Adaptive commodity classification method based on AI identification of large model

Abstract

The invention relates to the field of label information analysis, in particular to an adaptive commodity classification method based on AI identification of a large model, which comprises the following steps: determining a text reference state of each related analysis text according to a text coincidence parameter and an evaluation reference index; determining an effective analysis strategy according to the text reference state of each related analysis text; when phrase reference analysis is carried out on the text analysis set, determining a text division mode according to the evaluation reference index and the related evaluation coefficient; when effective evaluation analysis is carried out on the related evaluation keywords, effective evaluation phrases are determined according to the text correlation coefficient and the key user proportion, and the evaluation key coefficient of each effective evaluation phrase is determined according to the text correlation degree and the user reference coefficient; under the condition that evaluation extraction is completed, a label updating strategy is determined according to the effective key parameters and the reference key coefficients so as to determine an early warning updating label, and the reliability of an optimization result of label data is improved.

Description

Technical Field

[0001] The present invention relates to the field of label information analysis, and in particular to an adaptive commodity classification method based on AI recognition of a large model. Background Art

[0002] Fine classification of goods can effectively improve the communication efficiency between consumers and merchants. The process of e-commerce platform classification of goods is usually based on the product label information provided by merchants. However, in order to increase the probability of goods being retrieved or due to insufficient understanding of product classification, merchants may provide low-quality product label information, resulting in low accuracy of product classification. Optimizing label information through the information content of various types of product reviews can effectively improve the accuracy of product classification results. However, the review content often has low content quality and overlapping reviews. Therefore, how to ensure the effectiveness of the review content used to optimize the label information is a problem that needs to be urgently solved by technical personnel in this field.

[0003] Chinese patent publication number CN117973392A discloses a method for automatic data collection based on web page tag analysis. The method includes the following steps: extracting inter-cluster structural features from the acquired target web page data to obtain initial DOM tree structure feature data; monitoring page dynamic loading based on the initial DOM tree structure feature data to generate page dynamic loading data; performing dynamic tag combination processing based on the page dynamic loading data to obtain dynamic tag combination data; identifying brand word-of-mouth tags based on the dynamic tag combination data to generate brand word-of-mouth tag data; performing adaptive collection optimization based on the brand word-of-mouth tag data to generate an adaptive page collection strategy; performing multimodal brand data collection based on the adaptive page collection strategy, and performing product word-of-mouth prediction to obtain product word-of-mouth prediction data. However, the above technical solution has the following problems: it fails to screen effective information for the comment information based on which the tag data is optimized, resulting in low reliability of the optimization results for the tag data. Summary of the invention

[0004] To this end, the present invention provides an adaptive commodity classification method based on AI recognition of a large model, so as to overcome the problem that the prior art fails to screen effective information based on the review information when optimizing the label data, resulting in low reliability of the optimization results of the label data, and further resulting in low accuracy of the commodity classification results.

[0005] To achieve the above object, the present invention provides an adaptive commodity classification method based on AI recognition of a large model, comprising: Obtain relevant analysis texts of target category products, and determine the text reference status of each relevant analysis text according to the text overlap parameter and the evaluation reference index; Determining an effective analysis strategy according to the text reference status of each relevant analysis text, the effective analysis strategy including performing phrase reference analysis on the text analysis set, and performing effective evaluation analysis on relevant evaluation keywords; When performing phrase reference analysis on a text analysis set, a text division method is determined according to an evaluation reference index and a related evaluation coefficient, and a setting method of the evaluation key coefficient is determined according to the text division method, wherein the text division method is to determine a text analysis set according to an evaluation relevance, or to determine a text analysis set according to an evaluation reference tendency coefficient and a reference related evaluation coefficient; When conducting effective evaluation analysis on relevant evaluation keywords, determine effective evaluation phrases based on text relevance coefficients and key user proportions, and determine the evaluation key coefficients of each effective evaluation phrase based on text relevance and user reference coefficients; Under the condition that the evaluation extraction is completed, the label update strategy is determined according to the effective key parameters and the reference key coefficients to determine the warning update label. The label update strategy is to determine the evaluation phrase set of each label keyword according to the tendency coefficient difference value, or to determine the update optimization coefficient of each label keyword according to the evaluation tendency coefficient of the effective matching phrase and the evaluation key coefficient.

[0006] Further, the text reference status of each relevant analysis text is determined according to the text overlap parameter and the evaluation reference index; If a text overlap parameter of a related analysis text is greater than a preset text overlap parameter or an evaluation reference index is less than or equal to a preset evaluation reference index, the related analysis text is determined to be in a first preset text reference state; If the text overlap parameter of a correlation analysis text is less than or equal to the preset text overlap parameter and the evaluation reference index is greater than the preset evaluation reference index, it is determined that the correlation analysis text is in the second preset text reference state.

[0007] Further, determining effective analysis strategies based on the text reference status of each relevant analysis text; If a related analysis text is in the first preset text reference state, performing phrase reference analysis on the text analysis set; If a related analysis text is in the second preset text reference state, an effective evaluation analysis is performed on the related evaluation keywords.

[0008] Furthermore, the division method of the text analysis set is determined according to the text division coefficient; If the text division coefficient of a related analysis text is greater than the preset text division coefficient, a text analysis set is determined according to the evaluation relevance; If the text division coefficient of a related analysis text is less than or equal to the preset text division coefficient, determine the text analysis set according to the evaluation reference tendency coefficient and the reference related evaluation coefficient; The text division coefficient is determined according to the evaluation reference index and the relevant evaluation coefficient.

[0009] Furthermore, for a single text analysis set, the phrase reference analysis process includes: Determine effective evaluation phrases according to text correlation coefficient and related evaluation coefficient; Determine the setting method of the evaluation key coefficient of the effective evaluation phrase according to the division method of the text analysis set; If the text analysis set is determined according to the evaluation relevance, the evaluation key coefficient for each valid evaluation phrase of the text analysis set is set according to the reference coincidence coefficient, and the evaluation key coefficient is negatively correlated with the reference coincidence coefficient; If the text analysis set is determined based on the reference tendency coefficient and the reference correlation coefficient, the evaluation key coefficient for each valid evaluation phrase of the text analysis set is set based on the set abnormal tendency parameter and the set reference correlation coefficient, and the evaluation key coefficient is positively correlated with the set evaluation index.

[0010] Further, extract relevant evaluation phrases from each relevant analysis text in the second preset text reference state, and determine the evaluation validity coefficient of the evaluation phrase according to the text correlation coefficient and the proportion of key users; The evaluation phrases whose evaluation effectiveness coefficient is greater than the preset evaluation effectiveness coefficient are recorded as effective evaluation phrases, and effective evaluation analysis is performed on the evaluation key coefficient of each effective evaluation phrase.

[0011] Furthermore, the effective evaluation analysis process for a single effective evaluation phrase includes: Detecting the user reference coefficient of the relevant analysis text of the effective evaluation phrase, wherein the user reference coefficient is determined according to the user evaluation quality parameter and the historical category overlap parameter; Determine the evaluation key coefficient of the effective evaluation phrase according to the text relevance and the user reference coefficient; The evaluation key coefficient is positively correlated with the text relevance and the user reference coefficient respectively.

[0012] Further, under the evaluation extraction completion condition, the label update strategy is determined according to the effective key parameters and the reference key coefficients; If the effective key parameter is greater than the preset effective key parameter or the reference key coefficient is greater than the preset reference key coefficient, the evaluation phrase set of each tag keyword is determined according to the difference value of the tendency coefficient; If the effective key parameter is less than or equal to the preset effective key parameter and the reference key coefficient is less than or equal to the preset reference key coefficient, then the update optimization coefficient of each tag keyword is determined according to the evaluation tendency coefficient of the effective matching phrase and the evaluation key coefficient; The evaluation extraction completion condition is that all relevant analysis texts of the target category products have completed effective key analysis.

[0013] Furthermore, for a single tag keyword, an update optimization coefficient of each tag keyword is determined according to the tendency conflict coefficient of each evaluation phrase set and the set reference key coefficient; The update optimization coefficient is positively correlated with the tendency conflict coefficient and the set reference key coefficient respectively; The difference value of the tendency coefficient of any evaluation phrase set is smaller than the preset difference value of the tendency coefficient.

[0014] Further, when determining the update optimization coefficient of each tag keyword according to the evaluation tendency coefficient and the evaluation key coefficient of the effective matching phrase, the update optimization coefficient is determined according to the reference tendency parameter and the relevant key coefficient; The update optimization coefficient is positively correlated with the relevant matching parameter and the relevant key coefficient respectively; The early warning update label is determined according to the update optimization coefficient of each label keyword, and the label keyword whose update optimization coefficient is greater than the preset update optimization coefficient is recorded as the early warning update label.

[0015] Compared with the prior art, the beneficial effect of the present invention lies in that the technical solution of the present invention determines a targeted and effective analysis strategy based on the text overlap parameters of the relevant analysis text of the target classified goods and the evaluation reference index, so that the method of extracting effective evaluation phrases is more in line with the actual text situation, so as to screen the evaluation content and improve the effectiveness of the text used for label optimization. The present invention improves the reliability of the optimization results of the label data.

[0016] Furthermore, the present invention determines the text reference status of each relevant analysis text based on the text overlap parameter and the evaluation reference index to distinguish the proportion of content available for subsequent label optimization and whether there are repeated comments in different relevant analysis texts, so as to characterize the reference quality of the evaluation content contained in the relevant analysis text, and determines the subsequent effective analysis strategy based on the text reference status to avoid interference in the label optimization process caused by repeated evaluation phrases with low reference value, thereby improving the effectiveness of the text used for label optimization.

[0017] Furthermore, the present invention determines a text analysis set based on a text division coefficient, and determines a setting method of an evaluation key coefficient of an extracted effective evaluation phrase for different text analysis sets. The text division coefficient is determined by an evaluation reference index and a relevant evaluation coefficient to determine the content related to label information and target classified commodities contained in the text. In this way, relevant analysis texts in a first preset text reference state are combined, and the extraction of effective evaluation phrases is completed, thereby reducing the interference of repeated content on the label optimization process and improving the efficiency of the effective analysis process.

[0018] Furthermore, the present invention extracts relevant evaluation phrases for each relevant analysis text in the second preset text reference state, and performs effective evaluation analysis on the evaluation key coefficient of each effective evaluation phrase. During the effective evaluation analysis, for content with higher text quality, its users' historical evaluations are analyzed, and the evaluation key coefficients of the effective evaluation phrases are set accordingly. The present invention improves the reliability of the optimization results for label data. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] Figure 1 A schematic diagram of an adaptive commodity classification method based on AI recognition of a large model according to the present invention; Figure 2 A flowchart of the present invention for determining the text reference status of each relevant analysis text according to the text coincidence parameter and the evaluation reference index; Figure 3 A flow chart of the present invention for determining an effective analysis strategy according to the text reference status of each relevant analysis text; Figure 4 The present invention is a flow chart of determining a division method of a text analysis set according to a text division coefficient. DETAILED DESCRIPTION

[0020] In order to make the objects and advantages of the present invention more clearly understood, the present invention is further described below in conjunction with embodiments; it should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0021] The preferred embodiments of the present invention are described below with reference to the accompanying drawings. It should be understood by those skilled in the art that these embodiments are only used to explain the technical principles of the present invention and are not intended to limit the protection scope of the present invention.

[0022] It should be noted that, in the description of the present invention, terms such as "up", "down", "left", "right", "inside" and "outside" indicating directions or positional relationships are based on the directions or positional relationships shown in the drawings. This is merely for the convenience of description and does not indicate or imply that the device or element must have a specific orientation, be constructed and operated in a specific orientation. Therefore, it cannot be understood as a limitation on the present invention.

[0023] In addition, it should be noted that in the description of the present invention, unless otherwise clearly specified and limited, the terms "installed", "connected", and "connected" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal communication of two components. For those skilled in the art, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0024] See also Figures 1 to 4 As shown, the present invention provides an adaptive commodity classification method based on AI recognition of a large model, comprising: Obtain relevant analysis texts of target category products, and determine the text reference status of each relevant analysis text according to the text overlap parameter and the evaluation reference index; Determining an effective analysis strategy according to the text reference status of each relevant analysis text, the effective analysis strategy including performing phrase reference analysis on the text analysis set, and performing effective evaluation analysis on relevant evaluation keywords; When performing phrase reference analysis on a text analysis set, a text division method is determined according to an evaluation reference index and a related evaluation coefficient, and a setting method of the evaluation key coefficient is determined according to the text division method, wherein the text division method is to determine a text analysis set according to an evaluation relevance, or to determine a text analysis set according to an evaluation reference tendency coefficient and a reference related evaluation coefficient; When conducting effective evaluation analysis on relevant evaluation keywords, determine effective evaluation phrases based on text relevance coefficients and key user proportions, and determine the evaluation key coefficients of each effective evaluation phrase based on text relevance and user reference coefficients; Under the condition that the evaluation extraction is completed, the label update strategy is determined according to the effective key parameters and the reference key coefficients to determine the warning update label. The label update strategy is to determine the evaluation phrase set of each label keyword according to the tendency coefficient difference value, or to determine the update optimization coefficient of each label keyword according to the evaluation tendency coefficient of the effective matching phrase and the evaluation key coefficient.

[0025] Among them, the present invention is used to update and optimize the product label information involved in the product classification process, record the products that undergo a single product label information update and optimization as target classified products, and obtain relevant comment texts for the target classified products. The relevant comment texts are evaluation contents of the target classified products by the purchasing users of the target classified products. How to obtain the relevant comment texts is easy for technical personnel in this field to understand. The texts posted by the purchasing users on the product purchasing platform they use can be recorded as relevant comment texts, which will not be elaborated here. In the present invention, each product is provided with a preset category, and the categories of the preset categories include but are not limited to: household appliances, digital devices, clothing, and beauty products.

[0026] The relevant comment text of the target classification product is recorded as the relevant analysis text, and the product description text of the target classification product itself is recorded as the label text. In the present invention, AI recognition is performed on the relevant analysis text and the label text by completing the trained phrase recognition model to obtain label keywords and evaluation phrases. The evaluation tendency coefficient of each evaluation phrase is determined according to the product evaluation score corresponding to the relevant analysis text. For a single evaluation phrase, the evaluation tendency coefficient is the average value of the product evaluation scores of the relevant analysis text containing the evaluation phrase. The product evaluation score is the evaluation score made for the product when the relevant analysis text is released. How to obtain the product evaluation score is content that is easy to understand for technicians in this field and will not be elaborated here. The process of AI recognition for label keywords and evaluation phrases is based on the trained phrase recognition model. How to train the phrase recognition model is easy for technicians in this field to understand. The phrase recognition model training process includes: pre-training the phrase recognition model using large-scale unsupervised data, learning the general representation of the language by predicting the next word task, preparing labeled analysis text and label text data sets, these data need to be cleaned and labeled, fine-tuning on the basis of completing the pre-trained phrase recognition model, initializing the model parameters to be the same as the pre-trained phrase recognition model, inputting the analysis text into the model, and the model outputs the predicted label keywords and evaluation phrases. By calculating the loss between the predicted result and the true label (such as cross entropy loss), the model parameters are adjusted using the back propagation algorithm to minimize the loss. At the same time, it is necessary to adjust the learning rate, batch size and other hyperparameters to optimize the training effect of the model. Users can set the training process of the phrase recognition model according to actual needs. This is easy for technicians in this field to understand and will not be repeated here. The content of the evaluation phrase in the present invention includes but is not limited to: high power consumption, high noise and allergies, and the content of the label keywords in the present invention includes but is not limited to: energy consumption, quiet and gentle.

[0027] The present invention uses several label optimization records, and any label optimization record records the number of relevant analysis texts of repeated continuous paragraphs in the process of updating and optimizing label information for a target classified product at least once, the number of words in each repeated continuous paragraph, the reference evaluation coefficient, text overlap parameter, evaluation reference index, text division coefficient, evaluation relevance, set difference coefficient, effective evaluation parameter, evaluation effectiveness coefficient, user evaluation quality parameter, effective key parameter, reference key coefficient, update optimization coefficient and tendency coefficient difference value, and each label optimization record corresponds to a qualified mark, which records whether the accuracy of the label information optimization result meets the user's needs. It can be understood that the user can determine whether the accuracy of the label information optimization result meets the needs based on self-set indicators. For example, the self-set indicator can be but is not limited to the product recommendation accuracy, and the product recommendation accuracy is the user's evaluation satisfaction collected in the form of a questionnaire after the label information optimization is completed.

[0028] Specifically, the text reference status of each relevant analysis text is determined based on the text overlap parameter and the evaluation reference index; If a text overlap parameter of a related analysis text is greater than a preset text overlap parameter or an evaluation reference index is less than or equal to a preset evaluation reference index, the related analysis text is determined to be in a first preset text reference state; If the text overlap parameter of a correlation analysis text is less than or equal to the preset text overlap parameter and the evaluation reference index is greater than the preset evaluation reference index, it is determined that the correlation analysis text is in the second preset text reference state.

[0029] Among them, for a single related analysis text, the text overlap parameter = the sum of the number of words in each repeated continuous paragraph / the total number of words in the related analysis text. For a continuous paragraph existing in the related analysis text, if the number of related analysis texts existing in the continuous paragraph is greater than the preset number of repeated texts, the continuous paragraph is recorded as a repeated continuous paragraph. The continuous paragraph is a text paragraph containing more than the preset number of consecutive words. The text paragraph is composed of one or more sentences. The related analysis text is separated according to line breaks, spaces or punctuation marks to obtain a number of text paragraphs. The user can determine the values ​​of the preset number of repeated texts and the preset number of consecutive words according to the actual work scenario. For example, the user can set it according to the label optimization record. A method for determining the value of the preset number of repeated texts is provided. The minimum value of the number of related analysis texts in each repeated continuous paragraph in the label optimization record that meets the user's requirements for the accuracy of the label information optimization result is recorded as the preset number of repeated texts. A method for determining the value of the preset number of consecutive words is provided. The average value of the number of words in each repeated continuous paragraph in the label optimization record that meets the user's requirements for the accuracy of the label information optimization result is recorded as the preset number of consecutive words. The evaluation reference index is the number of reference evaluation phrases contained in the relevant analysis text. The reference evaluation phrase is an evaluation phrase whose reference evaluation coefficient is greater than a preset reference evaluation coefficient. For a single evaluation phrase, the reference evaluation coefficient is the maximum value of the number of times the evaluation phrase is used as an effective matching phrase for each label keyword of the target classification product. The value of the preset reference evaluation coefficient can be determined by the user according to the actual working scenario. For example, the user can set it according to the label optimization record. The higher the user's accuracy requirement for the label information optimization result, the larger the value of the preset reference evaluation coefficient. A method for setting the value of the preset reference evaluation coefficient is provided, and the minimum value of the reference evaluation coefficient of each reference evaluation phrase in the label optimization record that meets the user's accuracy requirement for the label information optimization result is recorded as the preset reference evaluation coefficient. The values ​​of the preset text overlap parameter and the preset evaluation reference index can be determined by the user according to the actual working scenario. For example, the user can set them according to the label optimization record. The higher the user's requirement for the accuracy of the label information optimization result, the smaller the value of the preset text overlap parameter and the larger the value of the preset evaluation reference index. A method for determining the value of the preset text overlap parameter is provided, and the minimum value of the text overlap parameter of the relevant analysis text in the first preset text reference state in the label optimization record that meets the user's requirement for the accuracy of the label information optimization result is recorded as the preset text overlap parameter. A method for determining the value of the preset evaluation reference index is provided, and the minimum value of the evaluation reference index of the relevant analysis text in the first preset text reference state in the label optimization record that meets the user's requirement for the accuracy of the label information optimization result is recorded as the preset evaluation reference index.

[0030] Specifically, effective analysis strategies are determined based on the textual reference status of each relevant analysis text; If a related analysis text is in the first preset text reference state, performing phrase reference analysis on the text analysis set; If a related analysis text is in the second preset text reference state, an effective evaluation analysis is performed on the related evaluation keywords.

[0031] Specifically, the division method of the text analysis set is determined according to the text division coefficient; If the text division coefficient of a related analysis text is greater than the preset text division coefficient, a text analysis set is determined according to the evaluation relevance; If the text division coefficient of a correlation analysis text is less than or equal to the preset text division coefficient, determine the text analysis set according to the evaluation reference tendency coefficient and the reference correlation coefficient; The text division coefficient is determined according to the evaluation reference index and the relevant evaluation coefficient.

[0032] Among them, for a single related analysis text, the text division coefficient = ln (evaluation reference index × reference related evaluation coefficient), the reference related evaluation coefficient is the average value of the related evaluation coefficients of each evaluation phrase contained in the related analysis text, for a single evaluation phrase, the related evaluation coefficient is the product of the category related quantity and the category related frequency, the category related quantity is the number of related category products of the evaluation phrase, the products that have the evaluation phrase in the related analysis text and are the same as the preset category of the target classification product are recorded as related category products of the evaluation phrase, the category related frequency is the average value of the number of related analysis texts that have the evaluation phrase for each related category product, the value of the preset text division coefficient can be determined by the user according to the actual work scenario, for example, the user can set it according to the label optimization record, and a method for determining the value of the preset text division coefficient is provided, the label optimization record of the text analysis set determined according to the evaluation relevance is recorded as the division reference record, and the minimum value of the text division coefficient of the related analysis text in the division reference record that meets the user's requirements for the accuracy of the label information optimization result is recorded as the preset text division coefficient; The evaluation relevance of any text analysis set determined according to the evaluation relevance is greater than the preset evaluation relevance, evaluation relevance = the number of overlapping evaluation phrases in the text analysis set / the number of evaluation phrases included in the text analysis set. For a single evaluation phrase, the related analysis text of the evaluation phrase is recorded as the associated text. If the number of associated texts of the evaluation phrase in a text analysis set including the evaluation phrase is greater than 1, the evaluation phrase is recorded as the overlapping evaluation phrase of the text analysis set. The value of the preset evaluation relevance can be determined by the user according to the actual work scenario. For example, the user can set it according to the label optimization record. The higher the user's accuracy requirement for the label information optimization result, the greater the value of the preset evaluation relevance. A method for setting the value of the preset evaluation relevance is provided, and the average value of the evaluation relevance of each text analysis set in the divided reference record that meets the user's accuracy requirement for the label information optimization result is recorded as the preset evaluation relevance. The set difference coefficient of any text analysis set determined according to the evaluation reference tendency coefficient and the reference correlation coefficient is less than the preset set difference coefficient. For a single text analysis set, the set difference coefficient is the sum of the products of the tendency coefficient difference value and the correlation coefficient difference value and the corresponding difference influence coefficient. , n is the number of relevant analysis texts contained in the text analysis set, is the reference tendency coefficient of the i-th related analysis text in the text analysis set, is the average value of the reference tendency coefficients of each related analysis text in the text analysis set. For a single related analysis text, the reference tendency coefficient is the average value of the evaluation tendency coefficients of each comment phrase contained in the related analysis text. , is the reference correlation coefficient of the i-th related analysis text in the text analysis set, is the average value of the reference correlation coefficients of each related analysis text in the text analysis set, the reference correlation coefficient is the average value of the related evaluation coefficients of each comment phrase contained in the related analysis text, the tendency coefficient difference value and the value of the difference influence coefficient corresponding to the correlation coefficient difference value can be determined by the user according to the actual work scenario, and a value of the difference influence coefficient corresponding to the tendency coefficient difference value is provided, and the value of the difference influence coefficient corresponding to the tendency coefficient difference value is 0.5, and a value of the difference influence coefficient corresponding to the correlation coefficient difference value is provided, and the value of the difference influence coefficient corresponding to the correlation coefficient difference value is 0.5; The value of the preset set difference coefficient can be determined by the user according to the actual work scenario. For example, the user can set it according to the label optimization record. The higher the user's requirement for the accuracy of the label information optimization result, the smaller the value of the preset set difference coefficient. A method for determining the value of the preset set difference coefficient is provided. The label optimization record of the text analysis set determined according to the evaluation tendency coefficient and the relevant evaluation coefficient is recorded as a reference difference record, and the maximum value of the set difference coefficient of the text analysis set in the reference difference record that meets the user's requirement for the accuracy of the label information optimization result is recorded as the preset set difference coefficient.

[0033] Specifically, for a single text analysis set, the phrase reference analysis process includes: Determine effective evaluation phrases according to text correlation coefficient and related evaluation coefficient; Determine the setting method of the evaluation key coefficient of the effective evaluation phrase according to the division method of the text analysis set; If the text analysis set is determined according to the evaluation relevance, the evaluation key coefficient for each valid evaluation phrase of the text analysis set is set according to the reference coincidence coefficient, and the evaluation key coefficient is negatively correlated with the reference coincidence coefficient; If the text analysis set is determined based on the reference tendency coefficient and the reference correlation coefficient, the evaluation key coefficient for each valid evaluation phrase of the text analysis set is set based on the set abnormal tendency parameter and the set reference correlation coefficient, and the evaluation key coefficient is positively correlated with the set evaluation index.

[0034] Among them, for a single text analysis set, the effective evaluation phrase is an evaluation phrase whose effective evaluation parameter is greater than a preset effective evaluation parameter. For a single evaluation phrase, the effective evaluation parameter is the product of a text correlation coefficient and a relevant evaluation coefficient. The text correlation coefficient is the number of relevant analysis texts in the text analysis set that contain the evaluation phrase. The value of the preset effective evaluation parameter can be determined by the user according to the actual work scenario. For example, the user can set it according to the label optimization record. The higher the user's accuracy requirement for the label information optimization result, the larger the value of the preset effective evaluation parameter. A method for setting the value of the preset effective evaluation parameter is provided, and the minimum value of the effective evaluation parameter of the effective evaluation phrase in the division reference record that meets the user's accuracy requirement for the label information optimization result is recorded as the preset effective evaluation parameter; If a text analysis set is determined according to the evaluation relevance, the evaluation key coefficient of each valid evaluation phrase contained in the text analysis set is determined according to the reference overlap coefficient, and the reference overlap coefficient is the average value of the text overlap parameters of each related analysis text in the text analysis set; if a text analysis set is determined according to the evaluation sentiment coefficient and the related evaluation coefficient, the evaluation key coefficient of each valid evaluation phrase contained in the text analysis set is determined according to the set abnormal sentiment parameter and the set reference correlation coefficient, and the set evaluation index is determined according to the set abnormal sentiment parameter and the set reference correlation coefficient, and the set evaluation index = set reference correlation coefficient × index weight coefficient corresponding to the set reference correlation coefficient - set abnormal tendency parameter × set abnormal The index weight coefficient corresponding to the normal tendency parameter, for a single text analysis set, the set reference correlation coefficient is the average value of the reference correlation coefficients of each relevant analysis text in the text analysis set, and the set abnormal tendency parameter is the absolute value of the difference between the average value of the reference tendency coefficients of each relevant analysis text in the text analysis set and the average value of the reference tendency coefficients of each relevant analysis text of the target category product. The values ​​of the set reference correlation coefficient and the index weight coefficient corresponding to the set abnormal tendency parameter can be determined by the user according to the actual work scenario, and a value of the index weight coefficient corresponding to the set reference correlation coefficient is provided as 0.6, and a value of the index weight coefficient corresponding to the set abnormal tendency parameter is provided as 0.4.

[0035] Specifically, extract relevant evaluation phrases for each relevant analysis text in the second preset text reference state, and determine the evaluation validity coefficient of the evaluation phrase according to the text correlation coefficient and the proportion of key users; The evaluation phrases whose evaluation effectiveness coefficient is greater than the preset evaluation effectiveness coefficient are recorded as effective evaluation phrases, and effective evaluation analysis is performed on the evaluation key coefficient of each effective evaluation phrase.

[0036] Among them, for a single evaluation phrase, the evaluation effectiveness coefficient is the sum of the products of the text correlation coefficient and the key user proportion and the corresponding evaluation influence coefficient, the key user proportion = the number of key users / the number of related users, the related users are the purchasing users corresponding to the related analysis text containing the evaluation phrase, the key users are the related users whose user evaluation quality parameters are greater than the preset user evaluation quality parameters, the values ​​of the text correlation coefficient and the evaluation influence coefficient corresponding to the key user proportion can be determined by the user according to the actual work scenario, and a text correlation coefficient and the evaluation influence coefficient corresponding to the key user proportion are provided. The value of the evaluation influence coefficient corresponding to the text correlation coefficient is 0.4, and the value of the evaluation influence coefficient corresponding to the key user proportion is 0.6. For a single related user, the user evaluation quality parameter = the number of optimization basis texts / the number of historical evaluation texts, the historical evaluation texts are the related analysis texts published by the related users in the label optimization records, and the optimization basis texts are the historical evaluation texts with valid evaluation phrases in the corresponding label optimization records; The values ​​of the preset evaluation effectiveness coefficient and the preset user evaluation quality parameter can be determined by the user according to the actual work scenario. For example, the user can set them according to the label optimization record. The higher the user's accuracy requirement for the label information optimization result, the larger the value of the preset evaluation effectiveness coefficient and the larger the value of the preset user evaluation quality parameter. A method for determining the value of the preset evaluation effectiveness coefficient is provided, and the label optimization record for extracting relevant evaluation phrases for the relevant analysis text in the second preset text reference state is recorded as a valid analysis record, and the minimum value of the evaluation effectiveness coefficient of the effective evaluation phrases in the effective analysis record that meets the user's accuracy requirement for the label information optimization result is recorded as the preset evaluation effectiveness coefficient. A method for determining the value of the preset user evaluation quality parameter is provided, and the average value of the user evaluation quality parameters of each key user in the effective analysis record that meets the user's accuracy requirement for the label information optimization result is recorded as the preset user evaluation quality parameter.

[0037] Specifically, the effective evaluation analysis process for a single effective evaluation phrase includes: Detecting the user reference coefficient of the relevant analysis text of the effective evaluation phrase, wherein the user reference coefficient is determined according to the user evaluation quality parameter and the historical category overlap parameter; Determine the evaluation key coefficient of the effective evaluation phrase according to the text relevance and the user reference coefficient; The evaluation key coefficient is positively correlated with the text relevance and the user reference coefficient respectively.

[0038] Among them, for a single valid evaluation phrase, its user reference coefficient is the sum of the reference evaluation quality parameter and the historical category overlap parameter, the historical category overlap parameter = the number of overlapping category texts of the relevant users of the valid evaluation phrase / the number of historical evaluation texts of the relevant users of the valid evaluation phrase. If the product category corresponding to a historical evaluation text is the same as the target category product, the historical evaluation text is recorded as the overlapping category text. The historical evaluation text is the relevant comment text of each product in the label optimization record. The reference evaluation quality parameter is the average value of the user evaluation quality parameters of each relevant user of the valid evaluation phrase. The text relevance is the number of relevant analysis texts containing the valid evaluation phrase. The evaluation key coefficient is the sum of the text relevance and the user reference coefficient.

[0039] Specifically, under the evaluation extraction completion condition, the label update strategy is determined based on the effective key parameters and the reference key coefficients; If the effective key parameter is greater than the preset effective key parameter or the reference key coefficient is greater than the preset reference key coefficient, the evaluation phrase set of each tag keyword is determined according to the difference value of the tendency coefficient; If the effective key parameter is less than or equal to the preset effective key parameter and the reference key coefficient is less than or equal to the preset reference key coefficient, then the update optimization coefficient of each tag keyword is determined according to the evaluation tendency coefficient of the effective matching phrase and the evaluation key coefficient; The evaluation extraction completion condition is that all relevant analysis texts of the target category products have completed effective key analysis.

[0040] Among them, the effective key parameter is the number of effective evaluation phrases determined, the reference key coefficient is the average value of the evaluation key coefficients of each effective evaluation phrase, and the values ​​of the preset effective key parameter and the preset reference key coefficient can be determined by the user according to the actual work scenario. For example, the user can set it according to the label optimization record, and provide a method for taking the value of the preset effective key parameter. The label optimization record of the evaluation phrase set of each label keyword determined according to the tendency coefficient difference value is recorded as the first update record, and the minimum value of the effective key parameter in the first update record that meets the user's requirements for the accuracy of the label information optimization result is recorded as the preset effective key parameter. A method for taking the value of the preset reference key coefficient is provided, and the minimum value of the reference key coefficient in the first update record that meets the user's requirements for the accuracy of the label information optimization result is recorded as the preset reference key coefficient; each relevant analysis text of the target category product has completed the effective key analysis, and the effective evaluation phrases have been extracted, and the evaluation key coefficients of each effective evaluation phrase have been set.

[0041] Specifically, for a single tag keyword, the update optimization coefficient of each tag keyword is determined according to the tendency conflict coefficient of each evaluation phrase set and the set reference key coefficient; The update optimization coefficient is positively correlated with the tendency conflict coefficient and the reference key coefficient respectively; The difference value of the tendency coefficient of any evaluation phrase set is smaller than the preset difference value of the tendency coefficient.

[0042] Among them, for a single evaluation phrase set, the difference value of the tendency coefficient , m is the number of valid matching phrases contained in the evaluation phrase set, pj is the evaluation tendency coefficient of the jth valid matching phrase in the evaluation phrase set, is the average value of the evaluation tendency coefficients of the valid matching phrases contained in the evaluation phrase set. The value of the preset tendency coefficient difference value can be determined by the user according to the actual work scenario. For example, the user can set it according to the label optimization record. A method for determining the preset tendency coefficient difference value is provided. The minimum value of the tendency coefficient difference value of the evaluation phrase set in the first update record that meets the user's accuracy requirements for the label information optimization result is recorded as the preset tendency coefficient difference value. For a single tag keyword, the update optimization coefficient , h is the number of evaluation phrase sets of the tag keyword, as well as are the tendency conflict coefficient of the sth evaluation phrase set of the tag keyword and the set reference key coefficient, respectively. as well as They are the tendency conflict coefficient and the influence coefficient corresponding to the set reference key coefficient respectively. For a single evaluation phrase set, the set reference key coefficient is the average value of the evaluation key coefficients of each valid matching phrase contained in the evaluation phrase set. The tendency conflict coefficient is the absolute value of the difference between the tendency reference value of the evaluation phrase set and the average tendency reference value. The tendency reference value is the average value of the evaluation tendency coefficients of each valid matching phrase contained in the evaluation phrase set. The average tendency reference value is the average value of the tendency reference values ​​of each evaluation phrase set of the tag keyword. The user can determine the values ​​of the influence coefficient corresponding to the tendency conflict coefficient and the set reference key coefficient according to the actual work scenario. A value of the influence coefficient corresponding to the tendency conflict coefficient is provided, and the value of the influence coefficient corresponding to the tendency conflict coefficient is 0.5. A value of the influence coefficient corresponding to the set reference key coefficient is provided, and the value of the influence coefficient corresponding to the tendency conflict coefficient is 0.5.

[0043] Specifically, when determining the update optimization coefficient of each tag keyword according to the evaluation tendency coefficient and the evaluation key coefficient of the effective matching phrase, the update optimization coefficient is determined according to the reference tendency parameter and the relevant key coefficient; The update optimization coefficient is positively correlated with the relevant matching parameter and the relevant key coefficient respectively; The early warning update label is determined according to the update optimization coefficient of each label keyword, and the label keyword whose update optimization coefficient is greater than the preset update optimization coefficient is recorded as the early warning update label.

[0044] Among them, for a single label keyword, the update optimization coefficient = ln (reference tendency parameter × related key coefficient), the reference tendency parameter is the average value of the evaluation tendency coefficients of each effective matching phrase of the label keyword, and the related key coefficient is the average value of the evaluation key coefficients of each effective matching phrase of the label keyword. The value of the preset update optimization coefficient can be determined by the user according to the actual work scenario. For example, the user can set it according to the label optimization record. The higher the user's accuracy requirement for the label information optimization result, the larger the value of the preset update optimization coefficient. A method for setting the value of the preset update optimization coefficient is provided, and the minimum value of the update optimization coefficient of each warning update label in the label optimization record that meets the user's accuracy requirement for the label information optimization result is recorded as the preset update optimization coefficient. If the target category product has a warning update label, a label update request is sent to the user, and the content of the warning update label is deleted or replaced.

[0045] So far, the technical solutions of the present invention have been described in conjunction with the preferred embodiments shown in the accompanying drawings. However, it is easy for those skilled in the art to understand that the protection scope of the present invention is obviously not limited to these specific embodiments. Without departing from the principle of the present invention, those skilled in the art can make equivalent changes or substitutions to the relevant technical features, and the technical solutions after these changes or substitutions will fall within the protection scope of the present invention.

[0046] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. An adaptive commodity classification method based on AI recognition of a large model, characterized in that: include: Obtain relevant analysis texts of target category products, and determine the text reference status of each relevant analysis text according to the text overlap parameter and the evaluation reference index; Determining an effective analysis strategy according to the text reference status of each relevant analysis text, the effective analysis strategy including performing phrase reference analysis on the text analysis set, and performing effective evaluation analysis on relevant evaluation keywords; When performing phrase reference analysis on a text analysis set, a text division method is determined according to an evaluation reference index and a related evaluation coefficient, and a setting method of the evaluation key coefficient is determined according to the text division method, wherein the text division method is to determine a text analysis set according to an evaluation relevance, or to determine a text analysis set according to an evaluation reference tendency coefficient and a reference related evaluation coefficient; When conducting effective evaluation analysis on relevant evaluation keywords, determine effective evaluation phrases based on text relevance coefficients and key user proportions, and determine the evaluation key coefficients of each effective evaluation phrase based on text relevance and user reference coefficients; Under the condition that the evaluation extraction is completed, the label update strategy is determined according to the effective key parameters and the reference key coefficients to determine the warning update label. The label update strategy is to determine the evaluation phrase set of each label keyword according to the tendency coefficient difference value, or to determine the update optimization coefficient of each label keyword according to the evaluation tendency coefficient of the effective matching phrase and the evaluation key coefficient.

2. The adaptive commodity classification method based on AI recognition of a large model according to claim 1 is characterized in that: Determine the text reference status of each relevant analysis text according to the text overlap parameter and the evaluation reference index; If a text overlap parameter of a related analysis text is greater than a preset text overlap parameter or an evaluation reference index is less than or equal to a preset evaluation reference index, the related analysis text is determined to be in a first preset text reference state; If the text overlap parameter of a correlation analysis text is less than or equal to the preset text overlap parameter and the evaluation reference index is greater than the preset evaluation reference index, it is determined that the correlation analysis text is in the second preset text reference state.

3. The adaptive commodity classification method based on AI recognition of large models according to claim 2 is characterized in that: Determine effective analysis strategies based on the textual reference status of each relevant analysis text; If a related analysis text is in the first preset text reference state, performing phrase reference analysis on the text analysis set; If a related analysis text is in the second preset text reference state, an effective evaluation analysis is performed on the related evaluation keywords.

4. The adaptive commodity classification method based on AI recognition of a large model according to claim 3 is characterized in that: The division method of the text analysis set is determined according to the text division coefficient; If the text division coefficient of a related analysis text is greater than the preset text division coefficient, a text analysis set is determined according to the evaluation relevance; If the text division coefficient of a related analysis text is less than or equal to the preset text division coefficient, determine the text analysis set according to the evaluation reference tendency coefficient and the reference related evaluation coefficient; The text division coefficient is determined according to the evaluation reference index and the relevant evaluation coefficient.

5. The adaptive commodity classification method based on AI recognition of a large model according to claim 4 is characterized in that: For a single text analysis set, the phrase reference analysis process includes: Determine effective evaluation phrases according to text correlation coefficient and related evaluation coefficient; Determine the setting method of the evaluation key coefficient of the effective evaluation phrase according to the division method of the text analysis set; If the text analysis set is determined according to the evaluation relevance, the evaluation key coefficient for each valid evaluation phrase of the text analysis set is set according to the reference coincidence coefficient, and the evaluation key coefficient is negatively correlated with the reference coincidence coefficient; If the text analysis set is determined based on the reference tendency coefficient and the reference correlation coefficient, the evaluation key coefficient for each valid evaluation phrase of the text analysis set is set based on the set abnormal tendency parameter and the set reference correlation coefficient, and the evaluation key coefficient is positively correlated with the set evaluation index.

6. The adaptive commodity classification method based on AI recognition of a large model according to claim 5 is characterized in that: Extracting relevant evaluation phrases from each relevant analysis text in the second preset text reference state, and determining the evaluation validity coefficient of the evaluation phrase according to the text correlation coefficient and the proportion of key users; The evaluation phrases whose evaluation effectiveness coefficient is greater than the preset evaluation effectiveness coefficient are recorded as effective evaluation phrases, and effective evaluation analysis is performed on the evaluation key coefficient of each effective evaluation phrase.

7. The adaptive commodity classification method based on AI recognition of a large model according to claim 6 is characterized in that: The effective evaluation analysis process for a single effective evaluation phrase includes: Detecting the user reference coefficient of the relevant analysis text of the effective evaluation phrase, wherein the user reference coefficient is determined according to the user evaluation quality parameter and the historical category overlap parameter; Determine the evaluation key coefficient of the effective evaluation phrase according to the text relevance and the user reference coefficient; The evaluation key coefficient is positively correlated with the text relevance and the user reference coefficient respectively.

8. The adaptive commodity classification method based on AI recognition of a large model according to claim 7 is characterized in that: When the evaluation extraction is completed, the effective matching phrases of each tag keyword are determined according to the evaluation related frequency and the update overlap ratio, and the tag update strategy is determined according to the effective key parameters and the reference key coefficients; If the effective key parameter is greater than the preset effective key parameter or the reference key coefficient is greater than the preset reference key coefficient, the evaluation phrase set of each tag keyword is determined according to the difference value of the tendency coefficient; If the effective key parameter is less than or equal to the preset effective key parameter and the reference key coefficient is less than or equal to the preset reference key coefficient, then the update optimization coefficient of each tag keyword is determined according to the evaluation tendency coefficient of the effective matching phrase and the evaluation key coefficient; The evaluation extraction completion condition is that all relevant analysis texts of the target category products have completed effective key analysis.

9. The adaptive commodity classification method based on AI recognition of a large model according to claim 8 is characterized in that: For a single tag keyword, determine the update optimization coefficient of each tag keyword based on the tendency conflict coefficient of each evaluation phrase set and the set reference key coefficient; The update optimization coefficient is positively correlated with the tendency conflict coefficient and the set reference key coefficient respectively; The difference value of the tendency coefficient of any evaluation phrase set is smaller than the preset difference value of the tendency coefficient.

10. The adaptive commodity classification method based on AI recognition of a large model according to claim 9 is characterized in that: When determining the update optimization coefficient of each tag keyword according to the evaluation tendency coefficient and the evaluation key coefficient of the effective matching phrase, the update optimization coefficient is determined according to the reference tendency parameter and the relevant key coefficient; The update optimization coefficient is positively correlated with the relevant matching parameter and the relevant key coefficient respectively; The early warning update label is determined according to the update optimization coefficient of each label keyword, and the label keyword whose update optimization coefficient is greater than the preset update optimization coefficient is recorded as the early warning update label.

Images