Vehicle quality similar problem table generation method and device and computer equipment
By generating a vehicle quality similarity problem table and using text vectorization technology to identify the similarity of vehicle quality problems, the problems of low efficiency and inability to identify similarity in traditional query methods are solved, and query efficiency and accuracy are improved.
Patent Information
- Application Number
- CN202411323490.9
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-09-23
- Publication Date
- 2025-01-10
AI Technical Summary
The traditional vehicle quality problem query method is inefficient in querying and cannot identify the similarity of vehicle quality problems, which affects the user experience.
By generating a vehicle quality similarity problem table, using text vector technology to obtain vehicle quality problem description text vectors, calculate the similarity value between the target vehicle and other vehicles, generate a vehicle quality similarity problem table based on the similarity threshold, and accurately identify vehicle quality problems. similarity.
It improves the efficiency and accuracy of vehicle quality problems query, avoids expression differences caused by different personnel or time entry, and enhances query convenience and accuracy.
Smart Images
Figure CN119293036A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of data processing technology, and in particular to a method, device, computer equipment and storage medium for generating a vehicle quality similarity problem table. Background Art
[0002] In recent years, with the continuous development of society and the continuous improvement of people's living standards, people have higher and higher requirements for travel convenience, and traveling by car has become an important way to improve travel convenience. With the mass production of vehicles, the number of vehicles and the frequency of use are gradually increasing, and the importance of vehicle after-sales service has gradually emerged. The timeliness of feedback on vehicle quality issues in after-sales service greatly affects the user experience.
[0003] However, traditional vehicle quality problem query methods have problems such as low query efficiency or inability to identify the similarities of vehicle quality problems. Summary of the invention
[0004] Based on this, it is necessary to provide a vehicle quality problem query method, device, computer equipment and storage medium that can improve query efficiency and accurately identify the similarities of vehicle quality problems in response to the above technical problems.
[0005] In a first aspect, a method for generating a vehicle quality similarity problem table is provided, the method comprising:
[0006] Obtaining a text vector set; wherein the text vector set includes a preset number of vehicle quality problem description text vectors; the vehicle quality problem description text vector is a description text vector that characterizes the vehicle quality problem;
[0007] Calculate in turn according to each target vehicle quality problem description text vector and the corresponding other vehicle quality problem description text vector to obtain the corresponding problem similarity value; wherein the other vehicle quality problem description text vectors are vehicle quality problem description text vectors other than the target vehicle quality problem description text vector in the text vector set; the target vehicle quality problem description text vector is any vehicle quality problem description text vector in the text vector set;
[0008] In response to the existence of target problem similarity, a vehicle quality similarity problem table is generated according to the target vehicle quality problem description text vector corresponding to the target problem similarity and the corresponding other vehicle quality problem description text vectors; wherein the target problem similarity is a problem similarity greater than a similarity threshold.
[0009] In one of the embodiments, obtaining a text vector set includes: obtaining a preset number of standard vehicle quality problem description texts; performing text vectorization on each standard vehicle quality problem description text to obtain a corresponding vehicle quality problem description text vector; and generating a text vector set based on each vehicle quality problem description text vector.
[0010] In one of the embodiments, obtaining a preset number of standard vehicle quality problem description texts includes: obtaining a preset number of vehicle quality problem description information; the vehicle quality problem description information includes semantic tag information, non-semantic tag information and description text information; performing non-semantic tag removal processing on each vehicle quality problem description information to obtain the corresponding processed vehicle quality problem description information; performing format processing and splicing processing on the processed vehicle quality problem description information corresponding to each vehicle quality problem description information to obtain the corresponding standard vehicle quality problem description text.
[0011] In one of the embodiments, obtaining a preset amount of vehicle quality problem description information includes: obtaining enterprise vehicle quality problem statistical information from an enterprise vehicle quality problem database and obtaining national vehicle quality problem statistical information from a national vehicle quality problem public database and storing them in the vehicle quality problem statistical database; wherein the enterprise vehicle quality problem statistical information includes enterprise internal vehicle development quality problem description information, enterprise internal vehicle quality inspection quality problem description information, enterprise internal vehicle production problem description information and enterprise internal vehicle after-sales problem description information; in response to receiving a request to generate a vehicle quality similarity problem table, obtaining a preset amount of vehicle quality problem description information according to the generation request.
[0012] In one of the embodiments, each standard vehicle quality problem description text is vectorized to obtain a corresponding vehicle quality problem description text vector, including: inputting each standard vehicle quality problem description text into a pre-trained natural language semantic vectorization model to obtain a corresponding vehicle quality problem description text vector.
[0013] In one embodiment, a vehicle quality similarity problem table is generated according to the target vehicle quality problem description text vector corresponding to the target problem similarity and the corresponding other vehicle quality problem description text vectors, including:
[0014] Generate a first problem feature identifier according to the target vehicle quality problem description text vector corresponding to the target problem similarity;
[0015] Generate a second problem feature identifier based on other vehicle quality problem description text vectors corresponding to the target problem similarity;
[0016] Determine the first question feature identifier as a first main keyword, and generate a first vehicle quality similarity question table according to the first keyword, the second question feature identifier, and the target question similarity;
[0017] The second question feature identifier is determined as the second main keyword, and a second vehicle quality similarity question table is generated according to the second keyword, the first question feature identifier and the target question similarity; wherein the vehicle quality similarity question table includes the first vehicle quality similarity question table and the second vehicle quality similarity question table.
[0018] In one of the embodiments, the method also includes: storing a vehicle quality similar problem table in a vehicle similar problem database; in response to a quality problem query operation on a vehicle quality management application, querying the problem in a vehicle original problem database according to the result of the query operation to obtain a target problem feature identifier; wherein the vehicle original problem database is used to store each vehicle quality original problem table; the vehicle quality original problem table includes a target problem feature identifier and problem attribute information corresponding to the target problem feature identifier; querying the similar problem database according to the target problem feature identifier to obtain a corresponding vehicle quality similar problem table; parsing the vehicle quality similar problem table according to the target problem feature identifier to obtain corresponding vehicle quality similar problems.
[0019] In a second aspect, a device for generating a vehicle quality similarity question table is provided, the device comprising a vector set acquisition module, a similarity calculation module and a question table generation module.
[0020] Among them, the vector set acquisition module is used to obtain a text vector set; wherein the text vector set includes a preset number of vehicle quality problem description text vectors; the vehicle quality problem description text vector is a description text vector that characterizes vehicle quality problems; the similarity calculation module is used to calculate in turn according to each target vehicle quality problem description text vector and the corresponding other vehicle quality problem description text vectors to obtain the corresponding problem similarity value; wherein the other vehicle quality problem description text vectors are vehicle quality problem description text vectors other than the target vehicle quality problem description text vector in the text vector set; the target vehicle quality problem description text vector is any vehicle quality problem description text vector in the text vector set; the problem table generation module is used to generate a vehicle quality similarity problem table in response to the existence of a target problem similarity according to the target vehicle quality problem description text vector corresponding to the target problem similarity and the corresponding other vehicle quality problem description text vectors; wherein the target problem similarity is a problem similarity greater than a similarity threshold.
[0021] In a third aspect, a computer device is provided. The computer device includes a memory and a processor. The memory stores a computer program. When the processor executes the computer program, the steps of any method in the above method embodiments are implemented.
[0022] In a fourth aspect, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps of any method in the above method embodiments are implemented.
[0023] The above-mentioned method, device, computer equipment and storage medium for generating a vehicle quality similarity problem table obtain a text vector set; wherein the text vector set includes a preset number of vehicle quality problem description text vectors; the vehicle quality problem description text vector is used to characterize the description text vector of the vehicle quality problem; then, calculations are performed in turn based on each target vehicle quality problem description text vector and the corresponding other vehicle quality problem description text vectors to obtain the corresponding problem similarity value; wherein the other vehicle quality problem description text vectors are vehicle quality problem description text vectors other than the target vehicle quality problem description text vector in the text vector set; the target vehicle quality problem description text vector is any vehicle quality problem description text vector in the text vector set; then, in response to the existence of the target problem similarity, a vehicle quality similarity problem table is generated based on the target vehicle quality problem description text vector corresponding to the target problem similarity and the corresponding other vehicle quality problem description text vectors; wherein the target problem similarity is a problem similarity greater than a similarity threshold, so that the similarity of vehicle quality problems can be accurately identified through the vehicle quality similarity problem table, and the query efficiency of vehicle quality problems can be avoided by avoiding the difference in expressions caused by vehicle quality problems being entered by different people or at different times, thereby improving the query efficiency, accuracy and convenience. BRIEF DESCRIPTION OF THE DRAWINGS
[0024] Figure 1 FIG. 1 is an application environment diagram of a method for generating a vehicle quality similarity problem table in one embodiment;
[0025] Figure 2 It is a first flow chart of a method for generating a vehicle quality similarity problem table in one embodiment;
[0026] Figure 3 A schematic diagram of a process for obtaining a text vector set in one embodiment;
[0027] Figure 4 A schematic diagram of a flow chart for obtaining a preset number of standard vehicle quality problem description texts in one embodiment;
[0028] Figure 5 A schematic diagram of a process for obtaining a preset amount of vehicle quality problem description information in one embodiment;
[0029] Figure 6A schematic diagram of a process for generating a vehicle quality similarity problem table according to a target vehicle quality problem description text vector corresponding to a target problem similarity and corresponding other vehicle quality problem description text vectors in one embodiment;
[0030] Figure 7 A second flow chart of a method for generating a vehicle quality similarity problem table in one embodiment;
[0031] Figure 8 is a structural block diagram of a device for generating a vehicle quality similarity problem table in one embodiment;
[0032] Fig. 9 FIG. 4 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION
[0033] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.
[0034] In order to facilitate understanding of the present application, the present application will be described more fully below with reference to the relevant drawings. Embodiments of the present application are provided in the drawings. However, the present application can be implemented in many different forms and is not limited to the embodiments described herein. On the contrary, the purpose of providing these embodiments is to make the disclosure of the present application more thorough and comprehensive.
[0035] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art to which this application belongs. The terms used herein in the specification of this application are only for the purpose of describing specific embodiments and are not intended to limit this application.
[0036] It is understood that the terms "first", "second", etc. used in this application may be used herein to describe various elements, but these elements are not limited by these terms. These terms are only used to distinguish a first element from another element. For example, without departing from the scope of this application, a first resistor may be referred to as a second resistor, and similarly, a second resistor may be referred to as a first resistor. Both the first resistor and the second resistor are resistors, but they are not the same resistor.
[0037] It can be understood that the “connection” in the following embodiments should be understood as “electrical connection”, “communication connection”, etc. if the connected circuits, modules, units, etc. have electrical signals or data transmission between each other.
[0038] When used herein, the singular forms "a", "an", and "said / the" may also include plural forms, unless the context clearly indicates otherwise. It should also be understood that the terms "include / comprise" or "have" etc. specify the presence of stated features, wholes, steps, operations, components, parts or combinations thereof, but do not exclude the possibility of the presence or addition of one or more other features, wholes, steps, operations, components, parts or combinations thereof.
[0039] The method for generating a vehicle quality similarity problem table provided in this application can be applied to Figure 1 In the application environment shown, the terminal 102 communicates with the server 104 through a network. The terminal 102 may be, but is not limited to, various personal computers, laptops, smart phones, tablet computers, and portable wearable devices, and the server 104 may be implemented as an independent server or a server cluster consisting of multiple servers.
[0040] In one embodiment, Figure 2 As shown, a method for generating a vehicle quality similarity problem table is provided, and the method is applied to Figure 1 The server 104 in the example is used for explanation, and the steps include the following steps 201 to 203.
[0041] Step 201, obtaining a text vector set.
[0042] The text vector set includes a preset number of vehicle quality problem description text vectors; the vehicle quality problem description text vector is a description text vector that characterizes the vehicle quality problem. Specifically, the server 104 may obtain the text vector set.
[0043] In one embodiment, if Figure 3 As shown, obtain the text vector set, including:
[0044] Step 301, obtaining a preset number of standard vehicle quality problem description texts.
[0045] The standard vehicle quality problem description text is a vehicle quality problem description text in a standard format after data processing. Specifically, the server 104 obtains a preset number of standard vehicle quality problem description texts.
[0046] In one embodiment, if Figure 4 As shown, obtaining a preset number of standard vehicle quality problem description texts includes steps 401 to 403.
[0047] Step 401, obtaining a preset amount of vehicle quality problem description information.
[0048] Step 402 , performing non-semantic label removal processing on each vehicle quality problem description information to obtain corresponding processed vehicle quality problem description information.
[0049] Step 403, formatting and splicing the processed vehicle quality problem description information corresponding to each vehicle quality problem description information to obtain a corresponding standard vehicle quality problem description text.
[0050] The vehicle quality problem description information includes semantic tag information, non-semantic tag information and description text information. Format processing may include, but is not limited to, bracket removal processing. Specifically, the server 104 obtains a preset number of vehicle quality problem description information; then, performs non-semantic tag removal processing on each vehicle quality problem description information to obtain the corresponding processed vehicle quality problem description information; then, performs format processing and splicing processing on the processed vehicle quality problem description information corresponding to each vehicle quality problem description information to obtain the corresponding standard vehicle quality problem description text, thereby improving the quality, efficiency and convenience of obtaining the standard vehicle quality problem description text.
[0051] In one embodiment, if Figure 5 As shown, obtaining a preset amount of vehicle quality problem description information includes steps 501 to 502.
[0052] Step 501, the enterprise vehicle quality problem statistical information obtained from the enterprise vehicle quality problem database and the national vehicle quality problem statistical information obtained from the national vehicle quality problem public database are stored in the vehicle quality problem statistical database.
[0053] Step 502, in response to receiving a request to generate a vehicle quality similarity problem table, obtaining a preset amount of vehicle quality problem description information according to the generation request.
[0054] Among them, the enterprise vehicle quality problem statistics include the description information of the enterprise's internal vehicle development quality problems, the description information of the enterprise's internal vehicle quality inspection quality problems, the description information of the enterprise's internal vehicle production problems and the description information of the enterprise's internal vehicle after-sales problems. It is understandable that the National Vehicle Quality Problem Public Database is used to store the national vehicle quality problem statistics of the General Administration of Quality Supervision, Inspection and Quarantine and the national vehicle quality problem statistics published by international authoritative media.
[0055] Specifically, the server 104 can obtain enterprise vehicle quality problem statistical information from the enterprise vehicle quality problem database and national vehicle quality problem statistical information from the national vehicle quality problem public database, and store them in the vehicle quality problem statistical database; then, when it recognizes that a request to generate a vehicle quality similar problem table has been received, a preset amount of vehicle quality problem description information is obtained according to the generation request, thereby improving the quality, efficiency and convenience of obtaining the vehicle quality problem description information.
[0056] In this embodiment, enterprise vehicle quality problem statistical information obtained from the enterprise vehicle quality problem database and national vehicle quality problem statistical information obtained from the national vehicle quality problem public database are stored in the vehicle quality problem statistical database; then, in response to receiving a request to generate a vehicle quality similar problem table, a preset amount of vehicle quality problem description information is obtained according to the generation request, thereby improving the quality, efficiency and convenience of obtaining the vehicle quality problem description information.
[0057] In a specific example, the vehicle quality problem description information is "[Power Management][S2-SPO1][EVR Four-wheel Drive][Probability: 1 / 4] When the range extender is started, the BMS sends a high-voltage request due to low battery, and the VDC does not make a judgment, and responds to the high voltage power-off." It can be understood that the semantically tagged information is "[Power Management]", and the non-semantically tagged information is "[S2-SPO1][EVR Four-wheel Drive][Probability: 1 / 4]", and the description text information is "When the range extender is started, the BMS sends a high-voltage request due to low battery, and the VDC does not make a judgment, and responds to the high voltage power-off." By removing the semantic labels from the vehicle quality problem description information, the corresponding processed vehicle quality problem description information is obtained as "[Power Management]" and "When starting the extended range, the BMS sends a high-voltage request due to low battery, and the VDC does not make a judgment, and responds to the high voltage power-off"; then, after formatting the processed vehicle quality problem description information corresponding to the vehicle quality problem description information, "Power Management" and "When starting the extended range, the BMS sends a high-voltage request due to low battery, and the VDC does not make a judgment, and responds to the high voltage power-off" are obtained; then "Power Management" and "When starting the extended range, the BMS sends a high-voltage request due to low battery, and the VDC does not make a judgment, and responds to the high voltage power-off" are spliced to obtain the standard vehicle quality problem description text as "When power management starts the extended range, the BMS sends a high-voltage request due to low battery, and the VDC does not make a judgment, and responds to the high voltage power-off". The above are only specific examples, which are flexibly set according to user needs in actual applications and are not limited here.
[0058] In this embodiment, a preset number of vehicle quality problem description information is obtained; then, the non-semantic label removal processing is performed on each vehicle quality problem description information to obtain the corresponding processed vehicle quality problem description information; then, the processed vehicle quality problem description information corresponding to each vehicle quality problem description information is formatted and spliced to obtain the corresponding standard vehicle quality problem description text, thereby improving the quality, efficiency and convenience of obtaining the standard vehicle quality problem description text.
[0059] Step 302 , vectorize each standard vehicle quality problem description text to obtain a corresponding vehicle quality problem description text vector.
[0060] Step 303: Generate a text vector set according to the text vectors describing the quality issues of each vehicle.
[0061] Specifically, the server 104 performs text vectorization on each standard vehicle quality problem description text to obtain a corresponding vehicle quality problem description text vector; then, a text vector set is generated based on each vehicle quality problem description text vector, thereby improving the efficiency and convenience of obtaining the text vector set.
[0062] In one embodiment, each standard vehicle quality problem description text is vectorized to obtain a corresponding vehicle quality problem description text vector, including:
[0063] The description texts of each standard vehicle quality problem are input into a pre-trained natural language semantic vectorization model to obtain the corresponding vehicle quality problem description text vector.
[0064] Specifically, the server 104 can input each standard vehicle quality problem description text into a pre-trained natural language semantic vectorization model to obtain a corresponding vehicle quality problem description text vector, thereby improving the efficiency and convenience of text vectorization.
[0065] In this embodiment, each standard vehicle quality problem description text is input into a pre-trained natural language semantic vectorization model to obtain a corresponding vehicle quality problem description text vector, thereby improving the efficiency and convenience of text vectorization.
[0066] In a specific example, the natural language semantic vectorization model can be but is not limited to the StructBert semantic vectorization model. The above is only a specific example. In actual applications, it is flexibly set according to user needs and is not limited here.
[0067] In this embodiment, a preset number of standard vehicle quality problem description texts are obtained; then, each standard vehicle quality problem description text is vectorized to obtain a corresponding vehicle quality problem description text vector; then, a text vector set is generated based on each vehicle quality problem description text vector, thereby improving the efficiency and convenience of obtaining the text vector set.
[0068] Step 202 , calculating in turn based on each target vehicle quality problem description text vector and the corresponding other vehicle quality problem description text vectors to obtain a corresponding problem similarity value.
[0069] Among them, other vehicle quality problem description text vectors are vehicle quality problem description text vectors other than the target vehicle quality problem description text vector in the text vector set; and the target vehicle quality problem description text vector is any vehicle quality problem description text vector in the text vector set.
[0070] Specifically, the server 104 performs calculations in sequence based on each target vehicle quality problem description text vector and the corresponding other vehicle quality problem description text vectors to obtain a corresponding problem similarity value.
[0071] In a specific example, the preset number is N, and there are N vehicle quality problem description text vectors in the text vector set, so each target vehicle quality problem description text vector corresponds to N-1 other vehicle quality problem description text vectors, and then each target vehicle quality problem description text vector can calculate the corresponding N-1 problem similarity values. The above is only a specific example, and it can be flexibly set according to user needs in actual applications, and is not limited here.
[0072] Step 203 , in response to the existence of the target problem similarity, a vehicle quality similarity problem table is generated according to the target vehicle quality problem description text vector corresponding to the target problem similarity and the corresponding other vehicle quality problem description text vectors.
[0073] Among them, the target problem similarity is the problem similarity greater than the similarity threshold. When the server 104 recognizes the existence of the target problem similarity, it means that the target vehicle quality problem description text vector corresponding to the target problem similarity and the corresponding other vehicle quality problem description text vectors have a large similarity, so a vehicle quality similarity problem table can be generated according to the target vehicle quality problem description text vector corresponding to the target problem similarity and the corresponding other vehicle quality problem description text vectors, so as to accurately identify the similarity of vehicle quality problems through the vehicle quality similarity problem table, and avoid the query efficiency of vehicle quality problems affected by the difference in expressions caused by vehicle quality problems being entered by different people or at different times, thereby improving the query efficiency, accuracy and convenience.
[0074] In a specific example, in response to the absence of target problem similarity, a prompt message is output that the target vehicle quality problem description text vector has no vehicle quality similarity problem. The above is only a specific example. In actual application, it is flexibly set according to user needs and is not limited here.
[0075] In one embodiment, if Figure 6 As shown, a vehicle quality similarity problem table is generated according to the target vehicle quality problem description text vector corresponding to the target problem similarity and the corresponding other vehicle quality problem description text vectors, including steps 601 to 604.
[0076] Step 601: Generate a first problem feature identifier according to a target vehicle quality problem description text vector corresponding to the target problem similarity.
[0077] Step 602: Generate a second problem feature identifier based on other vehicle quality problem description text vectors corresponding to the target problem similarity.
[0078] Step 603: determine the first question feature identifier as the first main keyword, and generate a first vehicle quality similarity question table according to the first keyword, the second question feature identifier and the target question similarity.
[0079] Step 604: determine the second question feature identifier as a second main keyword, and generate a second vehicle quality similarity question table according to the second keyword, the first question feature identifier and the target question similarity.
[0080] Among them, the vehicle quality similarity question table includes a first vehicle quality similarity question table and a second vehicle quality similarity question table. Specifically, the server 104 generates a first question feature identifier based on the target vehicle quality question description text vector corresponding to the target question similarity; then, generates a second question feature identifier based on other vehicle quality question description text vectors corresponding to the target question similarity; then, the first question feature identifier is determined as the first main keyword, and the first vehicle quality similarity question table is generated based on the first keyword, the second question feature identifier and the target question similarity; finally, the second question feature identifier is determined as the second main keyword, and the second vehicle quality similarity question table is generated based on the second keyword, the first question feature identifier and the target question similarity, thereby improving the comprehensiveness of the records of the vehicle quality similarity question table and the retrieval accuracy, and avoiding the reduction of query accuracy due to the incomplete records of the vehicle quality similarity question table.
[0081] In a specific example, the first problem feature is identified as id1, the second problem feature is identified as id2, and the target problem similarity is sim(id1, id2). The symmetric data (id1, id2, sim(id1, id2)) and (id2, id1, sim(id1, id2)) are respectively generated into the corresponding first vehicle quality similarity problem table and second vehicle quality similarity problem table.
[0082] As shown in the following table, Table 1 is the original vehicle quality problem table
[0083] Vehicle quality original problem table id Question attribute information 1 Question attribute information 2
[0084] Among them, id in Table 1 is the target problem feature identifier, and problem attribute information 1 and problem attribute information 2 are used to characterize the attribute information of the problem solution or problem component.
[0085] As shown in the following table, Table 2 is the first vehicle quality similarity problem table
[0086] Vehicle quality original problem table id1 id2 sim(id1,id2)
[0087] As shown in the following table, Table 3 is a table of similar problems of the second vehicle quality.
[0088] Vehicle quality original problem table id2 id1 sim(id1,id2)
[0089] The above are only specific examples, which can be flexibly configured according to user needs in actual applications and are not limited here.
[0090] In this embodiment, a first problem feature identifier is generated according to a target vehicle quality problem description text vector corresponding to the target problem similarity; then, a second problem feature identifier is generated according to other vehicle quality problem description text vectors corresponding to the target problem similarity; then, the first problem feature identifier is determined as the first main keyword, and a first vehicle quality similarity problem table is generated according to the first keyword, the second problem feature identifier and the target problem similarity; finally, the second problem feature identifier is determined as the second main keyword, and a second vehicle quality similarity problem table is generated according to the second keyword, the first problem feature identifier and the target problem similarity, thereby improving the comprehensiveness of the records in the vehicle quality similarity problem table and the retrieval accuracy, and avoiding a reduction in query accuracy due to incomplete records in the vehicle quality similarity problem table.
[0091] Based on this, the above-mentioned method for generating a vehicle quality similarity problem table obtains a text vector set; wherein the text vector set includes a preset number of vehicle quality problem description text vectors; the vehicle quality problem description text vector is used to characterize the description text vector of the vehicle quality problem; then, calculations are performed in turn according to each target vehicle quality problem description text vector and the corresponding other vehicle quality problem description text vectors to obtain the corresponding problem similarity value; wherein the other vehicle quality problem description text vectors are vehicle quality problem description text vectors other than the target vehicle quality problem description text vector in the text vector set; the target vehicle quality problem description text vector is any vehicle quality problem description text vector in the text vector set; then, in response to the existence of the target problem similarity, a vehicle quality similarity problem table is generated according to the target vehicle quality problem description text vector corresponding to the target problem similarity and the corresponding other vehicle quality problem description text vectors; wherein the target problem similarity is a problem similarity greater than a similarity threshold, so that the similarity of vehicle quality problems can be accurately identified through the vehicle quality similarity problem table, and the query efficiency of vehicle quality problems can be avoided by avoiding the difference in expressions caused by vehicle quality problems being entered by different people or at different times, thereby improving the query efficiency, accuracy and convenience.
[0092] In one embodiment, if Figure 7 As shown, the method also includes:
[0093] Step 701, storing the vehicle quality similarity problem table in the vehicle similarity problem database.
[0094] Step 702, in response to a query operation of a quality problem on a vehicle quality management application, a problem query is performed in a vehicle original problem database according to a result of the query operation to obtain a target problem feature identifier.
[0095] Step 703: query the similar problem database according to the target problem feature identifier to obtain a corresponding vehicle quality similar problem table.
[0096] Step 704: parse the vehicle quality similarity problem table according to the target problem feature identifier to obtain the corresponding vehicle quality similarity problem.
[0097] The vehicle original problem database is used to store the original problem table of each vehicle quality; the vehicle quality original problem table includes the target problem feature identifier and the problem attribute information corresponding to the target problem feature identifier.
[0098] Specifically, the server 104 can store the vehicle quality similar problem table in the vehicle similar problem database; then, in response to the query operation of the quality problem on the vehicle quality management application, the problem query is performed in the vehicle original problem database according to the result of the query operation to obtain the target problem feature identifier; then, the query is performed in the similar problem database according to the target problem feature identifier to obtain the corresponding vehicle quality similar problem table; finally, the vehicle quality similar problem table is parsed according to the target problem feature identifier to obtain the corresponding vehicle quality similar problems, so as to accurately identify the similarity of vehicle quality problems through the vehicle quality similar problem table, and the query efficiency of vehicle quality problems can be affected by the difference in expression caused by the vehicle quality problems being entered by different people or at different times, thereby improving the query efficiency, accuracy and convenience.
[0099] In a specific example, the method also includes: performing a problem query in a vehicle original problem database based on similar vehicle quality problems to obtain a target vehicle quality original problem table; parsing the target vehicle quality original problem table to obtain corresponding problem attribute information, thereby understanding solutions and problem accessories for similar vehicle quality problems through the problem attribute information corresponding to the target vehicle quality original problem table, thereby improving the convenience of problem query.
[0100] In this embodiment, a vehicle quality similarity problem table is stored in a vehicle similarity problem database; then, in response to a quality problem query operation on a vehicle quality management application, a problem query is performed in the vehicle original problem database according to the result of the query operation to obtain a target problem feature identifier; then, a query is performed in the similar problem database according to the target problem feature identifier to obtain a corresponding vehicle quality similarity problem table; finally, the vehicle quality similarity problem table is parsed according to the target problem feature identifier to obtain corresponding vehicle quality similar problems, thereby accurately identifying the similarity of vehicle quality problems through the vehicle quality similarity problem table, thereby avoiding the query efficiency of vehicle quality problems affected by differences in expressions caused by vehicle quality problems being entered by different people or at different times, thereby improving query efficiency, accuracy and convenience.
[0101] It should be understood that although Figure 2-7 The steps in the flowchart are shown in sequence as indicated by the arrows, but these steps are not necessarily executed in the order indicated by the arrows. Unless otherwise specified in this document, there is no strict order restriction for the execution of these steps, and these steps can be executed in other orders. Moreover, Figure 2-7At least part of the steps may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily executed at the same time, but can be executed at different times. The execution order of these sub-steps or stages is not necessarily sequential, but can be executed in turn or alternately with other steps or at least part of the sub-steps or stages of other steps.
[0102] Second, as Figure 8 As shown, a device for generating a vehicle quality similarity question table is provided, and the device includes a vector set acquisition module 810, a similarity calculation module 820 and a question table generation module 830.
[0103] Among them, the vector set acquisition module 810 is used to obtain a text vector set; wherein the text vector set includes a preset number of vehicle quality problem description text vectors; the vehicle quality problem description text vector is a description text vector that characterizes vehicle quality problems; the similarity calculation module 820 is used to calculate in turn according to each target vehicle quality problem description text vector and the corresponding other vehicle quality problem description text vectors to obtain the corresponding problem similarity value; wherein the other vehicle quality problem description text vectors are vehicle quality problem description text vectors other than the target vehicle quality problem description text vector in the text vector set; the target vehicle quality problem description text vector is any vehicle quality problem description text vector in the text vector set; the problem table generation module 830 is used to generate a vehicle quality similarity problem table in response to the existence of a target problem similarity according to the target vehicle quality problem description text vector corresponding to the target problem similarity and the corresponding other vehicle quality problem description text vectors; wherein the target problem similarity is a problem similarity greater than a similarity threshold.
[0104] In one embodiment, the vector set acquisition module 810 includes a vector set generation unit.
[0105] Among them, the vector set generation unit is used to obtain a preset number of standard vehicle quality problem description texts; the vector set generation unit is used to perform text vectorization on each standard vehicle quality problem description text to obtain a corresponding vehicle quality problem description text vector; the vector set generation unit is used to generate a text vector set based on each vehicle quality problem description text vector.
[0106] In one of the embodiments, the vector set generating unit includes a question description text acquiring subunit.
[0107] Among them, the problem description text acquisition subunit is used to obtain a preset number of vehicle quality problem description information; the vehicle quality problem description information includes semantic label information, non-semantic label information and description text information; the problem description text acquisition subunit is used to remove the non-semantic labels of each vehicle quality problem description information to obtain the corresponding processed vehicle quality problem description information; the problem description text acquisition subunit is used to format and splice the processed vehicle quality problem description information corresponding to each vehicle quality problem description information to obtain the corresponding standard vehicle quality problem description text.
[0108] In one of the embodiments, the problem description text acquisition subunit includes a vehicle quality problem description information acquirer.
[0109] Among them, the vehicle quality problem description information acquirer is used to acquire enterprise vehicle quality problem statistical information from the enterprise vehicle quality problem database and acquire national vehicle quality problem statistical information from the national vehicle quality problem public database and store them in the vehicle quality problem statistical database; wherein the enterprise vehicle quality problem statistical information includes enterprise internal vehicle development quality problem description information, enterprise internal vehicle quality inspection quality problem description information, enterprise internal vehicle production problem description information and enterprise internal vehicle after-sales problem description information; the vehicle quality problem description information acquirer is used to respond to a request for generating a vehicle quality similar problem table, and acquire a preset number of vehicle quality problem description information according to the generation request.
[0110] In one of the embodiments, the vector set generation unit includes a vectorization subunit.
[0111] Among them, the vectorization subunit is used to input each standard vehicle quality problem description text into a pre-trained natural language semantic vectorization model to obtain the corresponding vehicle quality problem description text vector.
[0112] In one of the embodiments, the question table generation module includes a question table generation unit.
[0113] Among them, the problem table generation unit is used to generate a first problem feature identifier according to a target vehicle quality problem description text vector corresponding to the target problem similarity; the problem table generation unit is used to generate a second problem feature identifier according to other vehicle quality problem description text vectors corresponding to the target problem similarity; the problem table generation unit is used to determine the first problem feature identifier as the first main keyword, and generate a first vehicle quality similarity problem table according to the first keyword, the second problem feature identifier and the target problem similarity; the problem table generation unit is used to determine the second problem feature identifier as the second main keyword, and generate a second vehicle quality similarity problem table according to the second keyword, the first problem feature identifier and the target problem similarity; wherein the vehicle quality similarity problem table includes a first vehicle quality similarity problem table and a second vehicle quality similarity problem table.
[0114] In one of the embodiments, the device further includes a similar question query module.
[0115] Among them, the similar problem query module is used to store the vehicle quality similar problem table in the vehicle similar problem database; the similar problem query module is used to respond to the query operation of the quality problem on the vehicle quality management application, and perform problem query in the vehicle original problem database according to the result of the query operation to obtain the target problem feature identifier; wherein the vehicle original problem database is used to store each vehicle quality original problem table; the vehicle quality original problem table includes the target problem feature identifier and the problem attribute information corresponding to the target problem feature identifier; the similar problem query module is used to query in the similar problem database according to the target problem feature identifier to obtain the corresponding vehicle quality similar problem table; the similar problem query module is used to parse the vehicle quality similar problem table according to the target problem feature identifier to obtain the corresponding vehicle quality similar problem.
[0116] The specific limitations of the device for generating the vehicle quality similarity problem table can be found in the limitations of the method for generating the vehicle quality similarity problem table mentioned above, which will not be repeated here. Each module in the above-mentioned device for generating the vehicle quality similarity problem table can be implemented in whole or in part by software, hardware and a combination thereof. The above-mentioned modules can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory of the computer device in the form of software, so that the processor can call and execute the operations corresponding to the above modules.
[0117] In one embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as follows: Fig. 9As shown. The computer device includes a processor, a memory, a network interface and a database connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store text vector set data. The network interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a method for generating a vehicle quality similarity problem table is implemented.
[0118] Those skilled in the art will understand that Fig. 9 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.
[0119] In a third aspect, a computer device is provided. The computer device includes a memory and a processor. The memory stores a computer program. When the processor executes the computer program, the steps of any method in the above method embodiments are implemented.
[0120] In a fourth aspect, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps of any method in the above method embodiments are implemented.
[0121] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).
[0122] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.
[0123] The above-mentioned embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the invention patent. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the patent of the present application shall be subject to the attached claims.
Claims
1. A method for generating a vehicle quality similarity problem table, the method comprising: Acquire a text vector set; wherein the text vector set includes a preset number of vehicle quality problem description text vectors; the vehicle quality problem description text vector is a description text vector that characterizes the vehicle quality problem; Calculating in turn according to each of the target vehicle quality problem description text vectors and the corresponding other vehicle quality problem description text vectors to obtain corresponding problem similarity values; wherein the other vehicle quality problem description text vectors are the vehicle quality problem description text vectors other than the target vehicle quality problem description text vector in the text vector set; the target vehicle quality problem description text vector is any of the vehicle quality problem description text vectors in the text vector set; In response to the existence of a target problem similarity, a vehicle quality similarity problem table is generated according to the target vehicle quality problem description text vector corresponding to the target problem similarity and the corresponding other vehicle quality problem description text vectors; wherein the target problem similarity is the problem similarity greater than a similarity threshold.
2. The method according to claim 1, characterized in that The step of obtaining a text vector set includes: Obtaining the preset number of standard vehicle quality problem description texts; Perform text vectorization on each standard vehicle quality problem description text to obtain the corresponding vehicle quality problem description text vector; The text vector set is generated according to each of the vehicle quality problem description text vectors.
3. The method according to claim 2, characterized in that The step of obtaining the preset number of standard vehicle quality problem description texts includes: Acquire the preset amount of vehicle quality problem description information; the vehicle quality problem description information includes semantic tag information, non-semantic tag information and description text information; Performing semantic label removal processing on each of the vehicle quality problem description information to obtain the corresponding processed vehicle quality problem description information; The processed vehicle quality problem description information corresponding to each piece of vehicle quality problem description information is formatted and spliced to obtain the corresponding standard vehicle quality problem description text.
4. The method according to claim 3, characterized in that The obtaining of the preset amount of vehicle quality problem description information includes: The enterprise vehicle quality problem statistical information obtained from the enterprise vehicle quality problem database and the national vehicle quality problem statistical information obtained from the national vehicle quality problem public database are stored in the vehicle quality problem statistical database; wherein the enterprise vehicle quality problem statistical information includes the description information of the enterprise's internal vehicle development quality problem, the description information of the enterprise's internal vehicle quality inspection quality problem, the description information of the enterprise's internal vehicle production problem and the description information of the enterprise's internal vehicle after-sales problem; In response to receiving a request to generate the vehicle quality similarity problem table, the preset amount of vehicle quality problem description information is obtained according to the generation request.
5. The method according to claim 2, characterized in that: The text vectorization of each standard vehicle quality problem description text to obtain a corresponding vehicle quality problem description text vector includes: Each of the standard vehicle quality problem description texts is input into a pre-trained natural language semantic vectorization model to obtain a corresponding vehicle quality problem description text vector.
6. The method according to any one of claims 1 to 5, characterized in that: The generating a vehicle quality similarity problem table according to the target vehicle quality problem description text vector corresponding to the target problem similarity and the corresponding other vehicle quality problem description text vectors includes: Generate a first problem feature identifier according to the target vehicle quality problem description text vector corresponding to the target problem similarity; Generate a second problem feature identifier according to the other vehicle quality problem description text vector corresponding to the target problem similarity; Determine the first problem feature identifier as a first main keyword, and generate a first vehicle quality similarity question table according to the first keyword, the second problem feature identifier and the target problem similarity; The second question feature identifier is determined as a second main keyword, and a second vehicle quality similarity question table is generated according to the second keyword, the first question feature identifier and the target question similarity; wherein the vehicle quality similarity question table includes the first vehicle quality similarity question table and the second vehicle quality similarity question table.
7. The method according to claim 6, characterized in that The method further comprises: Storing the vehicle quality similarity problem table in a vehicle similarity problem database; In response to a query operation of a quality problem on a vehicle quality management application, a problem query is performed in a vehicle original problem database according to a result of the query operation to obtain a target problem feature identifier; wherein the vehicle original problem database is used to store each vehicle quality original problem table; the vehicle quality original problem table includes a target problem feature identifier and problem attribute information corresponding to the target problem feature identifier; Searching the similar problem database according to the target problem feature identifier to obtain the corresponding vehicle quality similar problem table; The vehicle quality similarity problem table is parsed according to the target problem feature identifier to obtain corresponding vehicle quality similarity problems.
8. A device for generating a vehicle quality similarity problem table, characterized in that: The device comprises: A vector set acquisition module, used to acquire a text vector set; wherein the text vector set includes a preset number of vehicle quality problem description text vectors; the vehicle quality problem description text vectors are description text vectors that characterize vehicle quality problems; A similarity calculation module is used to calculate in turn according to each of the target vehicle quality problem description text vectors and the corresponding other vehicle quality problem description text vectors to obtain corresponding problem similarity values; wherein the other vehicle quality problem description text vectors are the vehicle quality problem description text vectors other than the target vehicle quality problem description text vector in the text vector set; the target vehicle quality problem description text vector is any of the vehicle quality problem description text vectors in the text vector set; A problem table generation module is used to generate a vehicle quality similarity problem table in response to the existence of a target problem similarity according to the target vehicle quality problem description text vector corresponding to the target problem similarity and the corresponding other vehicle quality problem description text vectors; wherein the target problem similarity is the problem similarity greater than a similarity threshold.
9. A computer device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 7 are implemented.
10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.