Data Processing Method, Apparatus, Electronic Device, and Computer-Readable Medium

Abstract

Embodiments of the present disclosure disclose a data processing method, apparatus, electronic device, and computer-readable medium. A specific implementation of the method includes: performing semantic recognition on problem information to obtain problem semantic feature information; displaying supplementary problem information in a question-and-answer window, and displaying a three-dimensional simulation model of a target product on the interface where the question-and-answer window is located; performing feature fusion on supplementary reply information and problem semantic feature information to obtain fused problem feature information; performing problem retrieval on a preset product problem database according to the fused problem feature information to obtain product problem feedback information, and displaying the product problem feedback information in the question-and-answer window; in response to detecting a confirmation operation for product accessory replacement information in the product problem feedback information, shipping product accessories according to the product accessory replacement information. This implementation can avoid waste of logistics resources.

Description

Technical Field

[0001] Embodiments of the present disclosure relate to the field of human-computer interaction technology, and more particularly to data processing methods, devices, electronic devices, and computer-readable media. Background Art

[0002] During the process of using a product, users often need to access various information of the product. Currently, when performing data processing interactions, the commonly used method is to use a large language model to answer product anomaly questions mentioned by users. Or directly retrieve the product problem handling methods stored in the database and push them to the users so that the users can perform product maintenance according to the product problem handling methods.

[0003] However, it is found in practice that when the above method is applied to data processing for product information interaction on a product information interaction platform, the following technical problems often exist:

[0004] Training of large language models is relatively complex, and the questions answered to users mostly rely on publicly available data on the Internet. Therefore, it is difficult to accurately locate the target product and accurately answer the product anomaly questions raised by users about the target product. In addition, since the questions in the preset database are often not comprehensive, it is difficult to retrieve appropriate product problem handling methods, but instead, the handling methods of approximate questions are returned to users by fuzzy matching. As a result, it is also difficult to accurately answer the product anomaly questions raised by users about the target product, leading to a situation where the product accessories do not match when the users select product accessories for shipment based on the feedback data of the platform interaction. Furthermore, it causes a waste of logistics resources.

[0005] The above information disclosed in this background art section is only used to enhance the understanding of the background of the inventive concept, and thus, it may include information that does not form the prior art known to ordinary technicians in the field of this country. Summary of the Invention

[0006] This content part of the present disclosure is used to briefly introduce the concepts, which will be described in detail in the following detailed implementation part. This content part of the present disclosure is not intended to identify the key features or essential features of the claimed technical solution, nor is it intended to be used to limit the scope of the claimed technical solution.

[0007] Some embodiments of the present disclosure propose data processing methods, devices, electronic devices, and computer-readable media to solve one or more of the technical problems mentioned in the above background art section.

[0008] In a first aspect, some embodiments of the present disclosure provide a data processing method, which includes: in response to detecting question information issued by a user for a target product within a question-and-answer window on the above product information interaction platform, performing semantic recognition on the above question information to obtain question semantic feature information; in response to determining that the above question semantic feature information does not meet a preset question determination condition, based on the above question semantic feature information, displaying supplementary question information within the above question-and-answer window, and displaying a three-dimensional simulation model of the above target product within the interface where the above question-and-answer window is located, wherein the displayed three-dimensional simulation model matches the above question semantic feature information, and the above supplementary question information is generated through the following steps: determining the missing question information of the above question semantic feature information, and generating supplementary question information based on the above missing question information; in response to detecting supplementary reply information for the above supplementary question, performing feature fusion on the above supplementary reply information and the above question semantic feature information to obtain fused question feature information; based on the above fused question feature information, performing question retrieval on a preset product question database to obtain product question feedback information, and displaying the above product question feedback information within the above question-and-answer window, wherein the above product question feedback information includes product accessory replacement information; in response to detecting a confirmation operation for the product accessory replacement information in the above product question feedback information, shipping product accessories according to the above product accessory replacement information.

[0009] Second aspect, some embodiments of the present disclosure provide a data processing device, which includes: a semantic recognition unit configured to perform semantic recognition on the above-mentioned question information in response to detecting that the user issues question information about a target product within the question-and-answer window on the above-mentioned product information interaction platform, so as to obtain question semantic feature information; a display unit configured to, in response to determining that the above-mentioned question semantic feature information does not meet a preset question determination condition, display supplementary question information within the above-mentioned question-and-answer window according to the above-mentioned question semantic feature information, and display a three-dimensional simulation model of the above-mentioned target product within the interface where the above-mentioned question-and-answer window is located, wherein the displayed three-dimensional simulation model matches the above-mentioned question semantic feature information, and the above-mentioned supplementary question information is generated through the following steps: determining the missing question information of the above-mentioned question semantic feature information, and generating supplementary question information according to the above-mentioned missing question information; a feature fusion unit configured to perform feature fusion on the above-mentioned supplementary reply information and the above-mentioned question semantic feature information in response to detecting supplementary reply information for the above-mentioned supplementary question, so as to obtain fused question feature information; a question retrieval unit configured to perform question retrieval on a preset product question database according to the above-mentioned fused question feature information, so as to obtain product question feedback information, and display the above-mentioned product question feedback information within the above-mentioned question-and-answer window, wherein the above-mentioned product question feedback information includes product accessory replacement information; a confirmation and delivery unit configured to, in response to detecting a confirmation operation for the product accessory replacement information in the above-mentioned product question feedback information, perform product accessory delivery according to the above-mentioned product accessory replacement information.

[0010] Third aspect, some embodiments of the present disclosure provide an electronic device, including: one or more processors; a storage device having one or more programs stored thereon, and when the one or more programs are executed by the one or more processors, the one or more processors implement the method described in any implementation manner of the above first aspect.

[0011] Fourth aspect, some embodiments of the present disclosure provide a computer-readable medium having a computer program stored thereon, wherein when the program is executed by a processor, the method described in any implementation manner of the above first aspect is implemented.

[0012] The above-mentioned various embodiments of the present disclosure have the following beneficial effects: Through the data processing method of some embodiments of the present disclosure, the accuracy of replying to product anomaly problems raised by users for target products can be improved. Furthermore, it is possible to avoid mis-sending product accessories and waste of logistics resources. Specifically, the reason for the waste of logistics resources is as follows: The training of large language models is relatively complex, and the questions answered to users mostly rely on publicly available data on the Internet. Therefore, it is difficult to accurately locate the target product and accurately reply to the product anomaly problems raised by users for the target product. In addition, since the questions in the preset database are often not comprehensive, it is difficult to retrieve appropriate product problem handling methods, but instead, the handling methods of approximate problems are returned to users through fuzzy matching. Thus, it is also difficult to accurately reply to the product anomaly problems raised by users for the target product, resulting in a situation where the product accessories do not match when users select product accessories for shipment based on the feedback data of platform interaction. Based on this, in the data processing method of some embodiments of the present disclosure, first, through the question-and-answer window of the above-mentioned product information interaction platform, the question information input by the user for the target product is obtained. Here, in order to avoid directly using a large model for question parsing and feedback, the semantic recognition is used to determine the problem semantic feature information. Then, considering the problem that the user's questions may be inaccurately described, the question determination condition is introduced to determine whether the question is accurate. Here, for inaccurate questions, the supplementary question information is displayed in the above-mentioned question-and-answer window to facilitate the user to further elaborate on the product problem. At the same time, the three-dimensional simulation model of the target product is also displayed for the user to refer to and describe, which can further improve the accuracy of the user's description of the required problem. Thus, the demand problem raised by the user for the product can be located from end to end. Then, through feature fusion, the features of all the information replied by the user can be comprehensively processed to obtain the fused problem feature information. After that, the product problem database is used to retrieve the problem to obtain the product problem feedback information. Here, it is also because the accuracy of the user's demand obtained can be ensured. Thus, the corresponding product problem feedback information can be accurately retrieved from the product problem database. Thereby, it is convenient for the user to confirm the accessories to be replaced according to the product problem feedback information for product accessory shipment. Therefore, the waste of logistics resources is avoided. BRIEF DESCRIPTION OF THE DRAWINGS

[0013] In combination with the accompanying drawings and with reference to the following specific embodiments, the above and other features, advantages and aspects of the various embodiments of the present disclosure will become more obvious. Throughout the drawings, the same or similar reference numerals denote the same or similar elements. It should be understood that the drawings are schematic and the elements and elements are not necessarily drawn to scale.

[0014] Figure 1 is a flowchart of some embodiments of the data processing method according to the present disclosure;

[0015] Figure 2 Schematic diagram of the interface of the Q&A window according to some embodiments of the data processing method of the present disclosure;

[0016] Figure 3 Schematic diagram of the structure of a data processing device according to some embodiments of the present disclosure;

[0017] Figure 4 Schematic diagram of the structure of an electronic device suitable for implementing some embodiments of the present disclosure. Detailed implementation manners

[0018] Embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although some embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure can be implemented in various forms and should not be construed as limited to the embodiments set forth herein. On the contrary, these embodiments are provided to more thoroughly and completely understand the present disclosure. It should be understood that the drawings and embodiments of the present disclosure are only for exemplary purposes and are not used to limit the protection scope of the present disclosure.

[0019] In addition, it should be noted that for the sake of convenience of description, only parts related to the relevant invention are shown in the drawings. Without conflict, the embodiments in the present disclosure and the features in the embodiments can be combined with each other.

[0020] It should be noted that the concepts such as "first" and "second" mentioned in the present disclosure are only used to distinguish different devices, modules or units, and are not used to limit the order or interdependence relationship of the functions performed by these devices, modules or units.

[0021] It should be noted that the modifications of "one" and "plural" mentioned in the present disclosure are illustrative rather than restrictive. Those skilled in the art should understand that unless otherwise clearly specified in the context, it should be understood as "one or more".

[0022] The names of the messages or information exchanged between multiple devices in the embodiments of the present disclosure are only for illustrative purposes and are not used to limit the scope of these messages or information.

[0023] The present disclosure will be described in detail below with reference to the drawings and in combination with the embodiments.

[0024] Figure 1 Flow 100 according to some embodiments of the data processing method of the present disclosure is shown. The data processing method, which is applied to the product information interaction platform, may include the following steps:

[0025] Step 101, in response to detecting question information sent by a user for a target product in the Q&A window on the product information interaction platform, perform semantic recognition on the question information to obtain question semantic feature information.

[0026] In some embodiments, the execution subject of the data processing method may, in response to detecting question information sent by a user regarding a target product within the question-and-answer window on the above-mentioned product information interaction platform, perform semantic recognition on the above-mentioned question information to obtain question semantic feature information. Among them, the above-mentioned question-and-answer window may be a page pop-up window.

[0027] Here, the product information interaction platform may be a pre-set platform for information interaction for one or more products. Users can query various information of the required products within the question-and-answer window of this platform.

[0028] As an example, the above-mentioned question-and-answer window may be as Figure 2 shown. Specifically, for a product information interaction platform taking an excavator as an example, users can query information within the question-and-answer window as Figure 2 shown.

[0029] In practice, in the process of adopting technical solutions to solve the problems mentioned in the background art, there is often another technical problem 2: Considering direct semantic analysis, there is a situation where the theme is not clear. Then, there is often a situation where the user only sends a question without determining the problem requirements, making it difficult to judge the user's needs. Or there is a situation where the user has difficulty expressing the problem clearly. Therefore, in all cases, the error of the extracted sentence meaning is relatively large. It is difficult to provide an accurate question reply for the user. In response to the above technical problem 2, the inventor decides to adopt the following solution.

[0030] In some optional implementation manners of some embodiments, the above-mentioned execution subject performs semantic recognition on the above-mentioned question information to obtain question semantic feature information, which may include the following steps:

[0031] The first step is to extract product feature words from the above-mentioned question information. Among them, the product feature words in the above-mentioned question information can be extracted through a pre-set feature word extraction algorithm. For example, the product feature word can be "excavator track".

[0032] As an example, the feature word extraction algorithm may include but is not limited to at least one of the following: Bag of Words, TF-IDF (Term Frequency-Inverse Document Frequency) algorithm.

[0033] The second step is to perform question semantic extraction on the above-mentioned question information according to the above-mentioned product feature words to generate question semantic feature information. Among them, the above-mentioned product feature words can be used as keywords, and through a pre-set semantic extraction algorithm, question semantic extraction is performed on the above-mentioned question information to generate question semantic feature information.

[0034] As an example, the above semantic extraction algorithm may include, but is not limited to, at least one of the following: Named Entity Recognition (NER) algorithm, Support Vector Machine (SVM), Word Embedding model, etc. For example, the obtained problem semantic feature information may be "There is vibration when the excavator starts up."

[0035] In practice, considering that there is a situation where the theme is not clear when directly performing semantic analysis, therefore, by first extracting product feature words and then performing semantic extraction with the product feature words as keywords, it can be used to improve the accuracy of the generated problem semantic feature information.

[0036] Step 102, in response to determining that the problem semantic feature information does not meet the preset problem determination condition, display supplementary problem information in the Q&A window according to the problem semantic feature information, and display the 3D simulation model of the target product in the interface where the Q&A window is located.

[0037] In some embodiments, the above execution entity may, in response to determining that the above problem semantic feature information does not meet the preset problem determination condition, display supplementary problem information in the above Q&A window according to the above problem semantic feature information, and display the 3D simulation model of the above target product in the interface where the above Q&A window is located.

[0038] Among them, the displayed 3D simulation model matches the above problem semantic feature information, and the above supplementary problem information is generated through the following steps:

[0039] Determine the missing problem information of the above problem semantic feature information, and generate supplementary problem information according to the above missing problem information.

[0040] In some optional implementation manners of some embodiments, the above execution entity, in response to determining that the above problem semantic feature information does not meet the preset problem determination condition, displaying supplementary problem information in the above Q&A window according to the above problem semantic feature information, may include the following steps:

[0041] First step, retrieve product problem description information that matches the above product feature words from the above product problem database. Among them, the above product problem database includes component identifiers corresponding to each component of the above target product and problem identifiers of various problems. There is also problem association description information between the component identifier and the problem identifier. Therefore, the component identifier that is the same as the product feature word can be retrieved from the above product problem database, and the corresponding problem association description information is determined as the product problem description information. Here, there may be multiple problem identifiers corresponding to the product problem description information.

[0042] As an example, different problems can be preset with different identification codes.

[0043] In the second step, in response to the mismatch between the above product problem description information and the above problem semantic feature information, it is determined that the above problem semantic feature information does not meet the preset problem determination condition. Among them, since one data identifier stored in the product problem database may correspond to multiple problem-related description information. Therefore, the retrieved product problem description information does not match the above problem semantic feature information. Thus, it can be determined that the above problem semantic feature information does not meet the preset problem determination condition. Here, the problem determination condition can be a condition for determining whether the problem semantic feature information can retrieve matching product problem description information. In addition, it can be determined that multiple problem identifiers in the product problem description information and the above problem semantic feature information match the product feature words. Specifically, it is possible to check whether there is associated description information between the product feature words and multiple problem identifiers.

[0044] In the third step, according to the above problem semantic feature information, supplementary problem information is displayed in the above Q&A window.

[0045] Optionally, the above execution entity displaying the 3D simulation model of the above target product in the interface where the above Q&A window is located may include the following steps:

[0046] In the first step, a product simulation model corresponding to the above target product is called from the database. Among them, the above product simulation model is constructed according to the product structure of the above target product. The product simulation model may include sub-models of each product component. The sub-models of the product components are combined into a product simulation model according to the product structure.

[0047] In the second step, product component nodes that match the above product feature words in the above product simulation model are determined. Among them, each sub-model in the product simulation model includes a component identifier of the corresponding component. The component identifier that represents the same component as the product feature word can be determined as the product component node.

[0048] In the third step, the above product component nodes are model-rendered, and the display perspective of the above product simulation model is adjusted to display the rendered product component nodes. Among them, a product digital passport of the above target product may also be displayed in the interface where the above Q&A window is located. The above product digital passport may include at least one of the following: product digital certificate, product carbon consumption, product specification parameters, product supply chain, product maintenance information, etc.

[0049] In some optional implementation manners of some embodiments, the above execution entity, the above execution entity determines the missing problem information of the above problem semantic feature information, and generates supplementary problem information according to the above missing problem information, may include the following steps:

[0050] First step, extract the user demand feature words from the above problem semantic feature information, and in response to the failure to extract, through the above Q&A window, instruct the user to send the user demand feature words. Among them, the user demand feature words can be extracted from the above problem semantic feature information through the above feature word extraction algorithm. Here, the user demand feature words can be the keywords characterizing the information required by the user. For example, "display accessory information", "provide repair steps", etc.

[0051] In practice, there are often cases where the user only issues a problem without determining the problem demand. Therefore, it is necessary to extract the demand feature words. For example, the user issues "The excavator track is abnormal", but does not provide specific circumstances.

[0052] Second step, in response to determining that the above user demand feature words belong to the product failure category, extract the product failure problem chain set corresponding to the above product component node from the above product problem database. Among them, each product failure problem chain in the above product failure problem chain set can include at least one component failure node, and the component failure nodes are connected by failure pointer information. Here, the component failure node can be the node corresponding to a component of the target product. The product failure category is the problem indicating that the information of the user demand interaction belongs to the product failure aspect. Specifically, for each failure problem, the above product problem database can establish a product failure problem chain according to the pre-stored component identifier and problem identifier to characterize the components involved in solving the failure problem. Then, the failure pointer information between the component failure nodes is the problem association description information.

[0053] As an example, taking an excavator as an example, the component failure node can be the track node. The corresponding product failure problem chain can also include: track drive wheel node, track support wheel node, etc. Then, the failure pointer information can be: track support wheel node (severely worn) - track drive wheel node (loose track meshing) - track node (resulting in abnormal track drive).

[0054] Third step, use the above user demand feature words and the above problem semantic feature information to select a matching product failure problem chain from the above product failure problem chain set as the target product failure problem chain. Among them, the word vector sets of the above user demand feature words and the above problem semantic feature information can be determined. Then, the association degree between each product failure problem chain and the word vector set can be determined respectively. Finally, the product failure problem chain with the largest association degree can be determined as the target product failure problem chain.

[0055] Step 4: Using the above product feature words as core words, generate supplementary question information according to a preset set of question description patterns. Among them, the above supplementary question information may include a supplementary question prompt text group corresponding to the above target product fault problem chain. Each supplementary question prompt text in the above supplementary question prompt text group may correspond to a question. Here, the question description pattern may be a pre-established sentence lacking vocabulary. Thus, the above product feature words can be filled into each question description pattern as core words to obtain the supplementary question prompt text. In addition, the supplementary question prompt text group may be pre-constructed according to the adjacent two component fault nodes and the fault pointer information between them in the target product fault problem chain.

[0056] In practice, there are often situations where users have difficulty expressing their problems clearly. Therefore, it is necessary to send questions to the user in the form of multiple guiding inquiries to guide the user to supplement the product problems to be solved.

[0057] Step 5: Send the supplementary question prompt text group in the above supplementary question information to the above Q&A window for display in sequence for the user to reply. Among them, the sent supplementary question prompt text can be used for the user to select questions or for the user to freely organize language to reply.

[0058] Step 103: In response to detecting supplementary reply information for a supplementary question, perform feature fusion on the supplementary reply information and the question semantic feature information to obtain fused question feature information.

[0059] In some embodiments, the above execution entity may, in response to detecting supplementary reply information for the above supplementary question, perform feature fusion on the above supplementary reply information and the above question semantic feature information to obtain fused question feature information.

[0060] In some optional implementation manners of some embodiments, the above execution entity performing feature fusion on the above supplementary reply information and the above question semantic feature information to obtain fused question feature information may include the following steps:

[0061] First step: Determine the user reply results corresponding to each supplementary question prompt text in the above supplementary reply information. Among them, the above feature word extraction algorithm may be used to determine the user reply results corresponding to each supplementary question prompt text in the above supplementary reply information. Here, the user reply results may include reply keywords.

[0062] Second step: Determine the question fields corresponding to each user reply result in the product question database to obtain a question field group. Among them, the corresponding question fields in the product question database may be selected through the reply keywords in the user reply results.

[0063] Step 3: Add the problem field group to the above problem semantic feature information to obtain the fused problem feature information. Among them, the problem field group can be added to the above problem semantic feature information according to the order of the fault nodes of each component in the above target product fault problem chain to obtain the fused problem feature information.

[0064] The above steps 101-103 and their related content are an inventive point of the embodiments of the present disclosure, which solves the second technical problem mentioned in the background art: "Considering direct semantic analysis, there is a situation where the theme is not clear. Then, there is often a situation where the user only issues a problem without determining the problem requirements, making it difficult to judge the user's needs. Or there is a situation where the user has difficulty expressing the problem clearly. Therefore, in all cases, the error of the extracted sentence meaning is relatively large. It is difficult to provide an accurate problem response for the user." The factors that make it difficult to provide an accurate problem response for the user are usually as follows: Considering direct semantic analysis, there is a situation where the theme is not clear. Then, there is often a situation where the user only issues a problem without determining the problem requirements, making it difficult to judge the user's needs. Or there is a situation where the user has difficulty expressing the problem clearly. Therefore, in all cases, the error of the extracted sentence meaning is relatively large. To achieve this effect, first, by extracting product feature words first and then performing semantic extraction with the product feature words as keywords, it can be used to improve the accuracy of the generated problem semantic feature information. Then, by initially retrieving the product problem database to determine whether the user's problem is precise. At the same time, considering that there is a situation where the user only issues a problem without determining the problem requirements. Therefore, it is necessary to extract demand feature words to locate the user's specific needs. Then, considering the situation where the user has difficulty expressing the problem clearly. Therefore, it is necessary to send questions to the user in the form of multiple guided inquiries. To guide the user to supplement the product problems to be solved. At the same time, by displaying the product component nodes rendered by the 3D simulation model and the product digital passport of the above target product, it can further facilitate the user's reference to improve the clarity of the user's response to the question. Thus, it is convenient to more accurately locate the user's needs and provide an accurate problem response for the user. Furthermore, it is possible to accurately send the required accessories for the user, avoiding waste of logistics resources.

[0065] Step 104: According to the fused problem feature information, perform a problem search on the preset product problem database to obtain product problem feedback information, and display the product problem feedback information in the Q&A window.

[0066] In some embodiments, the above execution subject can perform a problem search on the preset product problem database according to the above fused problem feature information to obtain product problem feedback information, and display the above product problem feedback information in the above Q&A window. Among them, the above product problem feedback information includes product accessory replacement information.

[0067] In the process of adopting technical solutions to solve the problems mentioned in the background technology, there is often another technical problem 3: Although it is possible to accurately locate the problem requirements needed by the user, since the problems in the preset database are often not comprehensive, it is still difficult to accurately reply to the product anomaly problems raised by the user regarding the target product. In response to the above technical problem 3, the inventor decided to adopt the following solutions.

[0068] In some optional implementation manners of some embodiments, the above-mentioned execution subject performs a problem search on the preset product problem database according to the above-mentioned fused problem feature information to obtain product problem feedback information, which may include the following steps:

[0069] In the first step, in response to determining that the above-mentioned user demand feature word belongs to the product failure category, retrieve failure discrimination information that matches the above-mentioned fused problem feature information from the above-mentioned product problem database as the product problem feedback information. Among them, it is possible to retrieve failure discrimination information that matches the above-mentioned fused problem feature information from the above-mentioned product problem database again as the product problem feedback information.

[0070] As an example, the product part replacement information in the product problem feedback information may include "the excavator track support wheel needs to be replaced".

[0071] In the second step, in response to determining that the above-mentioned user demand feature word belongs to the product maintenance category, call the usage data of the above-mentioned target product. Among them, it is possible to obtain usage data from the usage terminal of the target product. It is also possible to obtain the target product usage data uploaded by the user.

[0072] As an example, the usage data of the target product may include but is not limited to at least one of the following: product usage duration, product part replacement duration, product part maintenance duration, etc.

[0073] In the third step, perform feature matching on the pre-stored product maintenance process structure tree corresponding to the above-mentioned target product and the usage data of the above-mentioned target product to obtain a group of product nodes to be maintained. Among them, it is possible to select nodes that match the usage data of the above-mentioned target product from the product maintenance process structure tree as the product nodes to be maintained. Here, the nodes in the product maintenance process structure tree may be arranged in chronological order. Each node may correspond to a component or a product production node. In addition, each node may also include node maintenance guide information arranged in chronological order. Therefore, it is possible to determine the component nodes in the above-mentioned product maintenance process structure tree corresponding to the usage data of the target product.

[0074] In practice, among them, the main node of the product maintenance process structure tree is the completion node of the above-mentioned product, and the above-mentioned completion node includes the product production completion time point.

[0075] As an example, the main node can be defined first. For example, the main node corresponds to the product process node of the excavator's factory date. Then, the production process nodes corresponding to the components that make up the excavator can be defined as sub-nodes under the main node. For each sub-node, the production process nodes of the raw materials required to produce the components of that sub-node can be defined as sub-sub nodes. Thus, a production process structure tree is established according to the product's production supply chain and product production log. Here, since each production process node corresponds to a timestamp, the nodes in the production process structure tree can also be established according to the time difference, with the characteristics of chronological order and the production sequence of the product supply chain. In addition, the node maintenance guide information can include 3D animation for component maintenance and component maintenance step indication information.

[0076] Fourth step, send the component maintenance names corresponding to each product to-be-maintained node in the above product to-be-maintained node group to the above Q&A window for the user to select the component maintenance name to be maintained, and obtain the target component maintenance name.

[0077] Fifth step, call the maintenance step information that matches the above target component maintenance name. Among them, the above maintenance step information can include 3D animation for component maintenance and component maintenance step indication information. Here, the 3D animation for component maintenance and component maintenance step indication information can be extracted from the node maintenance guide information in the component node corresponding to the target component maintenance name as the matching maintenance step information.

[0078] Sixth step, render the above maintenance step information including 3D animation for component maintenance and component maintenance step indication information onto the 3D simulation model displayed in the above interface to demonstrate the target product maintenance steps.

[0079] Step 105, in response to detecting a confirmation operation for the product accessory replacement information in the product problem feedback information, ship the product accessories according to the product accessory replacement information.

[0080] In some embodiments, the above execution entity can, in response to detecting a confirmation operation for the product accessory replacement information in the above product problem feedback information, ship the product accessories according to the above product accessory replacement information.

[0081] Optionally, the above execution entity can also perform the following steps:

[0082] First step, decompose the above fused problem feature information to obtain a decomposed problem data chain;

[0083] Second step, update the above decomposed problem data chain to the above product problem database.

[0084] The above steps 104-105 and their related content are an inventive point of an embodiment of the present disclosure, which solves the third technical problem mentioned in the background art, that is, "although it is possible to accurately locate the problem requirements needed by the user, since the problems in the preset database are often not comprehensive, it is still difficult to accurately reply to the product anomaly problems raised by the user for the target product". The factors that make it difficult to accurately reply to the product anomaly problems raised by the user for the target product are often as follows: Although it is possible to accurately locate the problem requirements needed by the user, since the problems in the preset database are often not comprehensive. To achieve this effect, first, considering the situation that the problems stored in the database are not comprehensive, therefore, for each product, component identifiers and problem identifiers are added to the database. At the same time, the component failure nodes are associated with each other by failure pointer information to form a product failure problem chain. Thus, various problems related to the product can be ensured. Thereby, it is convenient to quickly retrieve the product failure problem chain according to the user's needs to generate product problem feedback information. In addition, it is also considered that there are two situations for the problems raised by the user, namely the product failure category and the product maintenance category. Therefore, by introducing the product maintenance process structure tree, the product process can be structured. At the same time, because the product process nodes, product component nodes and maintenance step information are recorded. Therefore, when the user's demand is the product maintenance category, the database can be assisted to accurately push the maintenance step information to the user. Thus, the interaction duration of the user can be reduced, and the amount of interaction information can be reduced. Furthermore, the occupation of transmission resources can be reduced.

[0085] The above-described embodiments of the present disclosure have the following beneficial effects: Through the data processing method of some embodiments of the present disclosure, the accuracy of answering product anomaly questions raised by users regarding the target product can be improved. Furthermore, mis-sending product accessories can be avoided, and waste of logistics resources can be avoided. Specifically, the reason for the waste of logistics resources is as follows: The training of large language models is relatively complex, and the questions answered to users mostly rely on publicly available data on the Internet. Therefore, it is difficult to accurately locate the target product and accurately answer the product anomaly questions raised by users regarding the target product. In addition, since the questions in the preset database are often not comprehensive, it is difficult to retrieve an appropriate product problem handling method, but rather a similar problem handling method is returned to the user through fuzzy matching. Thus, it is also difficult to accurately answer the product anomaly questions raised by users regarding the target product, resulting in a situation where the product accessories do not match when the user selects the product accessories for shipment based on the feedback data of the platform interaction. Based on this, in the data processing method of some embodiments of the present disclosure, first, through the question-and-answer window of the above product information interaction platform, the question information input by the user regarding the target product is obtained. Here, in order to avoid directly using the large model for question parsing and feedback, the semantic recognition is used to determine the question semantic feature information. Then, considering that there may be inaccurate descriptions in the user's questions, the question determination condition is introduced to determine whether the question is accurate. Here, for inaccurate questions, the supplementary question information is displayed in the above question-and-answer window to facilitate the user to further elaborate on the product problem. At the same time, the three-dimensional simulation model of the target product is also displayed for the user to refer to when describing, which can further improve the accuracy of the user's description of the required problem. Thus, the demand question raised by the user for the product can be located end-to-end. Then, through feature fusion, the features of all the information replied by the user can be comprehensively processed to obtain the fused question feature information. After that, the product problem database is used to retrieve the question to obtain the product problem feedback information. Here, the accuracy of the user's demand can also be ensured. Thus, the corresponding product problem feedback information can be accurately retrieved from the product problem database. Therefore, it is convenient for the user to confirm the accessories to be replaced based on the product problem feedback information for product accessory shipment. Therefore, the waste of logistics resources is avoided.

[0086] Further referring Figure 3 , as an implementation of the methods shown in the above figures, the present disclosure provides some embodiments of a data processing device. These device embodiments correspond to Figure 1 the method embodiments shown, and the device can be specifically applied to various electronic devices.

[0087] As Figure 3As shown in the figure, the data processing device 300 in some embodiments includes: a semantic recognition unit 301, a display unit 302, a feature fusion unit 303, a question retrieval unit 304, and a confirmation and shipping unit 305. Among them, the semantic recognition unit 301 is configured to, in response to detecting question information sent by a user regarding a target product in the question-and-answer window on the above product information interaction platform, perform semantic recognition on the above question information to obtain question semantic feature information; the display unit 302 is configured to, in response to determining that the above question semantic feature information does not meet a preset question determination condition, display supplementary question information in the above question-and-answer window according to the above question semantic feature information, and display a three-dimensional simulation model of the above target product in the interface where the above question-and-answer window is located, where the displayed three-dimensional simulation model matches the above question semantic feature information, and the above supplementary question information is generated through the following steps: determining the missing question information of the above question semantic feature information, and generating supplementary question information according to the above missing question information; the feature fusion unit 303 is configured to, in response to detecting supplementary reply information for the above supplementary question, perform feature fusion on the above supplementary reply information and the above question semantic feature information to obtain fused question feature information; the question retrieval unit 304 is configured to, according to the above fused question feature information, perform question retrieval on a preset product question database to obtain product question feedback information, and display the above product question feedback information in the above question-and-answer window, where the above product question feedback information includes product accessory replacement information; the confirmation and shipping unit 305 is configured to, in response to detecting a confirmation operation for the product accessory replacement information in the above product question feedback information, perform product accessory shipping according to the above product accessory replacement information.

[0088] It can be understood that the various units described in the device 300 correspond to the respective steps in the method described with reference to Figure 1 Therefore, the operations, features, and beneficial effects described above for the method also apply to the device 300 and the units included therein, and will not be repeated here.

[0089] Next, refer to Figure 4 , which shows a schematic structural diagram of an electronic device (e.g., a computing device) 400 suitable for implementing some embodiments of the present disclosure. Figure 4 The electronic device shown is merely an example and should not impose any limitation on the functions and usage scope of the embodiments of the present disclosure.

[0090] As Figure 4As shown, the electronic device 400 may include a processing device (such as a central processing unit, a graphics processing unit, etc.) 401, which may perform various appropriate actions and processes according to the program stored in the read-only memory 402 or the program loaded from the storage device 408 into the random access memory 403. In the random access memory 403, various programs and data required for the operation of the electronic device 400 are also stored. The processing device 401, the read-only memory 402, and the random access memory 403 are connected to each other through the bus 404. The input / output interface 405 is also connected to the bus 404.

[0091] Generally, the following devices may be connected to the I / O interface 405: an input device 406 including, for example, a touch screen, a touch pad, a keyboard, a mouse, a camera, a microphone, an accelerometer, a gyroscope, etc.; an output device 407 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; a storage device 408 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 409. The communication device 409 may allow the electronic device 400 to communicate with other devices wirelessly or wiredly to exchange data. Although Figure 4 the electronic device 400 with various devices is shown, it should be understood that it is not required to implement or have all the shown devices. More or fewer devices may be implemented or had alternatively. Figure 4 Each block shown in the figure may represent a device or, as needed, multiple devices.

[0092] In particular, according to some embodiments of the present disclosure, the processes described above with reference to the flowcharts may be implemented as computer software programs. For example, some embodiments of the present disclosure include a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program contains program codes for performing the methods shown in the flowcharts. In such some embodiments, the computer program may be downloaded and installed from the network through the communication device 409, or installed from the storage device 408, or installed from the read-only memory 402. When the computer program is executed by the processing device 401, the above functions defined in the methods of some embodiments of the present disclosure are executed.

[0093] It should be noted that the computer-readable media described in some embodiments of the present disclosure may be a computer-readable signal medium, a computer-readable storage medium, or any combination of the two. A computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the above. More specific examples of the computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In some embodiments of the present disclosure, the computer-readable storage medium may be any tangible medium that contains or stores a program, and the program may be used by or in conjunction with an instruction execution system, apparatus, or device. In some embodiments of the present disclosure, the computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, which carries computer-readable program code. Such a propagated data signal may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. The computer-readable signal medium may also be any computer-readable medium other than the computer-readable storage medium, and the computer-readable signal medium may send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium may be transmitted using any appropriate medium, including but not limited to: wires, optical cables, RF (radio frequency), etc., or any suitable combination of the above.

[0094] In some embodiments, the client and the server may communicate using any currently known or future-developed network protocol such as HTTP (Hyper Text Transfer Protocol), and may be interconnected with digital data communication in any form or medium (e.g., a communication network). Examples of communication networks include local area networks ("LANs"), wide area networks ("WANs"), the Internet (e.g., the Internet), and end-to-end networks (e.g., ad hoc end-to-end networks), as well as any currently known or future-developed networks.

[0095] The above computer-readable medium may be included in the above electronic device; or it may exist independently and not be assembled into the electronic device. The above computer-readable medium carries one or more programs. When the above one or more programs are executed by the electronic device, the electronic device is caused to: in response to detecting question information sent by the user for a target product within the question-and-answer window on the above product information interaction platform, perform semantic recognition on the above question information to obtain question semantic feature information; in response to determining that the above question semantic feature information does not meet a preset question determination condition, display supplementary question information within the above question-and-answer window according to the above question semantic feature information, and display a three-dimensional simulation model of the above target product within the interface where the above question-and-answer window is located, wherein the displayed three-dimensional simulation model matches the above question semantic feature information, and the above supplementary question information is generated through the following steps: determine the missing question information of the above question semantic feature information, and generate supplementary question information according to the above missing question information; in response to detecting supplementary reply information for the above supplementary question, perform feature fusion on the above supplementary reply information and the above question semantic feature information to obtain fused question feature information; perform question retrieval on a preset product question database according to the above fused question feature information to obtain product question feedback information, and display the above product question feedback information within the above question-and-answer window, wherein the above product question feedback information includes product accessory replacement information; in response to detecting a confirmation operation for the product accessory replacement information in the above product question feedback information, ship product accessories according to the above product accessory replacement information.

[0096] Computer program code for performing the operations of some embodiments of the present disclosure may be written in one or more programming languages or combinations thereof. The above programming languages include object-oriented programming languages - such as Java, Smalltalk, C++; and also include conventional procedural programming languages - such as the "C" language or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, executed as a stand-alone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network - including a local area network (LAN) or a wide area network (WAN) - or may be connected to an external computer (e.g., by using an Internet service provider to connect through the Internet).

[0097] The flowcharts and block diagrams in the accompanying drawings illustrate the possible architectures, functions, and operations of systems, methods, and computer program products according to various embodiments of the present disclosure. In this regard, each block in the flowchart or block diagram may represent a module, a segment of a program, or a portion of code that contains one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions noted in the blocks may occur in a different order than noted in the accompanying drawings. For example, two consecutive blocks shown may actually be executed substantially in parallel, or they may sometimes be executed in the reverse order, depending on the functions involved. It should also be noted that each block in the block diagram and / or flowchart, and combinations of blocks in the block diagram and / or flowchart, can be implemented by a dedicated hardware-based system that performs the specified functions or operations, or can be implemented by a combination of dedicated hardware and computer instructions.

[0098] The units described in some embodiments of the present disclosure can be implemented in software or in hardware. The described units can also be provided in a processor. For example, it can be described as: a processor includes a semantic recognition unit, a display unit, a feature fusion unit, a question retrieval unit, a confirmation and shipping unit. Among them, the names of these units do not constitute a limitation to the unit itself in some cases. For example, the semantic recognition unit can also be described as "a unit that performs semantic recognition on question information".

[0099] The functions described above can be performed at least in part by one or more hardware logic components. For example, without limitation, exemplary types of hardware logic components that can be used include: field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on a chip (SOCs), complex programmable logic devices (CPLDs), and so on.

[0100] The above description is only some preferred embodiments of the present disclosure and an explanation of the technical principles applied. Those skilled in the art should understand that the scope of the invention involved in the embodiments of the present disclosure is not limited to the technical solutions formed by the specific combination of the above technical features, but should also cover other technical solutions formed by any combination of the above technical features or their equivalent features without departing from the above inventive concept. For example, technical solutions formed by mutually replacing the above features with (but not limited to) technical features having similar functions disclosed in the embodiments of the present disclosure.

Claims

1. A data processing method, applied to a product information interaction platform, comprising: In response to detecting question information sent by a user for a target product in a question-and-answer window on the product information interaction platform, performing semantic recognition on the question information to obtain question semantic feature information; Wherein, the performing semantic recognition on the question information to obtain question semantic feature information includes: Extracting product feature words from the question information; Performing question semantic extraction on the question information according to the product feature words to generate question semantic feature information; In response to determining that the question semantic feature information does not meet a preset question determination condition, displaying supplementary question information in the question-and-answer window according to the question semantic feature information, and displaying a three-dimensional simulation model of the target product in the interface where the question-and-answer window is located, wherein the displayed three-dimensional simulation model matches the question semantic feature information, and the supplementary question information is generated through the following steps: Determining missing question information of the question semantic feature information, and generating supplementary question information according to the missing question information; Wherein, the displaying supplementary question information in the question-and-answer window according to the question semantic feature information in response to determining that the question semantic feature information does not meet a preset question determination condition includes: Retrieving product question description information matching the product feature words from a product question database; In response to the product question description information not matching the question semantic feature information, determining that the question semantic feature information does not meet a preset question determination condition; Displaying supplementary question information in the question-and-answer window according to the question semantic feature information; In response to detecting supplementary reply information for the supplementary question, performing feature fusion on the supplementary reply information and the question semantic feature information to obtain fused question feature information; Performing question retrieval on a preset product question database according to the fused question feature information to obtain product question feedback information, and displaying the product question feedback information in the question-and-answer window, wherein the product question feedback information includes product accessory replacement information; In response to detecting a confirmation operation for the product accessory replacement information in the product question feedback information, shipping product accessories according to the product accessory replacement information.

2. The method according to claim 1, wherein, The method further includes: Decomposing the fused question feature information to obtain a decomposed question data chain; Updating the decomposed question data chain to the product question database.

3. The method according to claim 1, wherein The displaying the three-dimensional simulation model of the target product in the interface where the question-and-answer window is located includes: Invoking a product simulation model corresponding to the target product from a database, wherein the product simulation model is constructed according to the product structure of the target product; Determining product component nodes in the product simulation model that match the product feature words; Rendering the product component nodes, and adjusting the display perspective of the product simulation model to display the rendered product component nodes, wherein a product digital passport of the target product is also displayed in the interface where the question-and-answer window is located.

4. The method according to claim 1, wherein, Determining the missing problem information of the problem semantic feature information, and generating supplementary problem information according to the missing problem information, including: Extracting user requirement feature words from the problem semantic feature information, and in response to the failure to extract, instructing the user to send user requirement feature words through the Q&A window; In response to determining that the user requirement feature words belong to the product failure category, extracting a set of product failure problem chains corresponding to product component nodes from the product problem database, where each product failure problem chain in the set of product failure problem chains includes at least one component failure node, and the component failure nodes are connected by failure pointer information; Using the user requirement feature words and the problem semantic feature information to select a matching product failure problem chain from the set of product failure problem chains as the target product failure problem chain; Taking the product feature words as the core words, generating supplementary problem information according to a preset set of problem description sentence patterns, where the supplementary problem information includes a set of supplementary problem prompt texts corresponding to the target product failure problem chain, and each supplementary problem prompt text in the set of supplementary problem prompt texts corresponds to a problem; Sequentially sending the set of supplementary problem prompt texts in the supplementary problem information to the Q&A window for display for the user to reply.

5. The method according to claim 4, wherein, Performing feature fusion on the supplementary reply information and the problem semantic feature information to obtain fused problem feature information, including: Determining the user reply results corresponding to each supplementary problem prompt text in the supplementary reply information; Determining the problem fields in the product problem database corresponding to each user reply result to obtain a set of problem fields; Adding the set of problem fields to the problem semantic feature information to obtain fused problem feature information.

6. A data processing device, including: A semantic recognition unit configured to, in response to detecting problem information sent by a user for a target product in a Q&A window on a product information interaction platform, perform semantic recognition on the problem information to obtain problem semantic feature information; The semantic recognition unit is further configured to: Extract product feature words from the problem information; Perform problem semantic extraction on the problem information according to the product feature words to generate problem semantic feature information; A display unit configured to, in response to determining that the problem semantic feature information does not meet a preset problem determination condition, display supplementary problem information in the Q&A window according to the problem semantic feature information, and display a three-dimensional simulation model of the target product on the interface where the Q&A window is located, where the displayed three-dimensional simulation model matches the problem semantic feature information, and the supplementary problem information is generated through the following steps: Determining the missing problem information of the problem semantic feature information, and generating supplementary problem information according to the missing problem information; The display unit is further configured to: Retrieve product problem description information matching the product feature words from a product problem database; In response to the mismatch between the product problem description information and the problem semantic feature information, it is determined that the problem semantic feature information does not meet the preset problem determination conditions; According to the problem semantic feature information, supplementary question information is displayed within the Q&A window; A feature fusion unit, configured to perform feature fusion on the supplementary reply information and the problem semantic feature information in response to detecting supplementary reply information for the supplementary question, to obtain fused problem feature information; A problem retrieval unit, configured to perform problem retrieval on a preset product problem database according to the fused problem feature information, to obtain product problem feedback information, and display the product problem feedback information in the Q&A window, where the product problem feedback information includes product accessory replacement information; A confirmation and shipping unit, configured to perform product accessory shipping according to the product accessory replacement information in response to detecting a confirmation operation for the product accessory replacement information in the product problem feedback information.

7. An electronic device, comprising: One or more processors; A storage device having stored thereon one or more programs, When the one or more programs are executed by the one or more processors, the one or more processors implement the method according to any one of claims 1-5.

8. A computer-readable medium having a computer program stored thereon, wherein, The computer program, when executed by a processor, implements the method according to any one of claims 1-5.

Images