Commodity information identification method, device, storage medium and computer equipment

Abstract

The commodity information identification method, device, storage medium and computer equipment provided by the present application can perform feature analysis on the target text to determine at least one commodity feature corresponding to the commodity activity link or commodity password when monitoring the target user to copy and paste the target text containing the commodity activity link or commodity password from any e-commerce platform to the present platform; then, the present application can match the at least one commodity feature with a plurality of pre-configured processing strategies according to the preset matching rules, and determine the target processing strategy corresponding to the at least one commodity feature according to the matching results; thus, the commodity activity link or commodity password can be routed to the corresponding processor for parsing according to the target processing strategy, and the commodity or activity corresponding to the commodity activity link or commodity password can be determined according to the parsing results. This process can effectively improve the matching efficiency and reduce the time and cost of manual matching, thereby effectively improving the user experience.

Description

Technical Field

[0001] The present application relates to the field of data processing technology, and in particular to a commodity information identification method, device, storage medium and computer equipment. Background Art

[0002] In e-commerce and marketing activities, product activity links or product passwords are often used to guide users to visit specific pages or enjoy specific discounts. For example, users can paste product activity links or product passwords obtained from other e-commerce platforms to this platform. After this platform recognizes the product activity links or product passwords pasted by users, it can obtain the corresponding product information based on the recognition results for display.

[0003] At present, with the diversification of e-commerce platforms, the same product may appear on multiple e-commerce platforms, and there will be certain differences in price, channel, service, etc. The traditional product information identification method is to identify a single product information provided by a single e-commerce platform. When faced with different product information provided by diverse e-commerce platforms, the traditional identification method cannot quickly and accurately match the corresponding product information, thereby reducing the user experience. Summary of the invention

[0004] The purpose of this application is to solve at least one of the above-mentioned technical defects, especially the technical defect in the prior art that when faced with different product information provided by various e-commerce platforms, traditional identification methods cannot quickly and accurately match the corresponding product information, thereby reducing the user experience.

[0005] The present application provides a method for identifying commodity information, the method comprising:

[0006] When it is detected that a target user copies and pastes a target text containing a product activity link or a product password from any e-commerce platform to the current platform, feature analysis is performed on the target text to determine at least one product feature corresponding to the product activity link or product password;

[0007] Matching the at least one commodity feature with a plurality of pre-configured processing strategies according to a preset matching rule, and determining a target processing strategy corresponding to the at least one commodity feature according to the matching result;

[0008] The commodity activity link or commodity password is routed to a corresponding processor for parsing according to the target processing strategy, and the commodity or activity corresponding to the commodity activity link or commodity password is determined according to the parsing result.

[0009] Optionally, the performing feature analysis on the target text to determine at least one commodity feature corresponding to the commodity activity link or commodity password includes:

[0010] Performing feature analysis on the target text to split the target text into the product activity link or product password and at least one product feature;

[0011] At least one commodity feature corresponding to the commodity activity link or commodity password is extracted from the split target text.

[0012] Optionally, the feature parsing of the target text to split the target text into the commodity activity link or commodity password and at least one commodity feature includes:

[0013] The target text is feature parsed using the aviator rule engine to split the target text into the commodity activity link or commodity password and at least one commodity feature.

[0014] Optionally, the feature parsing of the target text to split the target text into the commodity activity link or commodity password and at least one commodity feature includes:

[0015] Obtaining a pre-configured deep learning model, wherein the deep learning model is obtained by training with a training text containing a product activity link or a product password as sample data and with product features corresponding to the product activity link or product password in the training text as sample labels;

[0016] The target text is input into the deep learning model to obtain a product activity link or a product password and at least one corresponding product feature in the target text output by the deep learning model.

[0017] Optionally, matching the at least one commodity feature with a plurality of pre-configured processing strategies according to a preset matching rule to obtain a matching result includes:

[0018] Performing semantic analysis on the at least one commodity feature to obtain a semantic analysis result corresponding to the at least one commodity feature;

[0019] Acquire context information corresponding to the at least one commodity feature in the target text;

[0020] According to the semantic analysis result and the context information, the at least one commodity feature is matched with a plurality of pre-configured processing strategies according to a preset matching rule to obtain a matching result.

[0021] Optionally, matching the at least one commodity feature with a plurality of pre-configured processing strategies according to a preset matching rule to obtain a matching result includes:

[0022] Obtain multiple pre-configured processing strategies and the priority of each processing strategy;

[0023] According to the priority of each processing strategy, the at least one commodity feature is matched with each processing strategy respectively to obtain a matching result.

[0024] Optionally, the method further comprises:

[0025] According to the priority of each processing strategy, when matching the at least one commodity feature with each processing strategy respectively, the matching is performed using distributed computing and parallel processing technology to obtain a matching result.

[0026] The present application also provides a commodity information identification device, comprising:

[0027] A feature analysis module, for performing feature analysis on a target text containing a product activity link or a product password copied and pasted by a target user from any e-commerce platform to the platform, and determining at least one product feature corresponding to the product activity link or product password;

[0028] A feature matching module, used to match the at least one commodity feature with a plurality of pre-configured processing strategies according to a preset matching rule, and determine a target processing strategy corresponding to the at least one commodity feature according to the matching result;

[0029] The commodity analysis module is used to route the commodity activity link or commodity password to the corresponding processor for analysis according to the target processing strategy, and determine the commodity or activity corresponding to the commodity activity link or commodity password according to the analysis result.

[0030] The present application also provides a computer-readable storage medium, in which computer-readable instructions are stored. When the computer-readable instructions are executed by one or more processors, the one or more processors execute the steps of the commodity information identification method described in any one of the above embodiments.

[0031] The present application also provides a computer device, comprising: one or more processors, and a memory;

[0032] The memory stores computer-readable instructions, and when the computer-readable instructions are executed by the one or more processors, the steps of the commodity information identification method described in any one of the above embodiments are performed.

[0033] It can be seen from the above technical solutions that the embodiments of the present application have the following advantages:

[0034] The product information identification method, device, storage medium and computer equipment provided by the present application can perform feature analysis on the target text when it is monitored that the target user has copied and pasted a target text containing a product activity link or a product password from any e-commerce platform to this platform, and determine at least one product feature corresponding to the product activity link or product password; then, the present application can match the at least one product feature with a plurality of pre-configured processing strategies according to a preset matching rule, and determine a target processing strategy corresponding to the at least one product feature based on the matching result; in this way, the product activity link or product password can be routed to the corresponding processor for parsing according to the target processing strategy, and the product or activity corresponding to the product activity link or product password can be determined based on the parsing result. During this process, the platform does not need to consider the e-commerce platform corresponding to the received target text, but only needs to match the corresponding processing strategy through product features. This can not only adapt to product activity links or product passwords sent by different e-commerce platforms, but also avoid the problem of low accuracy caused by direct matching through product activity links or product passwords. It can also achieve rapid matching of a large number of product activity links or product passwords, thereby effectively improving matching efficiency and reducing the time and cost of manual matching, allowing users to participate in product activities faster, thereby effectively improving user experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0036] Figure 1 A flowchart of a method for identifying commodity information provided in an embodiment of the present application;

[0037] Figure 2 A schematic diagram of a process for feature parsing and processing a target text provided in an embodiment of the present application;

[0038] Figure 3 A schematic diagram of the structure of a commodity information identification device provided in an embodiment of the present application;

[0039] Figure 4 A schematic diagram of the internal structure of a computer device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0040] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0041] At present, with the diversification of e-commerce platforms, the same product may appear on multiple e-commerce platforms, and there will be certain differences in price, channel, service, etc. The traditional product information identification method is to identify a single product information provided by a single e-commerce platform. When faced with different product information provided by diverse e-commerce platforms, the traditional identification method cannot quickly and accurately match the corresponding product information, thereby reducing the user experience.

[0042] Based on this, this application proposes the following technical solutions, see below for details:

[0043] In one embodiment, Figure 1 As shown, Figure 1 A flowchart of a method for identifying commodity information provided in an embodiment of the present application; the present application provides a method for identifying commodity information, which may include:

[0044] S110: When it is monitored that the target user copies and pastes a target text containing a product activity link or a product password from any e-commerce platform to the current platform, feature analysis is performed on the target text to determine at least one product feature corresponding to the product activity link or the product password.

[0045] In this step, when it is monitored that a user logged into this platform pastes a target text containing a product activity link or a product password copied from any other e-commerce platform to this platform, the user logged into this platform can be used as the target user, and the recognition rule engine of this platform can be started to process the target text, such as performing feature analysis and preprocessing operations on the target text, so as to determine one or more product features corresponding to the product activity link or product password in the target text.

[0046] Specifically, when the target user browses related product information on other e-commerce platforms and pastes the product information into this platform in the form of a product activity link or a product password, this platform can obtain the target text containing the product activity link or product password, and perform feature analysis on the target text to determine at least one product feature in the target text that corresponds to the product activity link or product password. For example, the present application can use a pre-configured related rule engine to perform feature analysis on the target text to determine the correspondence between the product activity link or product password in the target text and the product feature. Generally speaking, a product activity link or product password can correspond to one or more product features, which include but are not limited to keywords, phrases, grammatical structures, etc., which can be determined based on the text type and text structure of the product activity link or product password of different e-commerce platforms, and are not limited here.

[0047] In addition, when performing feature analysis on the target text, in addition to using the relevant rule engine, the present application can also use machine learning technology to identify and parse the product features corresponding to the product activity links or product passwords in the target text. Of course, the present application can also use other technical means to perform feature analysis on the target text, which can be set according to the actual situation and is not limited here.

[0048] Furthermore, before performing feature analysis on the target text, in order to improve the accuracy of analyzing the product features, the present application may also perform preprocessing operations on the target text. The preprocessing operations include but are not limited to data cleaning, data integration, data conversion, data specification and data standardization of the target text. The specific settings may also be made according to actual conditions and are not limited here.

[0049] S120: Match at least one commodity feature with a plurality of pre-configured processing strategies according to a preset matching rule, and determine a target processing strategy corresponding to the at least one commodity feature according to the matching result.

[0050] In this step, after feature parsing is performed on the acquired target text through S110 to determine at least one product feature corresponding to the product activity link or product password, the present application can also match the at least one product feature with a plurality of pre-configured processing strategies according to a preset matching rule, and determine the target processing strategy corresponding to the at least one product feature based on the matching result.

[0051] In a specific implementation, the present application can first obtain preset matching rules, which can include the matching order during matching, such as matching according to the priority of different types of product activity links or product passwords, or matching according to the priority of the e-commerce platform, etc.; it can also include the matching method during matching, such as matching by keywords or matching by regular expressions, etc.; it can also include other matching strategies used during matching, which can be set according to actual conditions and are not limited here.

[0052] After determining the preset matching rules, the present application can also obtain multiple pre-configured processing strategies, which refer to the routing path, processor type, and parsing method when routing different product activity links or product passwords to the corresponding processor for parsing. After the present application obtains the preset matching rules and multiple pre-configured processing strategies, the present application can match the obtained at least one product feature with the pre-configured multiple processing strategies according to the preset matching rules, so that the target processing strategy corresponding to the at least one product feature can be determined according to the matching results.

[0053] For example, when there is only one product feature in the present application, the present application can first match the product feature with the corresponding processing strategy in sequence according to a preset matching order. When the product feature corresponds to the product feature included in one of the processing strategies, the processing strategy can be used as the target processing strategy corresponding to the product feature. Through the target processing strategy, the product activity link or product password corresponding to the product feature can be routed to the corresponding processor for parsing; and when there are multiple product features in the present application, the present application can match different product features with the corresponding processing strategies in sequence according to a preset matching order. After determining the processing strategies corresponding to each product feature, if the processing strategies are the same, the processing strategies can be directly used as the target processing strategies. If the processing strategies are different, the processing strategy with a higher proportion can be selected as the target processing strategy according to the proportion of the processing strategies. When two or more processing strategies have the same proportion, any one of the processing strategies can be selected as the target processing strategy, or other matching methods can be used to re-match to obtain the final target processing strategy.

[0054] S130: Routing the commodity activity link or commodity password to a corresponding processor for parsing according to the target processing strategy, and determining the commodity or activity corresponding to the commodity activity link or commodity password according to the parsing result.

[0055] In this step, after matching at least one product feature with a plurality of pre-configured processing strategies according to a preset matching rule through S120, and determining a target processing strategy corresponding to at least one product feature based on the matching result, the present application can route the product activity link or product password to the corresponding processor for parsing according to the target processing strategy, and determine the product or activity corresponding to the product activity link or product password based on the parsing result.

[0056] Indicatively, Figure 2 As shown, Figure 2 A schematic diagram of a process for feature parsing and processing a target text provided in an embodiment of the present application; Figure 2 In the present application, the aviator rule engine can be used to perform text feature analysis on the acquired text, and after feature extraction on the analyzed product features, the extracted product features are matched with rules so as to match the corresponding processing strategy. Then, the present application can send the corresponding product activity link or product password to the corresponding processor for processing according to the processing strategy. For example, the present application can send the Taobao password to the Taobao password processor for processing, send the Taobao short link to the Taobao short link processor for processing, send the JD short link to the JD short link processor for processing, or send other product activity links or product passwords to the corresponding processor for processing. Different processors can be set according to the actual situation, and there is no restriction here.

[0057] In the above embodiment, when it is monitored that the target user copies and pastes the target text containing the commodity activity link or commodity password from any e-commerce platform to this platform, the target text can be feature parsed to determine at least one commodity feature corresponding to the commodity activity link or commodity password; then, the present application can match the at least one commodity feature with the pre-configured multiple processing strategies according to the preset matching rules, and determine the target processing strategy corresponding to the at least one commodity feature according to the matching results; in this way, the commodity activity link or commodity password can be routed to the corresponding processor for parsing according to the target processing strategy, and the commodity or activity corresponding to the commodity activity link or commodity password can be determined according to the parsing results. In this process, the present platform does not need to consider the e-commerce platform corresponding to the received target text, but only needs to match the corresponding processing strategy through the commodity characteristics, so that it can adapt to the commodity activity links or commodity passwords sent by different e-commerce platforms, and avoid the problem of low accuracy caused by matching directly through commodity activity links or commodity passwords, and can also realize fast matching of a large number of commodity activity links or commodity passwords, thereby effectively improving matching efficiency and reducing the time and cost of manual matching, so that users can participate in commodity activities faster, thereby effectively improving user experience.

[0058] In one embodiment, performing feature analysis on the target text in S110 to determine at least one commodity feature corresponding to the commodity activity link or commodity password may include:

[0059] S111: performing feature analysis on the target text to split the target text into the commodity activity link or commodity password and at least one commodity feature.

[0060] S112: extracting at least one commodity feature corresponding to the commodity activity link or commodity password in the split target text.

[0061] In this embodiment, when performing feature parsing on the target text, since the target text contains a product activity link or a product password, the present application can first split the target text into a product activity link or a product password and one or more corresponding product features. Then, the present application can extract at least one product feature corresponding to the product activity link or the product password from the target text. For example, when the product activity link or the product password is / CZ34525skzWNkcGtI / , the corresponding product feature can be TB, TB_TKL; of course, the product feature here can also be other fields, which can be determined based on the text information contained in the corresponding target text, and is not limited here.

[0062] When the present application obtains the product features corresponding to the product activity link or product password, the product features can be matched with multiple pre-configured processing strategies according to preset matching rules, and the target processing strategy corresponding to at least one product feature can be determined based on the matching results. In this way, the product activity link or product password can be routed to the corresponding processor for parsing according to the target processing strategy, and the product or activity corresponding to the product activity link or product password can be determined based on the parsing results.

[0063] In one embodiment, feature parsing of the target text in S111 to split the target text into the commodity activity link or commodity password and at least one commodity feature may include:

[0064] The target text is feature parsed using the aviator rule engine to split the target text into the commodity activity link or commodity password and at least one commodity feature.

[0065] In this embodiment, when performing feature parsing on the target text, the aviator rule engine can be used in advance to dynamically configure the mapping relationship between the product activity link or product password and the corresponding feature. In this way, after receiving the target text, the aviator rule engine can be used to perform feature parsing on the target text to determine the product activity link or product password and product features that form a mapping relationship in the target text. In this way, the target text can be split into a product activity link or product password and at least one product feature.

[0066] In one embodiment, feature parsing of the target text in S111 to split the target text into the commodity activity link or commodity password and at least one commodity feature may include:

[0067] S1111: Obtain a pre-configured deep learning model, wherein the deep learning model is obtained after training using a training text containing a product activity link or a product password as sample data and using product features corresponding to the product activity link or product password in the training text as sample labels.

[0068] S1112: Input the target text into the deep learning model to obtain a product activity link or product password and at least one corresponding product feature in the target text output by the deep learning model.

[0069] In this embodiment, when performing feature analysis on the target text, a deep learning model can also be used for feature analysis. Specifically, the present application can obtain a pre-configured deep learning model, and then input the target text into the deep learning model, and then obtain the product activity link or product password in the target text and at least one corresponding product feature output by the deep learning model.

[0070] It is understandable that in order to better handle complex link and password structures, the present application can use training texts containing product activity links or product passwords as sample data, and use the product features corresponding to the product activity links or product passwords in the training text as sample labels to train the initial neural network. When the preset training conditions are met, the final deep learning model can be obtained. Among them, the initial neural network of the present application can be a convolutional neural network (CNN), a recurrent neural network (RNN) or other neural networks, which can be selected according to the actual situation and are not limited here.

[0071] After the application has trained the final deep learning model, since the deep learning model has learned the mapping relationship between different product activity links or product passwords and product features, the application can use the deep learning model to perform feature analysis on the target text to quickly obtain one or more product features corresponding to the product activity links or product passwords in the target text.

[0072] Furthermore, before performing feature analysis on the target text, the present application can also identify the text complexity of the target text. If the text complexity of the target text is high, a deep learning model can be used for feature analysis. If the text complexity of the target text is low, the aviator rule engine can be used directly to perform feature analysis on the target text to determine the product activity links or product passwords and product features that form a mapping relationship in the target text, thereby improving the recognition accuracy and efficiency of product features.

[0073] In one embodiment, in S120, matching the at least one commodity feature with a plurality of pre-configured processing strategies according to a preset matching rule to obtain a matching result may include:

[0074] S121: Performing semantic analysis on the at least one commodity feature to obtain a semantic analysis result corresponding to the at least one commodity feature.

[0075] S122: Acquire context information corresponding to the at least one commodity feature in the target text.

[0076] S123: According to the semantic analysis result and the context information, the at least one commodity feature is matched with a plurality of pre-configured processing strategies according to a preset matching rule to obtain a matching result.

[0077] In this embodiment, when matching at least one product feature with a plurality of pre-configured processing strategies according to a preset matching rule, in order to improve the matching accuracy, the present application may first perform a semantic analysis on the at least one product feature, and then obtain a semantic analysis result corresponding to the at least one product feature. Then, the present application may also obtain context information corresponding to the at least one product feature in the target text, so that the at least one product feature may be rule matched based on the semantic analysis result and the context information, and then the final matching result may be obtained.

[0078] Among them, when performing semantic analysis on product features, the present application can adopt word vector analysis or synonym analysis in the prior art to accurately determine the meaning of the product features and thereby improve matching accuracy; when obtaining context information corresponding to the at least one product feature in the target text, the present application can extract the product information before and after the text position corresponding to the product feature in the target text according to a pre-set context information extraction method, so that rule matching can be performed more accurately in combination with the context, syntax, lexical structure, etc. of the product feature in the target text.

[0079] In one embodiment, in S120 or S123, matching the at least one commodity feature with a plurality of pre-configured processing strategies according to a preset matching rule to obtain a matching result may include:

[0080] S210: Acquire multiple pre-configured processing strategies and the priority of each processing strategy.

[0081] S220: According to the priority of each processing strategy, the at least one commodity feature is matched with each processing strategy respectively to obtain a matching result.

[0082] In this embodiment, when matching at least one product feature with multiple pre-configured processing strategies according to a preset matching rule, the multiple pre-configured processing strategies and the priority of each processing strategy can be obtained first, and then the at least one product feature can be matched with each processing strategy according to the priority of each processing strategy.

[0083] Specifically, when setting the priority corresponding to each processing strategy, the application can first set the priority of the e-commerce platform corresponding to different processing strategies, and then set the priority of the corresponding processing strategy according to the priority corresponding to different commodity activity links or commodity passwords in each e-commerce platform. In this process, the application can also dynamically adjust the priority corresponding to different processing strategies based on user data such as historical purchase records or historical browsing records of the target user. For example, the application can use the e-commerce platform with more browsing records in the user data of the target user as the first e-commerce platform for rule matching, and use the type of commodity activity links or commodity passwords with more pasting times in the user data as the first commodity activity link or commodity password corresponding to the rule matching under the e-commerce platform. By analogy, the rule matching method corresponding to the usage habits of the target user can be dynamically configured. Of course, the application can also configure the corresponding matching rules according to other methods, such as according to the close degree of cooperation between each e-commerce platform, the probability of use of each commodity activity link or commodity password on the e-commerce platform, etc., which is not limited here.

[0084] In a specific implementation, taking Taobao as an example, this application can set the priority of Taobao short links to be higher than the priority of Taobao passwords, set the priority of Taobao passwords to be higher than Taobao special links + passwords, set the priority of Taobao special links + passwords to be higher than Taobao product links, and set the priority of Taobao product links to be higher than Taobao venues, and configure the following matching rules:

[0085] ## Taobao

[0086] if include(featureList, "TB") {

[0087] ## Taobao short link

[0088] if include(featureList, "TB_SHORT_LINK") {

[0089] return "TB_SHORT_LINK_HANDLER";

[0090] }

[0091] ## Taobao password

[0092] if include(featureList, "TB_TKL"){

[0093] return "TB_TKL_HANDLER";

[0094] }

[0095] ## Taobao special link + password

[0096] if include(featureList, "TB_TKL_N_SHORT_LINK"){

[0097] return "TKL_N_SHORT_LINK_HANDLER";

[0098] }

[0099] ## Taobao product link

[0100] if include(featureList, "TB_GOODS_LINK") {

[0101] return "TB_HANDLER";

[0102] }

[0103] ## Taobao Venue

[0104] if include(featureList, "TB_VENUE_LINK") {

[0105] return "TB_VENUE_HANDLER";

[0106] }

[0107] return "TB_HANDLER";

[0108] }

[0109] After obtaining at least one product feature, for each product feature, the present application can pre-match the product feature with the Taobao short link in the Taobao platform to determine whether the product feature contains the feature "TB_SHORT_LINK". If so, determine that the processing strategy corresponding to the product feature is "TB_SHORT_LINK_HANDLER". If not, continue to match the product feature with the Taobao password to determine whether the product feature contains the feature "TB_TKL". If so, determine that the processing strategy corresponding to the product feature is "TB_TKL_HANDLER". If not, continue to match the product feature with the next processing strategy, and so on, so as to determine the target processing strategy corresponding to the product feature.

[0110] In one embodiment, the method may further include:

[0111] According to the priority of each processing strategy, when matching the at least one commodity feature with each processing strategy respectively, the matching is performed using distributed computing and parallel processing technology to obtain a matching result.

[0112] In this embodiment, when matching at least one product feature with each processing strategy according to the priority of each processing strategy, since the product feature of this application is one or more, in order to improve the efficiency of rule matching, this application can use distributed computing and parallel processing technology for matching, such as performing rule matching on multiple product features at the same time, so as to quickly obtain matching results.

[0113] The following is a description of a commodity information identification device provided in an embodiment of the present application. The commodity information identification device described below and the commodity information identification method described above can be referenced to each other.

[0114] In one embodiment, Figure 3 As shown, Figure 3A schematic diagram of the structure of a commodity information identification device provided in an embodiment of the present application; the present application also provides a commodity information identification device, including a feature analysis module 210, a feature matching module 220, and a commodity analysis module 230, which specifically include the following:

[0115] The feature analysis module 210 is used to perform feature analysis on the target text containing a product activity link or a product password when it is monitored that the target user copies and pastes the target text from any e-commerce platform to this platform, and determine at least one product feature corresponding to the product activity link or product password.

[0116] The feature matching module 220 is used to match the at least one product feature with a plurality of pre-configured processing strategies according to a preset matching rule, and determine a target processing strategy corresponding to the at least one product feature according to the matching result.

[0117] The product analysis module 230 is used to route the product activity link or product password to a corresponding processor for analysis according to the target processing strategy, and determine the product or activity corresponding to the product activity link or product password according to the analysis result.

[0118] In the above embodiment, when it is monitored that the target user copies and pastes the target text containing the commodity activity link or commodity password from any e-commerce platform to this platform, the target text can be feature parsed to determine at least one commodity feature corresponding to the commodity activity link or commodity password; then, the present application can match the at least one commodity feature with the pre-configured multiple processing strategies according to the preset matching rules, and determine the target processing strategy corresponding to the at least one commodity feature according to the matching results; in this way, the commodity activity link or commodity password can be routed to the corresponding processor for parsing according to the target processing strategy, and the commodity or activity corresponding to the commodity activity link or commodity password can be determined according to the parsing results. In this process, the present platform does not need to consider the e-commerce platform corresponding to the received target text, but only needs to match the corresponding processing strategy through the commodity characteristics, so that it can adapt to the commodity activity links or commodity passwords sent by different e-commerce platforms, and avoid the problem of low accuracy caused by matching directly through commodity activity links or commodity passwords, and can also realize fast matching of a large number of commodity activity links or commodity passwords, thereby effectively improving matching efficiency and reducing the time and cost of manual matching, so that users can participate in commodity activities faster, thereby effectively improving user experience.

[0119] In one embodiment, the present application also provides a computer-readable storage medium, which stores computer-readable instructions. When the computer-readable instructions are executed by one or more processors, the one or more processors execute the steps of the product information identification method described in any of the above embodiments.

[0120] In one embodiment, the present application also provides a computer device, including: one or more processors, and a memory.

[0121] The memory stores computer-readable instructions, and when the computer-readable instructions are executed by the one or more processors, the steps of the commodity information identification method described in any one of the above embodiments are performed.

[0122] Indicatively, Figure 4 As shown, Figure 4 This is a schematic diagram of the internal structure of a computer device provided in an embodiment of the present application. The computer device 300 may be provided as a server. Figure 4 The computer device 300 includes a processing component 302, which further includes one or more processors, and a memory resource represented by a memory 301, for storing instructions executable by the processing component 302, such as an application. The application stored in the memory 301 may include one or more modules, each corresponding to a set of instructions. In addition, the processing component 302 is configured to execute instructions to perform the commodity information identification method of any of the above embodiments.

[0123] The computer device 300 may further include a power supply component 303 configured to perform power management of the computer device 300, a wired or wireless network interface 304 configured to connect the computer device 300 to a network, and an input / output (I / O) interface 305. The computer device 300 may operate based on an operating system stored in the memory 301, such as Windows Server TM, Mac OS X TM, Unix TM, Linux TM, Free BSD TM, or the like.

[0124] Those skilled in the art will understand that Figure 4 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0125] Finally, it should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the presence of other identical elements in the process, method, article or device including the elements.

[0126] The various embodiments in this specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The various embodiments can be combined as needed, and the same or similar parts can refer to each other.

[0127] The above description of the disclosed embodiments enables those skilled in the art to implement or use the present application. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to the embodiments shown herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A commodity information identification method, characterized in that: The method comprises: When it is detected that a target user copies and pastes a target text containing a product activity link or a product password from any e-commerce platform to the current platform, feature analysis is performed on the target text to determine at least one product feature corresponding to the product activity link or product password; Matching the at least one commodity feature with a plurality of pre-configured processing strategies according to a preset matching rule, and determining a target processing strategy corresponding to the at least one commodity feature according to the matching result; Routing the commodity activity link or commodity password to a corresponding processor for parsing according to the target processing strategy, and determining the commodity or activity corresponding to the commodity activity link or commodity password according to the parsing result; The matching of the at least one commodity feature with a plurality of pre-configured processing strategies according to a preset matching rule to obtain a matching result includes: Performing semantic analysis on the at least one commodity feature to obtain a semantic analysis result corresponding to the at least one commodity feature; Acquire context information corresponding to the at least one commodity feature in the target text, as well as a plurality of pre-configured processing strategies and a priority of each processing strategy; According to the semantic analysis result and the context information, and according to the priority of each processing strategy, the at least one commodity feature is matched with each processing strategy to obtain a matching result; or, Obtain multiple pre-configured processing strategies and the priority of each processing strategy; According to the priority of each processing strategy, the at least one commodity feature is matched with each processing strategy respectively to obtain a matching result.

2. The commodity information identification method according to claim 1, characterized in that: The feature analysis of the target text to determine at least one commodity feature corresponding to the commodity activity link or commodity password includes: Performing feature analysis on the target text to split the target text into the product activity link or product password and at least one product feature; At least one commodity feature corresponding to the commodity activity link or commodity password is extracted from the split target text.

3. The commodity information identification method according to claim 2, characterized in that: The feature parsing of the target text to split the target text into the commodity activity link or commodity password and at least one commodity feature includes: The target text is feature parsed using the aviator rule engine to split the target text into the commodity activity link or commodity password and at least one commodity feature.

4. The commodity information identification method according to claim 2, characterized in that: The feature parsing of the target text to split the target text into the commodity activity link or commodity password and at least one commodity feature includes: Obtaining a pre-configured deep learning model, wherein the deep learning model is obtained by training with a training text containing a product activity link or a product password as sample data and with product features corresponding to the product activity link or product password in the training text as sample labels; The target text is input into the deep learning model to obtain a product activity link or a product password and at least one corresponding product feature in the target text output by the deep learning model.

5. The commodity information identification method according to claim 1, characterized in that: The method further comprises: According to the priority of each processing strategy, when matching the at least one commodity feature with each processing strategy respectively, the matching is performed using distributed computing and parallel processing technology to obtain a matching result.

6. A commodity information identification device, characterized in that: include: A feature analysis module, for performing feature analysis on a target text containing a product activity link or a product password copied and pasted by a target user from any e-commerce platform to the platform, and determining at least one product feature corresponding to the product activity link or product password; A feature matching module, used to match the at least one commodity feature with a plurality of pre-configured processing strategies according to a preset matching rule, and determine a target processing strategy corresponding to the at least one commodity feature according to the matching result; A commodity analysis module, used for routing the commodity activity link or commodity password to a corresponding processor for analysis according to the target processing strategy, and determining the commodity or activity corresponding to the commodity activity link or commodity password according to the analysis result; The feature matching module comprises: Performing semantic analysis on the at least one commodity feature to obtain a semantic analysis result corresponding to the at least one commodity feature; Acquire context information corresponding to the at least one commodity feature in the target text, as well as a plurality of pre-configured processing strategies and a priority of each processing strategy; According to the semantic analysis result and the context information, and according to the priority of each processing strategy, the at least one commodity feature is matched with each processing strategy to obtain a matching result; or, Obtain multiple pre-configured processing strategies and the priority of each processing strategy; According to the priority of each processing strategy, the at least one commodity feature is matched with each processing strategy respectively to obtain a matching result.

7. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer-readable instructions, and when the computer-readable instructions are executed by one or more processors, the one or more processors execute the steps of the commodity information identification method according to any one of claims 1 to 5.

8. A computer device, characterized in that: include: one or more processors, and memory; The memory stores computer-readable instructions, and when the computer-readable instructions are executed by the one or more processors, the steps of the commodity information identification method according to any one of claims 1 to 5 are performed.

Images