Electronic appliance function analysis method and device, computer equipment and storage medium

Abstract

The invention relates to an electronic and electric appliance function analysis method and device, computer equipment and a storage medium, and the method comprises the steps: obtaining the first information data of a to-be-analyzed function module, and enabling the first information data to indicate the user information related to the to-be-analyzed function module; obtaining a document subset corresponding to each theme according to the first information data; according to the document subset, determining a target keyword of the first information data under each theme; according to the target keyword and a reference keyword under the theme, a first matching degree under each theme is obtained, the reference keyword under the theme is obtained according to second information data of a historical function module, and the second information data indicates user information related to the historical function module; and determining the information correlation of the to-be-analyzed function module according to the first matching degree. By adopting the method, the problem of low function analysis efficiency in the prior art can be improved.

Description

Technical Field

[0001] This application relates to the field of analysis technologies, and particularly to an electronic and electrical function analysis method, apparatus, computer device, and storage medium. Background Art

[0002] In the automotive field, with the progress of vehicle technologies, the functional modules of electronic and electrical appliances change rapidly and dynamically. It is very important to perform functional analysis (such as correlation analysis) on electronic and electrical appliances. However, methods such as rule-based detection and statistic-based detection have limited capabilities in dealing with complex relationships and insufficient adaptability to dynamic changes. Currently, manual analysis is still mainly relied on, depending on manual screening and judgment based on past experience systems and static rule screening, resulting in low efficiency. Summary of the Invention

[0003] Based on this, an electronic and electrical function analysis method, apparatus, computer device, and storage medium are provided to improve the problem of low efficiency in functional analysis in the existing technology.

[0004] On the one hand, an electronic and electrical function analysis method is provided, and the method includes:

[0005] Obtain first information data of a function module to be analyzed, where the first information data indicates user information involved in the function module to be analyzed;

[0006] According to the first information data, obtain a document subset corresponding to each theme;

[0007] According to the document subset, determine target keywords of the first information data under each theme;

[0008] According to the target keywords and reference keywords under the theme, obtain a first matching degree under each theme, where the reference keywords under the theme are obtained according to second information data of a historical function module, and the second information data indicates user information involved in the historical function module;

[0009] According to the first matching degree, determine the information correlation of the function module to be analyzed.

[0010] In one embodiment, the determining, according to the document subset, target keywords of the first information data under each theme includes:

[0011] According to the document subset corresponding to the theme, determine the word frequency and inverse document frequency of candidate keywords under the theme;

[0012] According to the word frequency and inverse document frequency, determine the weight of each candidate keyword;

[0013] Determine the target keyword from the candidate keywords based on the weight.

[0014] In one embodiment, the determining the target keyword from the candidate keywords based on the weight includes:

[0015] Determine the candidate keywords with large weights as the target keyword according to a preset quantity.

[0016] Before determining the word frequency and inverse document frequency of the candidate keywords under the theme, it further includes:

[0017] Perform word segmentation on the document subset to obtain word units;

[0018] Obtain the candidate keywords according to the part of speech of the word units, where the candidate keywords are combinations of word units of verb + noun.

[0019] In one embodiment, the obtaining the first matching degree of each theme according to the target keyword and the reference keyword under the theme includes:

[0020] Determine the repeated keywords under the theme according to the target keyword and the reference keyword under the theme;

[0021] Obtain the first matching degree according to the proportion of the repeated keywords in the target keyword.

[0022] In one embodiment, after determining the information relevance of the function module to be analyzed, it further includes:

[0023] When the first matching degree is greater than the relevance threshold, determine the reusability of the function module to be analyzed, including:

[0024] Determine the overlapping function points according to the target function points of the function module to be analyzed and the reference function points of the historical function modules;

[0025] Obtain a second matching degree according to the proportion of the overlapping function points in the target function points;

[0026] Determine the reusability of the function module to be analyzed according to the second matching degree.

[0027] In one embodiment, the obtaining the document subset corresponding to each theme according to the first information data includes:

[0028] Based on a probability model for generating document themes, obtain the document subset corresponding to each theme.

[0029] On the other hand, provide an electronic and electrical function analysis device, the device includes:

[0030] An acquisition module, configured to acquire first information data of a function module to be analyzed, where the first information data indicates user information involved in the function module to be analyzed;

[0031] A theme assignment module, configured to obtain a document subset corresponding to each theme according to the first information data;

[0032] A keyword recognition module, configured to determine target keywords of the first information data under each theme according to the document subset;

[0033] An analysis module, configured to obtain a first matching degree under each theme according to the target keyword and a reference keyword under the theme, where the reference keyword under the theme is obtained according to second information data of a historical function module, and the second information data indicates user information involved in the historical function module; and determine information relevance of the function module to be analyzed according to the first matching degree.

[0034] In another aspect, a computer device is provided, including a memory, a processor, and a computer program stored on the memory and executable on the processor, where the processor implements the method when executing the computer program.

[0035] A computer-readable storage medium is further provided, on which a computer program is stored, and the computer program implements the method when executed by a processor.

[0036] The above electronic and electrical function analysis method, device, computer device, and storage medium obtain a document subset corresponding to each theme according to the first information data indicating user information involved in the function module to be analyzed, obtain target keywords under each theme according to the document subset, match the target keywords with the reference keywords, and judge information relevance based on the first matching degree, where the reference keyword is obtained according to user information involved in the historical function module; through the above process, combined with keyword extraction under the theme, the relevance analysis between the function module to be analyzed and the historical function module is quickly completed, improving the problem of low efficiency of manual analysis. Description of the Drawings

[0037] Figure 1 It is a schematic flowchart of an electronic and electrical function analysis method in an embodiment;

[0038] Figure 2 It is a schematic flowchart of information relevance analysis for sensitive information in an embodiment;

[0039] Figure 3 It is a structural block diagram of an electronic and electrical function analysis device in an embodiment;

[0040] Figure 4 It is the internal structure diagram of a computer device in an embodiment. Detailed implementation manners

[0041] In order to make the purpose, technical solutions and advantages of the present application clearer, the present application will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0042] In new energy vehicles, the functions of vehicles are constantly increasing in terms of types, and the electronic and electrical appliances are iterating rapidly. Conducting functional analysis on the electronic and electrical appliances can identify the complex relationships between functional modules and potential reuse possibilities. Therefore, how to conduct functional analysis, especially correlation analysis and reusability analysis, has become an urgent problem in the current technology.

[0043] In the related art, functional analysis relies on the experience judgment of practitioners, static rule screening, and simple statistical models. This method is not only inefficient but also difficult to adapt to diverse reuse rules. In addition, due to the continuous development and progress of current vehicle production and manufacturing technologies, the manual screening judgment and static rule judgment relying on the past experience system are gradually invalidated. With the continuous introduction of new technologies, simple statistical models cannot be applied to high-dimensional data, which actually increases the difficulty of detecting functional correlation and reusability.

[0044] The present application provides an electronic and electrical appliance function analysis method, which is exemplarily applied in the automotive field, conducts information correlation analysis on the user information involved in the functional module, and quickly obtains the correlation analysis result of the functional module to be analyzed at the level of the involved user information.

[0045] In one embodiment, the electronic and electrical appliance function analysis method is as Figure 1 shown, and includes the following steps:

[0046] Step 110, obtain the first information data of the functional module to be analyzed.

[0047] The functional module to be analyzed is, for example, a newly added functional module of a vehicle. During the actual operation of the functional module to be analyzed, it will collect and process a series of user-related information. For example, the vehicle networking module may collect the user's identity information, vehicle location, driving trajectory, driving habits, etc. The autonomous driving module may involve more environmental data and driving behavior data. The navigation system will record location and route information. The remote control function may require the user's mobile phone number, account information, etc. Specifically which user information is involved is related to the specific situation of the functional module and is generally recorded in the relevant information documents. The user information involved in the functional module to be analyzed is used as the first information data and can be stored in the form of an information document.

[0048] Step 120: Obtain the document subsets corresponding to each topic according to the first information data.

[0049] A topic refers to a set of semantically related words implicit in a document. Assume that the user information involved in the function module to be analyzed can be regarded as being generated by one or several implicit topics. Each document can be regarded as a mixture of these topics. By using statistical and probability theory methods, the implicit topics in the document set are identified. Each topic consists of a group of semantically related words. These topics reflect the structure of the content in the document set.

[0050] The first information data can divide the document subsets according to topics. For example, for the sensitive information involved in the function module, topic allocation can be carried out according to aspects such as "personal identity information" and "personal biometric information" to obtain the document subsets corresponding to each topic.

[0051] Exemplarily, topic modeling is performed through the LDA (Latent Dirichlet Allocation) topic model to obtain the document subsets corresponding to each topic.

[0052] The LDA topic model is a document topic generation probability model. In the three-layer topological structure of the LDA topic model, keywords are combined into implicit topics according to a certain probability, and topics are combined into documents according to a certain probability. The LDA topic model adopts Bayesian theory and probability statistics. In this algorithm, a related concept of a topic is introduced, and each topic is used as a reference layer between a document and a word. Through this method, the correlations between doc-topic (document-topic) and topic-word (topic-word) can be obtained. According to the results of LDA, the documents belonging to the same topic are classified together to form a subset.

[0053] Step 130: Determine the target keywords of the first information data under each topic according to the document subsets.

[0054] In this step, using the document subsets as input, extract the keywords that can best represent "the user information under a certain topic involved in the function module to be analyzed", and perform subsequent correlation analysis with the target keywords.

[0055] Step 140: Obtain the first matching degrees under each topic according to the target keywords and the reference keywords under the topic.

[0056] Among them, the reference keywords under each topic are obtained according to the second information data of the historical function module, and the second information data indicates the user information involved in the historical function module.

[0057] Similar to the processing process of the first information data of the module to be analyzed, the electronic and electrical component information of historical vehicle models is collected, and data cleaning, format unification, standardization and fusion are carried out in units of functional modules. Then, the processed data is modeled, and multiple topic-related document subsets are formed according to the topic allocation results of LDA. The keywords of each document subset are identified, and the keywords that best represent "user information under a certain topic involved in the historical functional module" are used as candidate keywords.

[0058] The first matching degree can be obtained by calculating the number of repetitions of the target keyword and the reference keyword, and further calculating the proportion. It can be understood that the higher the repetition proportion, the higher the first matching degree.

[0059] Step 150: Determine the information relevance of the functional module to be analyzed according to the first matching degree.

[0060] It can be understood that the higher the first matching degree is, the higher the correlation between the user information involved in the functional module to be analyzed and the user information involved in the historical functional module is. Based on such analysis results, it can help R&D personnel use the data resources of historical vehicle models and historical functional modules to reduce duplication of work in the new car design and production process and reduce development costs.

[0061] In the above process, based on the keyword extraction and recognition technology, the data information content related to the vehicle is described with at least several relatively simple and accurate keywords, and keyword recognition is performed in a standardized manner to reduce the error of correlation analysis. Compared with manual analysis, work efficiency is improved.

[0062] For example, Figure 2 As shown, based on the above electronic and electrical function analysis method, it can be used to analyze the information relevance of the function module to be analyzed in terms of sensitive information. The following describes the process:

[0063] The personal sensitive information involved in the Internet of Vehicles system includes eight categories: "personal identity information", "personal biometric information", "personal property information", "personal communication information", "contact information", "personal application operation information", "personal location information", and "other information". Based on these eight categories, eight categories of sensitive information topics are defined.

[0064] For the user information involved in the historical function modules, according to the above eight major categories, the LDA topic model is used for processing, including word segmentation, stop word removal, etc. Then, each word is processed, and topics are assigned to it according to the major categories. Through the iterative process, these assignments are gradually adjusted so that some words tend to be associated with specific topics, and at the same time, some topics tend to be associated with specific documents. This process is based on two probability factors: some words are more likely to appear in some topics, and some topics are more common in some documents. Through repeated iteration, the topic assignments of each word and the topic proportions of each document will gradually stabilize, forming multiple document subsets related to topics, such as the document subset related to "personal identity information", the document subset related to "personal biometric information", etc.

[0065] In this process, the content of sensitive personal information is sorted into different document subsets, providing a basis for subsequent relevance discrimination.

[0066] The keyword recognition algorithm is used to analyze the keyword weights under each topic, and the reference keywords that best represent the information involved are selected under that topic.

[0067] For the user information involved in the function module to be analyzed, topic assignments are still made according to the eight major categories, and the LDA topic model is used for processing to form multiple document subsets related to topics. The keyword weights under each topic are analyzed, and the target keywords that best represent the information involved are selected under that topic.

[0068] Analyze the information relevance under each topic. For example, in "personal identity information", according to the target keywords and reference keywords under "personal identity information", calculate the coincidence degree to obtain the first matching degree under the topic of "personal identity information". Similarly, the first matching degrees under the topics of "personal biometric information", "personal property information", "personal communication information", "contact information", "personal application operation information", "personal location information", and "other information" can also be calculated, so as to analyze the relevance of the function module to be analyzed in each topic, and thus determine whether the function module to be analyzed is related to sensitive information.

[0069] The above-mentioned relevance recognition of sensitive information starts from the historical function modules of the input historical vehicle models, goes through data cleaning, format unification, standardization processing and fusion, and then models the processed data to generate a relevance analysis model combining the LDA topic model and keyword recognition. Using this relevance analysis model, input the user information involved in the function module to be analyzed to quickly obtain the results of function analysis.

[0070] The following provides a detailed description of steps 110 to 150.

[0071] For step 130, the TF-IDF (term frequency–inverse document frequency) algorithm is exemplarily used to implement the recognition of target keywords.

[0072] TF-IDF uses a statistical method to measure the contribution of each word to a document. If a word is more important to a document, then the probability of its appearance is naturally higher. However, in order to distinguish it from other documents, during the design process, if the number of occurrences of this word in the entire corpus is relatively large, its distinguishability in the document will decrease, and consequently its importance will be reduced.

[0073] TF refers to the term frequency, which represents the number of times a certain word appears in a document. In order to make this algorithm applicable to all texts, normalization will be performed during the calculation, that is, the number of occurrences is divided by the number of words in the entire document.

[0074] IDF refers to the inverse document frequency, which is calculated by dividing the number of documents in the corpus by the number of documents containing the word. Since the numerator remains unchanged, the smaller the denominator, the larger the result. This indicates that the fewer the number of documents including this term, the larger the inverse document frequency, which proves that this word has a greater distinguishability for this document. The larger the IDF value of a certain word, the greater the contribution of this word to the document, and it is also more likely to become a keyword.

[0075] In the actual implementation process, according to the document subset corresponding to the theme, the term frequency and inverse document frequency of the candidate keywords under this theme are determined; according to the term frequency and inverse document frequency, the weight of each candidate keyword is determined; based on the weight, the target keyword is determined from the candidate keywords.

[0076] Exemplarily, first, the document subsets under each theme are segmented into words and clauses, and irrelevant characters such as line breaks and punctuation marks in the text are removed. The user information involved in the document subset is cut into independent word units by a word segmentation tool, and finally, the incorrect segmentation results are merged and stop words are deleted.

[0077] The clause segmentation link includes cutting the text into independent clause units for subsequent finer-grained text analysis and processing, removing irrelevant characters such as line breaks and punctuation marks in the text, defining the sentence boundaries with an existing word segmentation library, and finally merging the incorrect segmentation results and processing long sentences.

[0078] In some embodiments, word segmentation is performed on a document subset to obtain word units, and candidate keywords are obtained based on the part-of-speech of the word units. Exemplarily, a statistical model is generated based on historical automotive data to identify the part-of-speech of each word unit, such as parts-of-speech like verbs and nouns. Word units with specific parts-of-speech are selected as candidate keywords. In this application, in the information retrieval task related to the function points of automotive functional modules, the combination of verb + noun is more discriminative. Therefore, the combination content of verb + noun is selected as the candidate keyword. The i-th document a i can be represented by the candidate keyword set as: a i =(t1, t2, ……, t n ,), where t1, t2, ……, t n are the 1-nth candidate keywords.

[0079] Perform TF-IDF calculation on the filtered candidate keywords to obtain the weight of each candidate keyword in the document subset.

[0080] According to the importance of the candidate keyword in document a i , a certain weight is assigned to it. The TF-IDF algorithm calculates the weight of the candidate keyword through the term frequency (TF) and inverse document frequency (IDF). Among them, the weight TFIDF(a i , t i ) corresponding to the candidate keyword t i in the text a i is calculated according to the following mathematical expression:

[0081] TFIDF(a i , t i ) = TF(a i , t i ) × IDF(t i );

[0082] Among them, TF(a i , t i ), IDF(t i ) are calculated in the following ways respectively:

[0083]

[0084] Among them, represents the term frequency of the candidate keyword t i in the document a i , represents the sum of the term frequencies of all candidate keywords in the document a i , D represents the total number of documents, j: t i ∈d j means including the candidate keyword t iThe number of documents, and to avoid a zero denominator, 1 is usually added.

[0085] In one implementation, the candidate keywords are sorted in descending order according to the weight TFIDF(a i ,t i ), and according to a preset quantity, the candidate keywords with large weights are determined as the target keywords.

[0086] For the user information involved in the historical function module, the candidate keywords with large weights are calculated according to the above process as the reference keywords.

[0087] In the above process, based on the TF-IDF algorithm, the target keywords or subsequent keywords are extracted, filtering out some common but unimportant words, and at the same time retaining the important words that affect the entire document.

[0088] The process utilizes the latent topic discovery ability of LDA, and also considers the frequency of the candidate keywords within the topic and the inverse document frequency in the entire corpus through TF-IDF, thereby highlighting the important words within the topic.

[0089] For step 140, when calculating the first matching degree under a certain topic, according to the target keywords and reference keywords under the topic, the repeated keywords under the topic are determined; according to the proportion of the repeated keywords in the target keywords, the first matching degree is obtained.

[0090] Exemplarily, the first matching degree S1 is calculated according to the following mathematical expression:

[0091]

[0092] Among them, A1 represents the set of target keywords, B1 represents the set of reference keywords, |A1∩B1| represents the overlapping keywords among the information involved in the function module to be analyzed. For example, in the information relevance analysis of sensitive information, |A1∩B1| represents the content overlapping with sensitive information among the information involved in the function module to be analyzed under a certain topic.

[0093] By calculating the information relevance, the information of various types of topics involved in the function module to be analyzed can be identified. For example, identifying the sensitive information involved in the function module to be analyzed helps developers determine whether the information involved in the function module to be analyzed belongs to general personal information or sensitive personal information.

[0094] In some implementations, based on the information relevance analysis, a reusability analysis is performed to help developers judge the reuse value of the function module, promote the rational use of resources, and reduce waste.

[0095] Exemplarily, it includes determining the reusability of the function module to be analyzed in the case where the first matching degree is greater than the relevance threshold.

[0096] For example, if the relevance threshold is predefined as 50%, when the first matching degree is greater than 50%, it is considered that the function module to be analyzed passes the relevance matching process and can further perform the reusability analysis; otherwise, no analysis is performed.

[0097] Determining the reusability of the function module to be analyzed includes: determining the overlapping function points based on the target function points of the function module to be analyzed and the reference function points of the historical function modules; obtaining the second matching degree based on the proportion of the overlapping function points in the target function points; and determining the reusability of the function module to be analyzed based on the second matching degree.

[0098] In the actual implementation process, the function points of the function module are defined as the attributes of the automotive function module itself, which are already defined elements and will not be elaborated here.

[0099] Exemplarily, the second matching degree S2 is calculated according to the following mathematical expression:

[0100]

[0101] Among them, A2 represents the total number of target function points of the function module to be analyzed, B2 represents the total number of reference function points of the historical function modules, and |A2∩B2| represents the intersection of the function points, that is, the number of function points that are the same between the function module to be analyzed and the historical function modules.

[0102] The second matching degree represents the proportion of the function points of the function module to be analyzed covered by a certain function module. If the second matching degree is greater than the preset threshold, the function module to be analyzed is determined to be a reusable module.

[0103] In some other embodiments, the reusability analysis further includes DPIA (Data Protection Impact Assessment) assessment. Whether the DPIA process has been executed is stored in the form of 0 and 1. The function module that has not executed the DPIA process is recorded as 0, and the function module that has executed the DPIA process is recorded as 1.

[0104] It should be understood that although Figure 1 、 Figure 2 the steps in the flowchart of Figure 1 、 Figure 2At least a part of the steps therein may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily executed and completed at the same moment, but can be executed at different moments. The execution order of these sub-steps or stages is not necessarily sequential, but can be executed alternately or in turns with at least a part of other steps or sub-steps or stages of other steps.

[0105] In one embodiment, as Figure 3 shown, there is provided an electronic and electrical function analysis device, including: an acquisition module 210, a theme assignment module 220, a keyword recognition module 230, and an analysis module 240, wherein:

[0106] The acquisition module 210 is configured to acquire first information data of a function module to be analyzed, and the first information data indicates user information involved in the function module to be analyzed;

[0107] The theme assignment module 220 is configured to obtain a document subset corresponding to each theme according to the first information data;

[0108] The keyword recognition module 230 is configured to determine target keywords of the first information data under each theme according to the document subset;

[0109] The analysis module 240 is configured to obtain a first matching degree under each theme according to the target keywords and reference keywords under the theme, wherein the reference keywords under the theme are obtained according to second information data of a historical function module, and the second information data indicates user information involved in the historical function module; and determine the information relevance of the function module to be analyzed according to the first matching degree.

[0110] By using the above device, by obtaining a document subset corresponding to each theme according to the first information data indicating user information involved in the function module to be analyzed, obtaining target keywords under each theme according to the document subset, matching the target keywords and reference keywords, and judging the information relevance based on the first matching degree, wherein the reference keywords are obtained according to user information involved in the historical function module; through the above process, combined with keyword extraction under the theme, the relevance analysis between the function module to be analyzed and the historical function module is quickly completed, and the problem of low efficiency of manual analysis is improved.

[0111] In one embodiment, the keyword recognition module 230 determines the word frequency and inverse document frequency of candidate keywords under the theme according to the document subset corresponding to the theme; determines the weight of each candidate keyword according to the word frequency and inverse document frequency; and determines target keywords from the candidate keywords based on the weight.

[0112] In one embodiment, the keyword recognition module 230 determines candidate keywords with large weights as target keywords according to a preset quantity.

[0113] In one embodiment, the keyword recognition module 230 performs word segmentation on the document subset to obtain word units, and obtains candidate keywords according to the part-of-speech of the word units, where the candidate keywords are combinations of word units of verb + noun.

[0114] The analysis module 240 determines the repeated keywords under the theme according to the target keywords and reference keywords under the theme, and obtains the first matching degree according to the proportion of the repeated keywords in the target keywords.

[0115] The analysis module 240 is further configured to determine the reusability of the function module to be analyzed when the first matching degree is greater than the correlation threshold, including: determining the overlapping function points according to the target function points of the function module to be analyzed and the reference function points of the historical function module; obtaining the second matching degree according to the proportion of the overlapping function points in the target function points; and determining the reusability of the function module to be analyzed according to the second matching degree.

[0116] The theme assignment module 220 is configured to generate a probability model based on the document theme and obtain the document subset corresponding to each theme.

[0117] For the specific limitations of the electronic and electrical function analysis device, reference can be made to the limitations of the electronic and electrical function analysis method in the above text, which will not be elaborated here. Each module in the above electronic and electrical function analysis device can be implemented in whole or in part by software, hardware, and their combination. The above modules can be embedded in the processor of the computer device in hardware form or independent of it, or stored in the memory of the computer device in software form, so that the processor can call and execute the operations corresponding to the above modules.

[0118] In one embodiment, a computer device is provided. The computer device can be a terminal, and its internal structure diagram can be as Figure 4 shown. The computer device includes a processor, a memory, a network interface, a display screen, and an input device connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The network interface of the computer device is used to communicate with an external terminal through a network connection. The computer program, when executed by the processor, implements an electronic and electrical function analysis method. The display screen of the computer device can be a liquid crystal display screen or an electronic ink display screen. The input device of the computer device can be a touch layer covering the display screen, or a button, a trackball, or a touchpad provided on the housing of the computer device, or an external keyboard, a touchpad, or a mouse, etc.

[0119] Those skilled in the art can understand that Figure 4 The structure shown in Figure 4 is only a block diagram of some structures related to the solution of this application, and does not constitute a limitation on the computer device to which the solution of this application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine some components, or have a different component layout.

[0120] In one embodiment, a computer device is provided, including a memory, a processor, and a computer program stored on the memory and executable on the processor. When the processor executes the computer program, the following steps are implemented:

[0121] Obtain the first information data of the function module to be analyzed, where the first information data indicates the user information involved in the function module to be analyzed;

[0122] According to the first information data, obtain the document subsets corresponding to each topic;

[0123] According to the document subsets, determine the target keywords of the first information data under each topic;

[0124] According to the target keywords and the reference keywords under the topic, obtain the first matching degree under each topic, where the reference keywords under the topic are obtained according to the second information data of the historical function module, and the second information data indicates the user information involved in the historical function module;

[0125] According to the first matching degree, determine the information relevance of the function module to be analyzed.

[0126] In one embodiment, when the processor executes the computer program, the following steps are further implemented:

[0127] According to the document subsets corresponding to the topics, determine the word frequency and inverse document frequency of the candidate keywords under the topics;

[0128] According to the word frequency and inverse document frequency, determine the weight of each candidate keyword;

[0129] Based on the weights, determine the target keywords from the candidate keywords.

[0130] In one embodiment, when the processor executes the computer program, the following steps are further implemented:

[0131] According to the preset quantity, determine the candidate keywords with large weights as the target keywords.

[0132] In one embodiment, when the processor executes the computer program, the following steps are further implemented:

[0133] Perform word segmentation on the document subsets to obtain word units;

[0134] Obtain candidate keywords according to the part-of-speech of word units, where the candidate keywords are combinations of verb + noun word units.

[0135] In one embodiment, when the processor executes the computer program, the following steps are further implemented:

[0136] Determine the repeated keywords under the theme according to the target keywords and reference keywords under the theme;

[0137] Obtain the first matching degree according to the proportion of the repeated keywords in the target keywords.

[0138] In one embodiment, when the processor executes the computer program, the following steps are further implemented:

[0139] In the case where the first matching degree is greater than the correlation threshold, determine the reusability of the function module to be analyzed, including:

[0140] Determine the overlapping function points according to the target function points of the function module to be analyzed and the reference function points of the historical function module;

[0141] Obtain the second matching degree according to the proportion of the overlapping function points in the target function points;

[0142] Determine the reusability of the function module to be analyzed according to the second matching degree.

[0143] In one embodiment, when the processor executes the computer program, the following steps are further implemented:

[0144] Generate a probability model based on the document theme, and obtain the document subsets corresponding to each theme.

[0145] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the following steps are implemented:

[0146] Obtain the first information data of the function module to be analyzed, where the first information data indicates the user information involved in the function module to be analyzed;

[0147] Obtain the document subsets corresponding to each theme according to the first information data;

[0148] Determine the target keywords of the first information data under each theme according to the document subsets;

[0149] Obtain the first matching degree under each theme according to the target keywords and the reference keywords under the theme, where the reference keywords under the theme are obtained according to the second information data of the historical function module, and the second information data indicates the user information involved in the historical function module;

[0150] Determine the information relevance of the function module to be analyzed according to the first matching degree.

[0151] In one embodiment, when the computer program is executed by a processor, the following steps are further implemented:

[0152] According to the document subset corresponding to the theme, determine the word frequency and inverse document frequency of the candidate keywords under the theme;

[0153] According to the word frequency and inverse document frequency, determine the weight of each candidate keyword;

[0154] Based on the weights, determine the target keywords from the candidate keywords.

[0155] In one embodiment, when the computer program is executed by a processor, the following steps are further implemented:

[0156] According to the preset quantity, determine the candidate keywords with large weights as the target keywords.

[0157] In one embodiment, when the computer program is executed by a processor, the following steps are further implemented:

[0158] Perform word segmentation on the document subset to obtain word units;

[0159] According to the part of speech of the word units, obtain candidate keywords, where the candidate keywords are combinations of word units of verb + noun.

[0160] In one embodiment, when the computer program is executed by a processor, the following steps are further implemented:

[0161] According to the target keywords and reference keywords under the theme, determine the repeated keywords under the theme;

[0162] According to the proportion of the repeated keywords in the target keywords, obtain the first matching degree.

[0163] In one embodiment, when the computer program is executed by a processor, the following steps are further implemented:

[0164] In the case where the first matching degree is greater than the correlation threshold, determine the reusability of the function module to be analyzed, including:

[0165] According to the target function points of the function module to be analyzed and the reference function points of the historical function module, determine the overlapping function points;

[0166] According to the proportion of the overlapping function points in the target function points, obtain the second matching degree;

[0167] According to the second matching degree, determine the reusability of the function module to be analyzed.

[0168] In one embodiment, when the computer program is executed by a processor, the following steps are further implemented:

[0169] Generate a probability model based on the document theme and obtain the document subsets corresponding to each theme.

[0170] Those of ordinary skill in the art can understand that all or part of the processes in the methods of the above embodiments can be completed by instructing relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above methods. Among them, any reference to a memory, storage, database, or other medium used in the embodiments provided in the present application can include non-volatile and / or volatile memories. Non-volatile memories can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memories can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDR SDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), Rambus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and Rambus dynamic RAM (RDRAM), etc.

[0171] The technical features of the above embodiments can be combined arbitrarily. For the sake of brevity of description, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, it should be considered as the scope described in this specification.

[0172] The above-described embodiments merely represent several implementation manners of the present application. The description is relatively specific and detailed, but it should not be construed as a limitation on the scope of the invention patent. It should be noted that for those of ordinary skill in the art, without departing from the concept of the present application, several modifications and improvements can still be made, and these all belong to the protection scope of the present application. Therefore, the protection scope of the patent of the present application should be subject to the appended claims.

Claims

1. A method for analyzing the function of electronic appliances, characterized in that: include: Acquire first information data of a function module to be analyzed, where the first information data indicates user information involved in the function module to be analyzed; According to the first information data, obtaining a document subset corresponding to each topic; Determining target keywords of the first information data under each topic according to the document subset; Obtaining a first matching degree under each topic according to the target keyword and the reference keyword under the topic, wherein the reference keyword under the topic is obtained according to second information data of a history function module, and the second information data indicates user information involved in the history function module; The information relevance of the functional module to be analyzed is determined according to the first matching degree.

2. The electronic and electrical appliance function analysis method according to claim 1, characterized in that: Determining the target keyword of the first information data under each topic according to the document subset includes: Determine the word frequency and inverse document frequency of candidate keywords under the topic according to the document subset corresponding to the topic; Determining the weight of each candidate keyword according to the word frequency and the inverse document frequency; Based on the weight, the target keyword is determined from the candidate keywords.

3. The electronic and electrical appliance function analysis method according to claim 2, characterized in that: The step of determining the target keyword from the candidate keywords based on the weight includes: According to a preset number, the candidate keyword with a large weight is determined as the target keyword.

4. The electronic and electrical appliance function analysis method according to claim 2, characterized in that: Before determining the word frequency and inverse document frequency of the candidate keywords under the topic, the method further includes: Perform word segmentation according to the document subset to obtain word units; The candidate keyword is obtained according to the part of speech of the word unit, wherein the candidate keyword is a word unit combination of verb+noun.

5. The electronic and electrical appliance function analysis method according to claim 1, characterized in that: The obtaining a first matching degree under each topic according to the target keyword and the reference keyword under the topic includes: Determine repeated keywords under the topic according to the target keywords and the reference keywords under the topic; The first matching degree is obtained according to the proportion of the repeated keywords in the target keywords.

6. The electronic appliance function analysis method according to claim 1, characterized in that: After determining the information relevance of the functional module to be analyzed, the method further includes: When the first matching degree is greater than a correlation threshold, determining the reusability of the to-be-analyzed functional module includes: Determine overlapping function points according to the target function points of the function module to be analyzed and the reference function points of the historical function modules; Obtaining a second matching degree according to a proportion of the overlapping function points in the target function points; The reusability of the functional module to be analyzed is determined according to the second matching degree.

7. The electronic and electrical appliance function analysis method according to claim 1, characterized in that: The step of obtaining a document subset corresponding to each topic according to the first information data includes: Based on the document topic generation probability model, the document subset corresponding to each topic is obtained.

8. An electronic appliance function analysis device, characterized in that: The device comprises: An acquisition module, used for acquiring first information data of a function module to be analyzed, wherein the first information data indicates user information involved in the function module to be analyzed; A topic allocation module, used for obtaining a document subset corresponding to each topic according to the first information data; A keyword identification module, used to determine the target keyword of the first information data under each topic according to the document subset; An analysis module is used to obtain a first matching degree under each topic based on the target keyword and the reference keyword under the topic, wherein the reference keyword under the topic is obtained based on second information data of a historical function module, and the second information data indicates user information involved in the historical function module; based on the first matching degree, determine the information relevance of the function module to be analyzed.

9. A computer device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the method according to any one of claims 1 to 7 is implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method according to any one of claims 1 to 7 is implemented.

Images