and one fault function information corresponds to at least one preset execution action information.

[0072] Table 2:

[0073]

[0074] From Table 2, it can be seen that the above several preset execution action information correspond to one fault function information, that is, sending music information to the instrument.

[0075] Referring to Figure 3 In this embodiment, the obtaining fault category information includes:

[0076] The obtained fault function information is clustered to obtain at least one fault category information.

[0077] The clustering method is k-mean, which is a similarity-based clustering algorithm for representing vectors of these keywords. Figure 2 This algorithm is described. Initially, it randomly selects k centers, each of which is a vector and represents the center of a cluster. Then, each feature F is assigned to the cluster whose center is closest to v (in vector distance). After that, each centroid is recalculated as the average vector of all keywords assigned to the corresponding cluster. This process is repeated until all clusters are stable, that is, no word is assigned to a cluster different from the current assignment. Because the center is the average vector of each cluster, it can be considered to represent the "common meaning" of the cluster. In the original algorithm, we calculate the vector of the word group in the feature and then cluster. The result is shown in Table 3:

[0078]

[0079] From Table 3, it can be seen that the fault function information of sending music information to the instrument, sending news information, sending Radio information, sending video information and sending navigation information all belong to the fault category information of audio-visual function.

[0080] In the embodiment, the failure function keywords and the failure category keywords are extracted from the failure function information and the failure category information by extracting keywords. For example, navigation information is extracted as a failure category keyword, and video and audio functions are extracted as failure category keywords.

[0081] In the embodiment, before the similar information in the plurality of failure function comment description information is removed according to the failure function keywords and the failure category keywords, and the required failure function comment description information is obtained, the method for obtaining the failure function comment of the vehicle model concerned by the user comprises:

[0082] The failure function comment database is cleaned to delete the useless information, and the cleaned failure function comment description information is obtained.

[0083] For example, in the embodiment, the failure function comment description information of the application is generally a vehicle model description text. The vehicle model description text is a relatively formal text, which describes the function of the car and the experience brought to the user. For the vehicle model description, the useless information needs to be deleted to ensure the integrity of the features.

[0084] The cleaning of the application first performs some preprocessing, for example, sentences describing contact information and subscription information (e-mail address, phone number, membership fee, etc.) and the sentences after them need to be removed. Such sentences usually appear at the end of the description, rather than describing the function of the vehicle model. Excessive punctuation marks, special symbols (such as %, #, @, etc.), emoticons and characters other than Chinese and English are also deleted from the description.

[0085] After the preprocessing is completed, the failure function comment database is cleaned to delete the useless information, and the cleaned failure function comment description information is obtained, comprising:

[0086] Each failure function comment description information is segmented into sentences, and the comment single sentence is obtained;

[0087] It is judged whether each to-be-analyzed single sentence meets the preset condition. If yes, then

[0088] The to-be-analyzed single sentence meeting the preset condition is obtained as the to-be-analyzed single sentence.

[0089] Specifically, the feature function is collected according to the part-of-speech tags of the constituent words in the comment single sentence. Verbs, adjectives and nouns play an important role in defining features. For example, adjectives and nouns are often combined to describe features.

[0090] Therefore we tag the real words and ignore the function words, such as prepositions and auxiliaries. Through the in-depth observation of a large number of application descriptions, especially the differences between the word features of the feature description sentences and the word features of the non-feature description sentences, we define 9 language rules (see Table 1) to capture the feature description sentences. Among them, N.set ∈ {NN, NP, NNS, NNP, NNPS}, V.set ∈ {VB, VBD, VBN, VBG, VBP, VBZ}.

[0091] The first column of Table 4 shows the language rules. Each element in the rule corresponds to the basic form of POS and its variants. In the second column, each rule gives a simple example. We use the Stanford POS Tagger to analyze each sentence and infer the POS tag of each word. Then we apply these nine rules one by one. If a sentence does not meet any of these language rules, it will be filtered out. Otherwise, it will be retained.

[0092] Table 4 Partial rules

[0093]

[0094] In this embodiment, the one or more fault function comment description information in the fault function comment database is obtained as the user concerned vehicle fault function comment information according to the fault function search word and the fault category search word according to the fault function:

[0095] In the keyword matching mode, each single sentence to be analyzed is judged according to the fault function search word and the fault category search word, whether the single sentence to be analyzed has at least one same word information as the fault function search word and the fault category search word, if yes, the single sentence to be analyzed is the keyword similar user concerned vehicle fault function comment information.

[0096] In the synonym matching mode, each single sentence to be analyzed is judged according to the fault function search word and the fault category search word, whether the single sentence to be analyzed has at least one synonym word information as the fault function search word and the fault category search word, if yes, the single sentence to be analyzed is the synonym user concerned vehicle fault function comment information.

[0097] In the semantic similarity mode, each single sentence to be analyzed is judged according to the fault function search word and the fault category search word, whether the single sentence to be analyzed has at least one word vector similarity exceeding a preset similarity threshold value as the fault function search word and the fault category search word, if yes, the single sentence to be analyzed is the semantic similar user concerned vehicle fault function comment information.

[0098] In the embodiment, the keyword similar user attention vehicle model fault function comment information, the synonym user attention vehicle model fault function comment information and the semantic similar user attention vehicle model fault function comment information constitute the user attention vehicle model fault function comment information.

[0099] Referring to Figure 4 In the embodiment, the keyword matching refers to matching at a single word level. If each unit of two feature candidates is equal, they are matched.

[0100] The synonym matching refers to performing a lookup matching feature using a synonym set from WordNet words. In this method, if the terms of two application program features are synonyms, they are considered to be matched. For example, "louver" and "skylight" represent a match. But the first two cannot completely guarantee to cover all feature matches, so in the third step we refer to semantic similarity.

[0101] In the embodiment, the semantic similarity refers to matching by using Word2vec. Specifically, Word2vec is a method of vectorizing text by word embedding, and the similarity degree between words can be judged according to the cosine distance of different word vectors. The greater the cosine value between word vectors, the higher the semantic similarity of two words; the smaller the cosine value between word vectors, the lower the semantic similarity. The numerical value of similarity is sorted and presented to the designer.

[0102] Taking the noun vehicle window as an example, the keyword matching method is used, for example, there are 100 sentences to be analyzed, 10 of which contain vehicle windows, so the 10 sentences are keyword similar user attention vehicle model fault function comment information.

[0103] For another example, in the above 100 sentences to be analyzed, 10 of which contain the noun vehicle window, through the above synonym matching, it is found that the vehicle window and the vehicle window belong to synonyms, so the 10 sentences are synonym user attention vehicle model fault function comment information.

[0104] For another example, in the above 100 sentences to be analyzed, 10 of which contain the noun window, through word vector analysis, it is analyzed that the vector similarity of the vehicle window and the window exceeds a preset similarity threshold, so the 10 sentences are considered to belong to semantic similar user attention vehicle model fault function comment information.

[0105] The above 10 sentences are keyword similar user attention vehicle model fault function comment information, 10 sentences are synonym user attention vehicle model fault function comment information, and 10 sentences belong to semantic similar user attention vehicle model fault function comment information, which constitute the user attention vehicle model fault function comment information.

[0106] In the embodiment, the method for obtaining the user-concerned vehicle model fault function comment further comprises:

[0107] obtaining a vehicle configuration table, the vehicle configuration table comprising at least one vehicle model and preset function information of each vehicle model;

[0108] classifying each user-concerned vehicle model fault function comment information according to the preset function information, so that the user-concerned vehicle model fault function comment information is associated with at least one vehicle.

[0109] For example, different vehicle models have different functions, as shown in Table 5 below:

[0110]

[0111]

[0112] As can be seen from Table 5, the high-end vehicle model has air conditioning function, window function, atmosphere lamp function and language switching function, the low-end vehicle model has air conditioning function, window function and language switching function, and the medium-end vehicle model has air conditioning function and window function. At this time, when the designer needs to analyze the vehicle model that has been determined, the comments on the functions that the vehicle model does not have are not needed.

[0113] For example, if the designer needs to analyze the medium-end vehicle model now, but in the above method, the user-concerned vehicle model fault function comment information corresponding to the fault function of any vehicle model is obtained, for example, 80 pieces of user-concerned vehicle model fault function comment information are obtained, including 20 pieces of information about air conditioning function, 20 pieces of information about window function, 20 pieces of information about atmosphere lamp function, and 20 pieces of information about language switching function. At this time, the medium-end vehicle model is analyzed, which does not have atmosphere lamp function and language switching function, so the user-concerned vehicle model fault function comment information related to the above two functions is removed, so that only 20 pieces of information about air conditioning function and 20 pieces of information about window function are obtained.

[0114] The application also provides a device for obtaining user-concerned vehicle model fault function comment, the device comprising a fault function information acquisition module, a fault category information acquisition module, a fault function keyword acquisition module, a fault category keyword acquisition module, a database acquisition module and a comment information acquisition module, wherein,

[0115] The fault function information acquisition module is used for obtaining fault function information.

[0116] The fault category information acquisition module is used for obtaining fault category information.

[0117] The fault function search term acquisition module is configured to acquire a fault function search term according to the fault function information;

[0118] The fault category search term acquisition module is configured to acquire a fault category search term according to the fault category information;

[0119] The database acquisition module is configured to acquire a fault function comment database, the fault function comment database including a plurality of fault function comment description information;

[0120] The comment information acquisition module is configured to acquire one or more fault function comment description information in the fault function comment database as the user-concerned car model fault function comment information according to the fault function search term and the fault category search term.

[0121] In this embodiment, the fault function comment description information in the fault function comment database is in the form of text, which can be provided by a person or crawled from the Internet by a crawler.

[0122] In this embodiment, the term used to represent the content of the document can be various categories, such as Chinese characters, words, phrases, and even higher-level units such as sentences or groups of sentences. The term can also be a semantic concept class of the corresponding word or phrase.

[0123] The selection of the term must be determined by the specific requirements of processing speed, accuracy, storage space, and the like. There are several principles for selecting feature terms: first, language units that contain more semantic information and have stronger representation capabilities for text should be selected as feature terms; second, the distribution of text on these feature terms should have more obvious statistical regularity, which will be suitable for information retrieval, document classification, and other application systems; third, the feature selection process should be easy to implement, and the time and space complexity should not be too large. In practical applications, words or phrases are often used as feature terms.

[0124] Since the vocabulary is the most basic representation term of the text, it has a high frequency of occurrence in the text and presents certain statistical regularity. Considering the difficulties faced in processing large-scale real text, the vocabulary or phrase is generally selected as the feature term. However, directly selecting the words or phrases in the text as the text feature term will also have the following problems:

[0125] (1) Texts exist in some of the high frequency of the word and the function word, such as Chinese "of", "put", "the" and so on, often some of the real classification of the word is submerged. The solution to this problem is to organize a disabled word list, or in the weight calculation, make their weight is very low, through the threshold value will be discarded. Using the disabled word list, the selection of the word list is very critical, it is difficult to include all the disabled words, and language is constantly developing, the disabled word list is also different with the training text set, a word here is not disabled, to another kind of text may become disabled. On the other hand, considering that the most representative of an article actually meaningful word, often those of the adjective, verb, noun, and the same word, when in different parts of speech, may belong to and not belong to the disabled word list. For example: "he is happy to go" (adverb "place" should be disabled), "the ground is very uneven" (noun "place" should not be disabled). In view of this phenomenon, only the adjectives, verbs and nouns are extracted as feature items, and the disabled word list method is tried to replace.

[0126] (2) The use of words as feature items will also appear so-called synonym phenomenon, synonym phenomenon refers to: for the same thing different people will be based on individual needs, the environment, the level of knowledge and language habits have different ways of expression, so the use of vocabulary also have a lot of difference. So often appear two text used vocabulary have some difference, but in fact the two are similar, this is the word synonym phenomenon caused. For example, computer and computer are the same concept, should belong to the same feature item, the most commonly used solution is to use concept dictionary to solve this problem.

[0127] It can be understood that the above description of the method is also applicable to the description of the device.

[0128] The application also provides an electronic device, comprising a memory, a processor and a computer program stored in the memory and capable of running on the processor, and the processor executes the computer program to realize the above-mentioned method for obtaining user attention car model fault function comment.

[0129] The application also provides a computer readable storage medium, the computer readable storage medium stores a computer program, and the computer program is executed by the processor to realize the above-mentioned method for obtaining user attention car model fault function comment.

[0130] Figure 2 is an exemplary structure diagram of the electronic device capable of realizing the method for obtaining user attention car model fault function comment provided by an embodiment of the application.

[0131] As Figure 2As shown, the electronic device includes an input device 501, an input interface 502, a central processor 503, a memory 504, an output interface 505, and an output device 506. Among them, the input interface 502, the central processor 503, the memory 504, and the output interface 505 are connected to each other through a bus 507, and the input device 501 and the output device 506 are connected to the bus 507 through the input interface 502 and the output interface 505 respectively, and then connected to other components of the electronic device. Specifically, the input device 504 receives input information from the outside, and transmits the input information to the central processor 503 through the input interface 502; the central processor 503 processes the input information based on the computer executable instructions stored in the memory 504 to generate output information, temporarily or permanently stores the output information in the memory 504, and then transmits the output information to the output device 506 through the output interface 505; the output device 506 outputs the output information to the outside of the electronic device for the user to use.

[0132] That is, Figure 2 The electronic device shown can also be implemented to include a memory storing computer executable instructions; and one or more processors which, when executing the computer executable instructions, can implement the method of obtaining user attention vehicle model fault function comment described in combination with Figure 1 The method of obtaining user attention vehicle model fault function comment described.

[0133] In one embodiment, Figure 2 The electronic device shown can be implemented to include a memory 504 configured to store executable program code, and one or more processors 503 configured to run the executable program code stored in the memory 504 to execute the method of obtaining user attention vehicle model fault function comment in the above-described embodiments.

[0134] In a typical configuration, the computing device includes one or more processors (CPUs), input / output interfaces, network interfaces, and memory.

[0135] The memory can include non-persistent memory in computer readable media, random access memory (RAM), and / or non-volatile memory, such as read-only memory (ROM) or flash memory (flash RAM). The memory is an example of computer readable media.

[0136] Computer-readable media includes permanent and non-permanent, movable and non-movable, media can be implemented by any method or technology to store information. Information can be computer-readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, compact disc read-only memory (CD-ROM), digital versatile disc (DVD) or other optical storage, magnetic cassette, magnetic tape disk storage or other magnetic storage devices, or any other non-transmission medium that can be used to store information accessible to a computing device.

[0137] Those skilled in the art will appreciate that embodiments of the present application can be provided as methods, systems or computer program products. Accordingly, the present application can take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application can take the form of a computer program product on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROMs, optical storage devices, etc.) embodying computer-readable program code.

[0138] In addition, it is clear that the word "comprising" does not exclude other units or steps. Multiple units, modules or devices stated in device claims can also be provided by one unit or a total device, by means of software or hardware.

[0139] The flow diagrams and block diagrams in the drawings are schematic illustrations of possible architectures, functions and operations of systems, methods and computer program products in accordance with various embodiments of the present application. In this regard, each block in the flow diagrams and block diagrams can represent a module, a segment, or a portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that in some alternative implementations, the functions noted in the blocks can occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently or the blocks can sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and / or flowchart illustrations, and combinations thereof, can be implemented by special purpose hardware-based systems that perform the specified functions or operations, or combinations of special purpose hardware and computer instructions.

[0140] The processor in this embodiment can be a central processing unit (CPU), and can also be other general-purpose processors, digital signal processors (DSP), application specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gates or transistor logic components, discrete hardware components, or the like. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor.

[0141] The memory can be configured to store computer programs and / or modules, and the processor can be configured to implement various functions of the apparatus / terminal device by running or executing the computer programs and / or modules stored in the memory, and calling data stored in the memory. The memory can mainly include a program storage area and a data storage area, where the program storage area can store operating systems, at least one application program required by a function (such as a sound playing function, an image playing function, etc.), and the like; and the data storage area can store data created according to use of the mobile phone (such as audio data, a phone book, etc.), and the like. In addition, the memory can include a high-speed random access memory, and can also include a nonvolatile memory, for example, a hard disk, a memory, a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, at least one disk storage device, a flash storage device, or other volatile solid-state storage devices.

[0142] In this embodiment, the modules / units integrated in the device / terminal equipment, if realized in the form of software function units and sold or used as independent products, can be stored in a computer readable storage medium. Based on such understanding, the computer program can be used to instruct the related hardware to complete all or part of the processes in the above-mentioned embodiment methods. The computer program can be stored in a computer readable storage medium, and the computer program can realize the steps of the above-mentioned method embodiments when executed by a processor. The computer program includes computer program code, which can be in the form of source code, object code, executable files or some intermediate forms. The computer readable medium can include any entity or device capable of carrying the computer program code, recording medium, U disk, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signal, telecommunication signal and software distribution medium, etc. It should be noted that the content included in the computer readable medium can be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction. Although the above disclosure discloses the preferred embodiments, it is not intended to limit the application. Any possible changes and modifications made by those skilled in the art without departing from the spirit and scope of the application should be included in the protection scope of the application. The protection scope of the application should be subject to the scope defined by the claims of the application.

[0143] Those skilled in the art will appreciate that embodiments of the application can be a method, a system or a computer program product. Accordingly, the application can take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the application can take the form of a computer program product on one or more computer readable storage media (including, but not limited to, disk memory, CD-ROM, optical storage medium, etc.) having computer usable program code contained therein.

[0144] In addition, it is clear that the word "comprising" does not exclude other units or steps. The plurality of units, modules or devices stated in the device claims can also be implemented by one unit or a total device through software or hardware.

[0145] Although the application has been described in detail above with specific reference to the preferred embodiments, it will be understood by those skilled in the art that various changes and modifications can be made without departing from the spirit and scope of the application. Therefore, these changes and modifications should be included in the protection scope of the application.

Claims

1. A method for obtaining a user's attention to a model failure function comment, characterized by, The method for obtaining the fault function comment of the user concerned vehicle model comprises the following steps: Obtaining fault function information and fault category information; Obtaining fault function search words according to the fault function information; Obtaining fault category search words according to the fault category information; Obtaining a fault function comment database, wherein the fault function comment database comprises a plurality of fault function comment description information; Obtaining one or more fault function comment description information in the fault function comment database as the fault function comment information of the user concerned vehicle model according to the fault function search words and the fault category search words; The step of obtaining the fault function information comprises the following steps: Obtaining a user operation log database, wherein the user operation log database comprises user operation logs of different users; Obtaining API information that has appeared in the user operation logs according to the user operation logs of different users; Obtaining execution action information corresponding to each API according to each obtained API information; Obtaining a function comparison library, wherein the function comparison library comprises at least one preset execution action information and fault function information, and one fault function information corresponds to at least one preset execution action information; Obtaining fault function information corresponding to the preset execution action information which is the same as the execution action information corresponding to each API. 2.The method of claim 1, wherein, The step of obtaining the fault category information comprises the following steps: Clustering each obtained fault function information, thereby obtaining at least one fault category information. 3.The method of claim 2, wherein, Before the step of eliminating similar information in the plurality of fault function comment description information according to the fault function search words and the fault category search words, thereby obtaining the required fault function comment description information, the method for obtaining the fault function comment of the user concerned vehicle model comprises the following steps: Cleaning each fault function comment description information in the fault function comment database, deleting useless information, thereby obtaining cleaned fault function comment description information.

4. The method of claim 3, wherein the acquiring of the user attention car model malfunction function comment is characterized by, The step of cleaning each fault function comment description information in the fault function comment database, deleting useless information, thereby obtaining cleaned fault function comment description information comprises the following steps: Dividing each fault function comment description information into sentences, thereby obtaining comment single sentences; Judging whether each to-be-analyzed single sentence meets a preset condition, if yes, then Obtaining the to-be-analyzed single sentence meeting the preset condition as a to-be-analyzed single sentence.

5. The method of claim 4, wherein the acquiring of the user attention car model malfunction function comment is characterized by, The step of obtaining one or more fault function comment description information in the fault function comment database as the fault function comment information of the user concerned vehicle model according to the fault function search words and the fault category search words comprises the following steps: Adopting a keyword matching mode, judging each to-be-analyzed single sentence according to the fault function search words and the fault category search words, judging whether the to-be-analyzed single sentence has at least one same word information as the fault function search words and the fault category search words, if yes, then the to-be-analyzed single sentence is the keyword similar fault function comment information of the user concerned vehicle model.

6. The method of claim 5, wherein the acquiring of the user attention car model malfunction function comment is characterized by, The step of obtaining one or more fault function comment description information in the fault function comment database as the fault function comment information of the user concerned vehicle model according to the fault function search words and the fault category search words further comprises the following steps: The same word matching manner is adopted to judge each single sentence to be analyzed according to the fault function search words and the fault category search words, to determine whether the single sentence to be analyzed has word information that is synonymous with at least one of the fault function search words and the fault category search words, and if so, the single sentence to be analyzed is the same word user concerned vehicle fault function comment information.

7. The method of claim 6, wherein the acquiring a user attention model vehicle malfunction function review function comprises: The fault function comment database is further obtained according to the fault function search words and the fault category search words to obtain one or more fault function comment description information as the user concerned vehicle fault function comment information. The semantic similarity manner is adopted to judge each single sentence to be analyzed according to the fault function search words and the fault category search words, to determine whether at least one word vector of the fault function search words and the fault category search words in the single sentence to be analyzed has a similarity exceeding a preset similarity threshold, and if so, the single sentence to be analyzed is the semantic similar user concerned vehicle fault function comment information. 8.The method of claim 7, wherein, The keyword similar user concerned vehicle fault function comment information, the same word user concerned vehicle fault function comment information, and the semantic similar user concerned vehicle fault function comment information constitute the user concerned vehicle fault function comment information. The method for obtaining the user concerned vehicle fault function comment further comprises: Obtaining a vehicle configuration table, the vehicle configuration table comprising at least one vehicle type and preset function information of each vehicle type; Classifying each user concerned vehicle fault function comment information according to the preset function information, so that one user concerned vehicle fault function comment information has an associated relationship with at least one vehicle.

9. An apparatus for acquiring a user attention car model malfunction function review, characterized by, The device for obtaining the user concerned vehicle fault function comment comprises: A fault function information obtaining module, configured to obtain fault function information, and the fault function information obtaining comprises: Obtaining a user operation log database, the user operation log database comprising user operation logs of different users; Obtaining API information that has appeared in the user operation logs according to the user operation logs of different users; Obtaining execution action information corresponding to each API according to each obtained API information; Obtaining a function reference library, the function reference library comprising at least one preset execution action information and fault function information, one fault function information corresponding to one preset execution action information; Obtaining fault function information corresponding to the same preset execution action information as the execution action information corresponding to each API; A fault category information obtaining module, configured to obtain fault category information; A fault function search word obtaining module, configured to obtain fault function search words according to the fault function information; A fault category search word obtaining module, configured to obtain fault category search words according to the fault category information; A database obtaining module is configured to obtain a failure function comment database, which includes a plurality of failure function comment description information. A comment information obtaining module is configured to obtain one or more failure function comment description information in the failure function comment database as the user concerned vehicle failure function comment information according to the failure function search term and the failure category search term.

Images