Method, device and equipment for determining difference of attention of each function of automobile and storage medium

Abstract

The application discloses a kind of each function of car attention difference determination method, device, equipment and storage medium.The method comprises: obtaining at least two description texts and at least two comment texts corresponding to target vehicle;Each of the description text is extracted to obtain the first feature set containing at least one set description feature by setting description feature, and each comment text is extracted to obtain the second feature set containing at least one set comment feature by setting comment feature;Each of the second feature set is matched with each of the first feature set, and the count value corresponding to the first feature set corresponding to the matching success result is updated;The count value corresponding to all first feature sets is sorted, and the attention degree of user to the function corresponding to each of the first feature set is determined according to the sorting result.The existing car function determination method cannot simultaneously determine the attention difference between each function of car based on description text and comment text.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of text processing, and in particular to a method and device for determining differences in attention to functions of a vehicle, an apparatus, and a storage medium. BACKGROUND

[0002] Since the sentence structure of the description text used to describe the functions of the vehicle and the sentence structure of the review text used to review the functions of the vehicle are different, the existing vehicle function determination method either targets user reviews to identify user complaints or requests to understand the expected functions of consumers, or studies vehicle descriptions to identify the functions of other vehicle products in the current market.

[0003] Therefore, the existing vehicle function determination method cannot simultaneously determine the differences in attention between the functions of the vehicle based on the description text and the review text. SUMMARY

[0004] The present application provides a method and device for determining differences in attention to functions of a vehicle, an apparatus, and a storage medium, to solve the problem that the existing vehicle function determination method cannot simultaneously determine the differences in attention between the functions of the vehicle based on the description text and the review text.

[0005] According to an aspect of the present application, a method for determining differences in attention to functions of a vehicle is provided, the method comprising:

[0006] obtaining at least two description texts and at least two review texts corresponding to a target vehicle, different description texts corresponding to different function descriptions, and the review texts corresponding to function reviews;

[0007] performing set description feature extraction on each of the description texts to obtain a first feature set containing at least one set description feature;

[0008] performing set review feature extraction on each of the review texts to obtain a second feature set containing at least one set review feature;

[0009] matching each of the second feature sets with each of the first feature sets, and updating the count value corresponding to the first feature set corresponding to the matching success result;

[0010] sorting the count values corresponding to all first feature sets, and determining the attention degree of the user to the functions corresponding to each of the first feature sets according to the sorting result.

[0011] According to another aspect of the present application, a device for determining differences in attention to functions of a vehicle is provided, the device comprising:

[0012] The text acquisition module is configured to acquire at least two description texts and at least two comment texts corresponding to the target vehicle, wherein different description texts correspond to different function descriptions, and the comment texts correspond to function comments.

[0013] The first feature extraction module is configured to perform set description feature extraction on each of the description texts to obtain a first feature set containing at least one set description feature.

[0014] The second feature extraction module is configured to perform set comment feature extraction on each of the comment texts to obtain a second feature set containing at least one set comment feature.

[0015] The matching module is configured to match each of the second feature sets with each of the first feature sets respectively, and update a count value corresponding to a first feature set corresponding to a matching success result.

[0016] The attention degree determination module is configured to sort count values corresponding to all first feature sets, and determine an attention degree of a user to a function corresponding to each of the first feature sets according to a sorting result.

[0017] According to another aspect of the present application, an electronic device is provided, which comprises:

[0018] at least one processor; and

[0019] a memory connected with the at least one processor in communication; wherein

[0020] The memory stores a computer program executable 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 method for determining a difference in attention to each function of a vehicle according to any one of the embodiments of the present application.

[0021] According to another aspect of the present application, a computer readable storage medium is provided, which stores computer instructions for enabling a processor to implement the method for determining a difference in attention to each function of a vehicle according to any one of the embodiments of the present application when executed by the processor.

[0022] The automobile function attention difference determination method provided by the embodiment of the present application extracts the description text to obtain a first feature set containing set description features, extracts the comment text to obtain a second feature set containing set comment features, matches the second feature set with the first feature set respectively, and updates the count value corresponding to the first feature set corresponding to the matching result, sorts the first feature set according to the count value corresponding to the first feature set, and determines the attention degree of the function corresponding to the first feature set according to the sorting result. The above method can not only extract features from the description text and the comment text at the same time, but also determine the attention degree of each function according to the feature matching result, so that the designer can upgrade and improve the vehicle function according to the attention degree of each function, improve the user experience, and improve the user's recognition of the product.

[0023] It should be understood that the content described in this part is not intended to identify the key or important features of the embodiments of the present application, nor is it used to limit the scope of the present application. Other features of the present application will become apparent from the following description. BRIEF DESCRIPTION OF DRAWINGS

[0024] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed in the embodiment description will be briefly introduced below. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can also be obtained by those skilled in the art without creative labor.

[0025] Figure 1 is a flow chart of an automobile function attention difference determination method provided by the first embodiment of the present application;

[0026] Figure 2 is a flow chart of another automobile function attention difference determination method provided by the second embodiment of the present application;

[0027] Figure 3 is a flow chart of another automobile function attention difference determination method provided by the third embodiment of the present application;

[0028] Figure 4A is a syntax tree diagram for extracting the first comment feature provided by the third embodiment of the present application;

[0029] Figure 4B is a syntax tree diagram for extracting the second comment feature provided by the third embodiment of the present application;

[0030] Figure 4C is a syntax tree diagram for extracting the third comment feature provided by the third embodiment of the present application;

[0031] Figure 5is a structural block diagram of an automobile function attention difference determination device provided by the fourth embodiment of the present application;

[0032] Figure 6 is a structural block diagram of an electronic device provided by the fifth embodiment of the present application. DETAILED DESCRIPTION

[0033] In order to enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, but not all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work should fall within the scope of protection of the present application.

[0034] It should be noted that the terms "first", "second" and the like in the specification and claims of the present application and the above-described drawings are used to distinguish similar objects, and do not necessarily indicate a specific order or a chronological sequence. It should be understood that the data thus used can be interchanged under appropriate circumstances, so that the embodiments of the present application described herein can be implemented in other than the order illustrated or described herein. In addition, the terms "include" and "have" and any variations thereof are intended to cover non-exclusive inclusion, for example, a process, method, system, product or device that includes a series of steps or units does not necessarily have to include all the steps or units clearly listed, but can include other steps or units not clearly listed or inherent to the process, method, product or device.

[0035] Embodiment one

[0036] Figure 1 A flowchart of a method for determining the attention difference of each function of an automobile is provided for the first embodiment of the present application. The present embodiment can be applicable to the case of obtaining the attention degree of vehicle function from the feedback information of user's description of vehicle. The method can be executed by an automobile function attention difference determination device, which can be realized in the form of hardware and / or software, and can be configured in an electronic device. As shown in the figure, the method comprises: Figure 1

[0037] S110, obtaining at least two description texts and at least two comment texts corresponding to a target vehicle, different description texts corresponding to different function descriptions, and comment texts corresponding to function comments.

[0038] Among them, the description text is used to describe the function of the vehicle. The comment text and the description text correspond to the text of the user's comment on the function of the vehicle.

[0039] ​The description text corresponds to the vehicle function one by one. One review text corresponds to at least one vehicle function, and one vehicle function corresponds to at least one review text.

[0040] S120, set description feature extraction is performed on each description text to obtain a first feature set containing at least one set description feature.

[0041] After obtaining the description text, the sentence structure corresponding to the description text is determined, and then set description feature extraction is performed on each description text according to the sentence structure of the description text to obtain a first feature set containing at least one set description feature. That is, one vehicle function corresponds to at least one set description feature in a first feature set.

[0042] S130, set review feature extraction is performed on each review text to obtain a second feature set containing at least one set review feature.

[0043] The syntax tree corresponding to the review text is determined, and then set review feature extraction is performed on the syntax tree to obtain a second feature set containing at least one set review feature. That is, one or more set review features are extracted from each review text in at least one review text corresponding to each vehicle function in the embodiment, and the one or more set review features are added to the corresponding second feature set.

[0044] S140, each second feature set is matched with each first feature set respectively, and the count value corresponding to the first feature set of the matching success result is updated.

[0045] For any second feature set and any first feature set, each review feature in the second feature set and each description feature in the first feature set are matched based on a set matching algorithm, wherein the set matching algorithm includes a keyword matching algorithm, a synonym matching algorithm and a syntax algorithm.

[0046] The keyword matching algorithm is to match features at the level of single words. If each word included in two review features is the same, the order of the words is ignored, and they are considered to be matched, for example, Bluetooth connection and connection Bluetooth are considered to be matched.

[0047] The synonym matching algorithm is to match features by judging whether the meanings of the words are the same. If two feature words belong to synonyms in a set of synonyms, they are considered to be matched. For example, "gearbox" and "gearbox" are considered to be matched.

[0048] The semantic matching algorithm is to match features by judging the similarity of the semantic of words. If two feature words represent the same thing, they are similar in semantics. The implementation method includes: if the semantics of two feature words in the same semantic set are the same, and the similarity of the word order vectors corresponding to the two feature words is greater than a set threshold, it is considered that the two features are matched. The word order vector is the order of the appearance of the feature word in the sentence.

[0049] Before performing feature matching, the count corresponding to the first feature set is set to 0. If the matching is successful, the count of the first feature set is incremented by 1 to update the count value corresponding to the first feature set. If the matching fails, the count value corresponding to the first feature set is maintained.

[0050] S150, sort the count values corresponding to all first feature sets, and determine the attention of the user to the function corresponding to each first feature set according to the sorting result.

[0051] After completing the matching of all second feature sets with each first feature set, the count values corresponding to the first feature sets are sorted in descending order to obtain a sorting result. It can be understood that the attention of the function corresponding to the first feature set is positively correlated with the count value corresponding to the first feature set. The greater the count value corresponding to the first feature set, the more the number of comments on the function corresponding to the first feature set, and the higher the attention of the function corresponding to the first feature set.

[0052] The method for determining the attention difference of each function of the automobile provided by the embodiment of the application extracts the first feature set containing the set description feature from the description text, and extracts the second feature set containing the set comment feature from the comment text. The second feature set is matched with the first feature set respectively, and the count value corresponding to the first feature set corresponding to the matching result is updated. The first feature set is sorted according to the count value corresponding to the first feature set, and the attention of the function corresponding to the first feature set is determined according to the sorting result. The above method can not only extract features from description text and comment text at the same time, but also determine the attention of the user to the function according to the feature matching result, so that the designer can upgrade and improve the vehicle function according to the function attention, improve the user experience, and improve the user's recognition of the product.

[0053] Embodiment two

[0054] Figure 2 The flowchart of the method for determining the attention difference of each function of the automobile provided by the embodiment two of the application, the embodiment of the application is used to optimize the "extracting the first feature set containing at least one set description feature from each description text" in the foregoing embodiment, including the following steps:

[0055] S210, at least two description texts and at least two comment texts corresponding to the target vehicle are obtained, different description texts correspond to different function descriptions, and comment texts correspond to function comments.

[0056] S2201, the description text is preprocessed to update the description text.

[0057] After obtaining the vehicle description text, the description text needs to be preprocessed to update the description text. The preprocessing operation includes but is not limited to replacing the comma in the description text with a period, deleting the conjunction in the description text and the data in the parentheses, and analyzing the left subtree data and the right subtree data of the updated description text to determine the sentence structure of the updated description text.

[0058] S2202, the sentence structure corresponding to the updated description text is determined.

[0059] The sentence structure is the composition structure of the sentence.

[0060] For example, Table 1 is a common sentence structure and example of the description text.

[0061] Table 1 Description sentence structure

[0062]

[0063] S2203, the feature extraction rule corresponding to the sentence structure is used to extract the features of the updated description text to obtain a first feature set containing at least one set description feature.

[0064] Different feature extraction rules are set in advance for different sentence structures. The sentence structure corresponding to the description text is determined, and the feature extraction rule corresponding to the sentence structure is used to extract the features of the updated description text to obtain a first feature set containing at least one set description feature, including:

[0065] a1, if the sentence structure is "noun plus noun", the noun in the sentence structure is extracted, and the noun is added to the corresponding first feature set as the first description feature.

[0066] The noun plus noun sentence structure is usually used to describe the highlight function of the vehicle. For example, liquid crystal instrument panel. At this time, the noun (instrument panel) in the sentence structure is extracted, and the noun is added to the corresponding first feature set as the first description feature. It should be noted that a description text corresponds to a feature set, and the feature set can be in an array form.

[0067] a2, if the sentence structure is "verb plus noun", the noun in the sentence structure is extracted, and the noun is added to the corresponding first feature set as the second description feature.

[0068] The "verb plus noun" sentence structure is generally used to represent a specific function, allowing users to more intuitively understand that the vehicle has a certain function. For example: "Add automatic air conditioning." In this case, the noun (automatic air conditioning) in the sentence structure is extracted, and this noun is added as a second descriptive feature to the corresponding first feature set.

[0069] a3. If the sentence structure is "adjective plus noun", then extract the noun in the sentence structure and add the noun as the third descriptive feature to the corresponding first feature set.

[0070] The sentence structure of "adjective plus noun" uses adjectives to express the characteristics of a vehicle. For example, "beautiful appearance." In this case, the noun (appearance) in the sentence structure can be extracted and added as a third descriptive feature to the corresponding first feature set.

[0071] a4. If the sentence structure is "a combination of verb and noun", then extract the noun in the noun combination in the sentence structure and add the noun as the fourth descriptive feature to the corresponding first feature set. The noun combination includes at least two nouns and a conjunction connecting the at least two nouns.

[0072] The sentence structure of a "verb plus noun combination" expresses two pieces of feature information. For this sentence structure, it is necessary to first identify the verb and noun combination, then identify the conjunction and the two nouns within the noun combination, extract the noun from the noun combination in the sentence structure, and add this noun as the fourth descriptive feature to the corresponding first feature set. For example, "electrically adjustable steering wheel and seat." The extracted fourth descriptive features are "steering wheel" and "seat." Here, the noun combination includes at least two nouns and a conjunction connecting the at least two nouns.

[0073] a5. If the sentence structure is "two verbs plus a noun", then extract the noun in the sentence structure and add the noun as the fifth descriptive feature to the corresponding first feature set.

[0074] The first verb in this sentence structure is usually related to a need, followed by a feature that the current product doesn't have, but it's uncertain whether it's something the user wants. For example, someone might want to add a sunroof. In this case, the noun (sunroof) in the sentence structure is extracted, and this noun is added as the fifth descriptive feature to the corresponding first feature set.

[0075] S230. Extract the set comment features from each comment text to obtain a second feature set containing at least one set comment feature.

[0076] S240, respectively match each second feature set with each first feature set, and update the count value corresponding to the first feature set corresponding to the matching success result.

[0077] S250, sort the count values corresponding to all first feature sets, and determine the attention degree of the user to the functions corresponding to each first feature set according to the sorting result.

[0078] The feature extraction rule corresponding to the sentence structure is used to extract features from the updated description text, which improves the accuracy of the description feature extraction of the description text, thereby improving the accuracy of the matching of the first feature set and the second feature set, and thereby improving the difference of the attention degree of each vehicle function.

[0079] Embodiment three

[0080] Figure 3 A flowchart of a method for determining the attention difference of each function of an automobile is provided in the third embodiment of the application. The third embodiment of the application is used to optimize the "setting description feature extraction on each comment text to obtain a second feature set containing at least one set comment feature" in the foregoing embodiments, which includes the following steps:

[0081] S310, obtaining at least two description texts and at least two comment texts corresponding to a target vehicle, different description texts corresponding to different function descriptions, and comment texts corresponding to function comments.

[0082] S320, setting description feature extraction on each description text to obtain a first feature set containing at least one set description feature.

[0083] S3301, preprocessing each comment text to update the comment text.

[0084] After obtaining the comment text, the comment text needs to be preprocessed, which can include comment sentence, correction of misspelling, and removal of noise words, etc.

[0085] The user's comment may include a comment feature sentence, a non-comment feature sentence, and a sentence commenting on multiple different functions, therefore, in order to improve the accuracy of the comment feature extraction, it is necessary to divide the complex comment text into sentences. In one embodiment, the comment text is divided into sentences by the following method: replacing exclamation marks, commas, colons, and ellipses in the comment with periods; using the word_tokenize function in NLTK (a commonly used Python package in natural language processing) to divide the comment into sentences.

[0086] Since the grammar of the user's comment text is not necessarily standard, there will be some spelling errors or special characters. In order to improve the accuracy of feature recognition, for English comments, all English letters are converted to lowercase letters, and non-English characters and special symbols are deleted. For Chinese comments, error words need to be corrected, and non-Chinese words and special characters are deleted. In addition, the content in the parentheses is an explanation and supplement to the information in the comment and has no actual meaning, so the content in the parentheses needs to be deleted.

[0087] S3302, determine the grammar tree corresponding to each of the updated comment texts.

[0088] Determine the grammar tree corresponding to each of the updated comment texts. The grammar tree is a tree formed when a certain rule is derived, which is a graphical representation of the syntax structure of the sentence. It represents the derivation result of the sentence and is conducive to understanding the hierarchy of the syntax structure of the sentence. For example, given a grammar tree G=(Vn, Vt, P, S), where Vn is a set of non-terminal symbols, usually represented by uppercase letters, which is the intermediate node of the grammar tree; Vt is a set of terminal symbols, usually represented by uppercase letters; P is a set of productions, i.e. a set of rules; S is the start symbol, which is the root node of the grammar tree.

[0089] S3303, according to the set comment feature extraction rule, the grammar tree is set to extract the comment feature to obtain a second feature set containing at least one set comment feature.

[0090] From the updated grammar tree corresponding to each comment text, the set comment feature extraction is performed to obtain a second feature set containing at least one set comment feature. Specifically,

[0091] b1, if there is a sub-node containing a verb phrase in the grammar tree, and the sub-node includes a verb and a noun phrase, the noun in the noun phrase is extracted and added to the corresponding second feature set as a first comment feature.

[0092] For example, as shown in Figure 4A The verb phrase is "like automatic air conditioner", and the two sub-nodes of the verb phrase are verb and noun, respectively. Therefore, the noun (automatic air conditioner) is extracted as a first comment feature and added to the corresponding second feature set.

[0093] b2, if the leaf node of the grammar tree appears first, the noun is the first noun, and the right node of the root is traversed from bottom to top, if there is a noun phrase, the first noun and the noun in the noun phrase are added to the second feature set as second comment features.

[0094] For example, as shown in Figure 4BAs shown, for the comment sentence "the sunroof area is smaller than the canopy area", the leaf node (sunroof) of the corresponding syntax tree has a noun appearing first, and there is another noun child node (canopy) in the right node of the root, so the sunroof and the canopy are taken as the second comment features.

[0095] b3、If the syntax tree has a node labeled as a verb phrase, and the verb phrase includes a first child node with a part of speech of noun and has a sibling node with a part of speech of adjective, then the noun corresponding to the first child node with a part of speech of noun and the adjective corresponding to the sibling node with a part of speech of adjective are taken as the third comment features, and the third comment features are added to the second feature set.

[0096] As shown, for the verb phrase "the seat adjustment is convenient", the first child node is the noun "seat", and there is a sibling node with a part of speech of adjective (convenient), so the noun (seat) corresponding to the first child node with a part of speech of noun and the adjective (convenient) corresponding to the sibling node with a part of speech of adjective are taken as the third comment features, and the third comment features are added to the second feature set. Figure 4C b4、If the syntax tree has a node with a part of speech of noun, and the noun has a sibling node with a part of speech of adjective, then the noun is taken as the fourth comment feature and added to the second feature set; or if the syntax tree has a node with a part of speech of adjective, and the adjective has a sibling node with a part of speech of noun, then the adjective is taken as the fourth comment feature and added to the second feature set.

[0097] As an example, for the comment sentence "the design is slow", the corresponding syntax tree has a noun (design) and a sibling node with a part of speech of adjective (slow), so the noun (design) is taken as the fourth comment feature and added to the second feature set.

[0098] Optionally, b5、If the syntax tree has a node with a part of speech of verb, and the node with a part of speech of verb has a parent node with a part of speech of adverb or has a parent node labeled as a dependent clause, then the adverb or the dependent clause is taken as the first additional evaluation feature and added to the second feature set.

[0099] b6、If the syntax tree has a node with a part of speech of noun, and the node with a part of speech of noun has a descendant node with a part of speech of adjective or is labeled as an adjective phrase, then the adjective or the adjective phrase is taken as the second additional evaluation feature and added to the second feature set.

[0100] S340、Match each second feature set with each first feature set respectively, and update the count value corresponding to the first feature set corresponding to the matching success result.

[0101]

[0102] ​S350. Sort the count values corresponding to all the first feature sets, and determine the attention degrees of the user to the functions corresponding to the first feature sets according to the sorting result.

[0103] Different comment feature extraction rules are used for comment texts corresponding to different syntax trees, which improves the efficiency and accuracy of comment feature extraction, and also provides the accuracy of matching the second feature set with the first feature set.

[0104] Embodiment Four

[0105] Figure 5 A structural block diagram of an automobile function attention difference determination device according to Embodiment Four of the present application is provided. As shown in the figure, Figure 5 The device comprises:

[0106] The text acquisition module 510 is configured to acquire at least two description texts and at least two comment texts corresponding to a target vehicle, wherein different description texts correspond to different function descriptions, and the comment texts correspond to function comments.

[0107] The first feature extraction module 520 is configured to perform set description feature extraction on each of the description texts to obtain a first feature set containing at least one set description feature.

[0108] The second feature extraction module 530 is configured to perform set comment feature extraction on each of the comment texts to obtain a second feature set containing at least one set comment feature.

[0109] The matching module 540 is configured to match each of the second feature sets with each of the first feature sets respectively, and update the count value corresponding to the first feature set corresponding to the matching success result.

[0110] The attention degree determination module 550 is configured to sort the count values corresponding to all the first feature sets, and determine the attention degrees of the user to the functions corresponding to the first feature sets according to the sorting result.

[0111] Optionally, the first feature extraction module 520 is specifically configured to pre-process the description texts to update the description texts, determine the sentence structure corresponding to the updated description texts, and perform feature extraction on the updated description texts by using the feature extraction rule corresponding to the sentence structure, to obtain the first feature set containing at least one set description feature.

[0112] Optionally, the first feature extraction module 520 is specifically configured to: if the sentence structure is "noun plus noun", extract the noun in the sentence structure and add the noun as a first description feature to a corresponding first feature set; if the sentence structure is "verb plus noun", extract the noun in the sentence structure and add the noun as a second description feature to the corresponding first feature set; if the sentence structure is "adjective plus noun", extract the noun in the sentence structure and add the noun as a third description feature to the corresponding first feature set; if the sentence structure is "verb plus noun combination", extract the noun in the noun combination in the sentence structure and add the noun as a fourth description feature to the corresponding first feature set, wherein the noun combination includes at least two nouns and a conjunction connecting the at least two nouns; and if the sentence structure is "two verbs plus noun", extract the noun in the sentence structure and add the noun as a fifth description feature to the corresponding first feature set.

[0113] Optionally, the second feature extraction module 530 is specifically configured to: pre-process each comment text to update the comment text; determine a syntax tree corresponding to each updated comment text; and perform set comment feature extraction on the syntax tree according to a set feature extraction rule to obtain a second feature set containing at least one set comment feature.

[0114] Optionally, the second feature extraction module 530 is specifically configured to: if a sub-node containing a verb phrase exists in the syntax tree and the sub-node includes a verb and a noun phrase, extract the noun in the noun phrase and add the noun as a first comment feature to the corresponding second feature set; if a noun appears first in a leaf node of the syntax tree, the noun is a first noun, and a right node of the root is started to be traversed in a descending order, if a noun phrase exists, the first noun and the noun in the noun phrase are added as second comment features to the second feature set; if a node with a label of a verb phrase exists in the syntax tree and the verb phrase includes a first sub-node with a part of speech of a noun and has a sibling node with a part of speech of an adjective, a noun corresponding to the first sub-node with the part of speech of the noun and an adjective corresponding to the sibling node with the part of speech of the adjective are added as third comment features to the second feature set; if a node with a part of speech of a noun exists in the syntax tree and the noun has a sibling node with a part of speech of an adjective, the noun is added as a fourth comment feature to the second feature set; or if a node with a part of speech of an adjective exists in the syntax tree and the adjective has a sibling node with a part of speech of a noun, the adjective is added as a fourth comment feature to the second feature set.

[0115] Optionally, the second feature extraction module 530 is specifically configured to add the adverb or the subordinate clause as a first additional evaluation feature to the second feature set if the syntax tree has a part-of-speech node of a verb, and the part-of-speech node of the verb corresponds to a parent node of a part-of-speech of an adverb or a parent node of a label of a subordinate clause; and add the adjective or the adjective phrase as a second additional evaluation feature to the second feature set if the syntax tree has a part-of-speech node of a noun, and the part-of-speech node of the noun corresponds to a descendant node of a part-of-speech of an adjective or a label of an adjective phrase.

[0116] Optionally, the matching module 540 is specifically configured to, for any second feature set and any first feature set, match each review feature in the second feature set with each description feature in the first feature set based on a set matching algorithm, wherein the set matching algorithm includes a keyword matching algorithm, a synonym matching algorithm, and a semantic matching algorithm; if the matching is successful, update the count value corresponding to the first feature set; and if the matching fails, keep the count value corresponding to the first feature set.

[0117] The automobile function attention difference determination device provided by the embodiment of the application extracts the description text to obtain a first feature set containing set description features, and extracts the review text to obtain a second feature set containing set review features. The matching module matches the second feature set with the first feature set respectively, and updates the count value corresponding to the first feature set corresponding to the matching result. The attention degree acquisition module sorts the first feature set according to the count value corresponding to the first feature set, and determines the attention degree of the function corresponding to the first feature set according to the sorting result. The above device can not only extract features from the description text and the review text at the same time, but also determine the attention degree of the function according to the feature matching result, so that the designer can upgrade and improve the vehicle function according to the function attention degree, improve the user experience, and improve the user's recognition of the product.

[0118] The automobile function attention difference determination device provided by the embodiment of the application can execute the automobile function attention difference determination method provided by any embodiment of the application, and has the corresponding function modules and beneficial effects of the execution method.

[0119] Embodiment five

[0120] Figure 6A structural block diagram of an electronic device 10 that can be used to implement embodiments of the present application is shown. The electronic device is intended to represent various forms of digital computers, such as laptops, desktops, tablets, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers. The electronic device can also represent various forms of mobile devices, such as personal digital assistants, cellular telephones, smartphones, wearable devices (e.g., headsets, glasses, watches, etc.), and other similar computing devices. The components shown here, their connections and relationships, and their functions, are meant to be examples only, and are not intended to limit the implementations of the present application described and / or claimed in this document.

[0121] As shown in Figure 6 The electronic device 10 includes at least one processor 11, and a memory, such as a read-only memory (ROM) 12, a random access memory (RAM) 13, etc., connected in communication with the at least one processor 11, where the memory stores computer programs executable by the at least one processor. The processor 11 can perform various appropriate actions and processes according to the computer programs stored in the read-only memory (ROM) 12 or loaded into the random access memory (RAM) 13 from the storage unit 18. In the RAM 13, various programs and data required for the operation of the electronic device 10 can also be stored. The processor 11, the ROM 12, and the RAM 13 are connected to each other through a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0122] A plurality of components in the electronic device 10 are connected to the I / O interface 15, including an input unit 16, such as a keyboard, a mouse, etc., an output unit 17, such as various types of displays, speakers, etc., a storage unit 18, such as a magnetic disk, an optical disk, etc., and a communication unit 19, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information / data with other devices through a computer network, such as the Internet, and / or various telecommunication networks.

[0123] The processor 11 can be various general and / or special purpose processing components with processing and computing capabilities. Some examples of the 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 appropriate processor, controller, microcontroller, etc. The processor 11 performs various methods and processes described above, such as the vehicle functional focus difference determination method.

[0124] In some embodiments, the automobile function focus difference determination method can be implemented as a computer program tangibly embodied in a computer readable storage medium, e.g., storage unit 18. In some embodiments, parts or all of the computer program can be loaded onto the electronic device 10 via, e.g., ROM 12 and / or communication unit 19. When the computer program is loaded onto RAM 13 and executed by processor 11, one or more steps of the above-described automobile function focus difference determination method can be performed. Alternatively, in other embodiments, processor 11 can be configured to perform the automobile function focus difference determination method by any other suitable means, e.g., by means of firmware.

[0125] Various implementations of the systems and techniques described above can be realized in digital electronic circuitry, integrated circuitry, specially designed application specific integrated circuits (ASICs), field programmable gate arrays (FPGAs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include implementation in one or more computer programs that are executable and / or interpretable on a programmable system including at least one programmable processor, which can be special or general purpose, coupled to receive data and instructions from, and to transmit data and instructions to, a storage system, at least one input device, and at least one output device.

[0126] Computer programs used to implement the methods of the present application 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, special purpose computer, or other programmable data processing apparatus to produce a machine, such that the computer program, when executed by the processor of the machine, implements the functions / acts specified in the flowcharts and / or block diagrams. The computer program can be executed entirely on a machine, partially on a machine, partially on a machine and partially on a remote machine or entirely on a remote machine or server.

[0127] In the context of the present application, a computer-readable storage medium can be a tangible medium that can contain or store a computer program for use by or in connection with an instruction execution system, apparatus, or device. A computer-readable storage medium can include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium can be a machine-readable signal medium. More specific examples of a machine-readable storage medium will include one or more lines of a program of instructions in a transitory signal, a portable computer diskette, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or Flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0128] To provide for interaction with a user, the systems and techniques described here 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 a pointing device (e.g., a mouse or a trackball) by which the user can provide input to the electronic device. Other kinds of devices can be used to provide for interaction with a user as well; 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 acoustic, speech, or tactile input.

[0129] The systems and techniques described here can be implemented in a computing system that includes a back end component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front end component (e.g., a user computer having a graphical user interface or a Web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such back end, middleware, or front end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.

[0130] The computing system can include clients and servers. A client and server are generally remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other. The server can be a cloud server, also known as a cloud computing server or cloud host, which is a host product in the cloud computing service system, to solve the defects of large management difficulty and weak business scalability in traditional physical host and VPS service.

[0131] It should be understood that the various forms of flow shown above can be reordered, added to, or have steps deleted. For example, the steps described in the present application can be performed in parallel, in series, or in a different order, as long as the desired results of the technical solutions of the present application can be achieved, which are not limited herein.

[0132] The above detailed description does not constitute a limitation on the protection scope of the present application. 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 replacements and improvements made within the spirit and principles of the present application shall be included in the protection scope of the present application.

Claims

1. A method for determining the differences in attention to various functions of an automobile, characterized in that, include: Obtain at least two descriptive texts and at least two comment texts corresponding to the target vehicle, where different descriptive texts correspond to different functional descriptions, and the comment texts correspond to functional comments; Each of the described texts is subjected to a defined descriptive feature extraction to obtain a first feature set containing at least one defined descriptive feature; Each comment text is subjected to a set of comment features to obtain a second feature set containing at least one set of comment features; Each second feature set is matched with each first feature set, and the count value corresponding to the first feature set corresponding to the successful matching result is updated. Sort the count values ​​corresponding to all first feature sets, and determine the user's attention to the functions corresponding to each first feature set based on the sorting results; The step of extracting descriptive features from each of the descriptive texts to obtain a first feature set containing at least one descriptive feature includes: The description text is preprocessed to update the description text; Determine the statement structure corresponding to the updated description text; The updated description text is subjected to feature extraction using the feature extraction rules corresponding to the sentence structure, so as to obtain a first feature set containing at least one set of description features; The step of extracting features from the updated description text using the feature extraction rules corresponding to the statement structure to obtain a first feature set containing at least one defined description feature includes: If the statement structure is "noun plus noun", then extract the nouns in the statement structure and add the nouns as the first descriptive feature to the corresponding first feature set; If the sentence structure is "verb plus noun", then the noun in the sentence structure is extracted and added as a second descriptive feature to the corresponding first feature set; If the sentence structure is "adjective plus noun", then the noun in the sentence structure is extracted and added as a third descriptive feature to the corresponding first feature set; If the statement structure is a "verb plus noun combination", then the noun in the noun combination in the statement structure is extracted, and the noun is added as the fourth descriptive feature to the corresponding first feature set. The noun combination includes at least two nouns and a conjunction connecting the at least two nouns. If the sentence structure is "two verbs plus a noun", then the noun in the sentence structure is extracted and added as the fifth descriptive feature to the corresponding first feature set.

2. The method according to claim 1, characterized in that, The step of extracting specified comment features from each comment text to obtain a second feature set containing at least one specified comment feature includes: The comment texts are preprocessed to update the comment texts; Determine the syntax tree corresponding to each of the updated comment texts; The syntax tree is subjected to specified comment feature extraction according to the specified feature extraction rules to obtain a second feature set containing at least one specified comment feature.

3. The method according to claim 2, characterized in that, The step of extracting specified comment features from the syntax tree according to the specified feature extraction rules to obtain a second feature set containing at least one specified comment feature includes: If there is a child node in the syntax tree that contains a verb phrase, and the child node includes both a verb and a noun phrase, then the noun in the noun phrase is extracted, and the noun is added as a first comment feature to the second feature set; If a noun appears first in the leaf node of the syntax tree, then that noun is taken as the first noun, and a descending level traversal is performed starting from the right node of the root. If a noun phrase exists, then the first noun and the nouns in the noun phrase are added as second comment features to the second feature set. If the syntax tree contains a node labeled as a verb phrase, and the verb phrase includes a first child node with the part of speech of noun and a corresponding sibling node with the part of speech of adjective, then the noun corresponding to the first child node with the part of speech of noun and the adjective corresponding to the sibling node with the part of speech of adjective are taken as the third comment feature, and the third comment feature is added to the second feature set; If the syntax tree contains a node with the part of speech of a noun, and that noun has a sibling node with the part of speech of an adjective, then the noun is added as a fourth comment feature to the second feature set; or if the syntax tree contains a node with the part of speech of an adjective, and that adjective has a sibling node with the part of speech of a noun, then the adjective is added as a fourth comment feature to the second feature set.

4. The method according to claim 3, characterized in that, The step of extracting specified comment features from the syntax tree according to the specified feature extraction rules to obtain a second feature set containing at least one specified comment feature includes: If the syntax tree contains a node with the part of speech of a verb, and the node with the part of speech of a verb corresponds to a parent node with the part of speech of an adverb or a parent node with the label of a subordinate clause, then the adverb or subordinate clause is added to the second feature set as the first additional evaluation feature. If the syntax tree contains a node whose part of speech is noun, and the node whose part of speech is noun corresponds to a descendant node containing an adjective or an adjective phrase, then the adjective or adjective phrase is added as a second additional evaluation feature to the second feature set.

5. The method according to any one of claims 1-4, characterized in that, The step of matching each second feature set with each first feature set and updating the count value corresponding to the first feature set corresponding to the successful matching result includes: For any second feature set and any first feature set, each comment feature in the second feature set is matched with each descriptive feature in the first feature set based on a set matching algorithm. The set matching algorithm includes keyword matching algorithm, synonym matching algorithm and semantic matching algorithm. If a match is successful, update the count value corresponding to the first feature set; If a match fails, the count value corresponding to the first feature set is retained.

6. A device for determining differences in the functions of an automobile, characterized in that, include: The text acquisition module is used to acquire at least two descriptive texts and at least two comment texts corresponding to the target vehicle. Different descriptive texts correspond to different functional descriptions, and the comment texts correspond to functional comments. The first feature extraction module is used to extract defined descriptive features from each of the descriptive texts to obtain a first feature set containing at least one defined descriptive feature. The second feature extraction module performs predefined comment feature extraction on each comment text to obtain a second feature set containing at least one predefined comment feature; The matching module is used to match each of the second feature sets with each of the first feature sets respectively, and update the count value corresponding to the first feature set corresponding to the successful matching result; The attention determination module is used to sort the count values ​​corresponding to all first feature sets and determine the user's attention to the functions corresponding to each first feature set based on the sorting results. The first feature extraction module is specifically used to preprocess the description text to update the description text; determine the sentence structure corresponding to the updated description text; and use the feature extraction rules corresponding to the sentence structure to extract features from the updated description text to obtain a first feature set containing at least one set of description features. The first feature extraction module is specifically used to extract the nouns in the sentence structure if the sentence structure is "noun plus noun", and add the nouns as the first descriptive feature to the corresponding first feature set; If the sentence structure is "verb plus noun", then extract the noun in the sentence structure and add the noun as the second descriptive feature to the corresponding first feature set; If the sentence structure is "adjective plus noun", then extract the noun in the sentence structure and add the noun as the third descriptive feature to the corresponding first feature set; If the sentence structure is "verb plus noun combination", then extract the noun in the noun combination in the sentence structure and add the noun as the fourth descriptive feature to the corresponding first feature set. The noun combination includes at least two nouns and a conjunction connecting at least two nouns. If the sentence structure is "two verbs plus a noun", then extract the noun in the sentence structure and add the noun as the fifth descriptive feature to the corresponding first feature set.

7. An electronic device, characterized in that, The electronic device includes: At least one processor; and A memory communicatively connected to the at least one processor; wherein, The memory stores a computer program that can be executed by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to perform the method for determining differences in various functions of an automobile as described in any one of claims 1-5.

8. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions that, when executed by a processor, implement the method for determining differences in the concerns of various functions of an automobile as described in any one of claims 1-5.

Images