A body comprehensive testing fixture matching degree evaluation method and system

Abstract

The application provides a vehicle body comprehensive testing tool matching degree evaluation method and system, wherein the method comprises the following steps: acquiring first multi-modal data of a vehicle body and second multi-modal data of a comprehensive testing tool respectively; based on a pre-established vehicle body-testing tool matching model, the vehicle body and the comprehensive testing tool are matched according to the first multi-modal data and the second multi-modal data, and a matching result is obtained; based on the matching result, the matching degree is evaluated, and an adjustment suggestion of the comprehensive testing tool is decided; and the matching result, the matching degree and the adjustment suggestion are output. According to the application, the design model or sample of the comprehensive testing tool does not need to be matched with the vehicle body manually by workers according to experience, so that the labor cost is reduced, the design efficiency of the comprehensive testing tool is improved, and the workers do not need to make adjustment decisions on the designed comprehensive testing tool according to the matching condition, which is very intelligent.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of automobile body detection, and particularly relates to a matching degree evaluation method and system for a comprehensive detection tool for automobile bodies. BACKGROUND

[0002] At present, in order to more efficiently detect automobile bodies, a comprehensive detection tool needs to be designed to simultaneously detect multiple components of an automobile body.

[0003] However, when designing the comprehensive detection tool, it is necessary to fully ensure the matching degree between the designed comprehensive detection tool and the automobile body, so that the comprehensive detection tool can be qualified to detect the automobile body.

[0004] However, the matching degree between the designed comprehensive detection tool and the automobile body is mostly determined by the staff according to experience by matching the design model or sample of the comprehensive detection tool with the automobile body, which is of great labor cost and reduces the design efficiency of the comprehensive detection tool. In addition, the staff needs to make adjustment decisions for the designed comprehensive detection tool according to the matching condition, which is insufficient in intelligentization.

[0005] Therefore, a solution is urgently needed. SUMMARY

[0006] One of the purposes of the present application is to provide a matching degree evaluation method for a comprehensive detection tool for automobile bodies. Based on a pre-established body-detection tool matching model, the automobile body and the comprehensive detection tool are matched according to the first multi-modal data of the automobile body and the second multi-modal data of the comprehensive detection tool, a matching result is obtained, the matching degree is evaluated based on the matching result, and adjustment suggestions for the comprehensive detection tool are decided. The staff does not need to manually match the design model or sample of the comprehensive detection tool with the automobile body according to experience, which reduces the labor cost, improves the design efficiency of the comprehensive detection tool, and the staff does not need to make adjustment decisions for the designed comprehensive detection tool according to the matching condition, which is very intelligent.

[0007] The matching degree evaluation method for a comprehensive detection tool for automobile bodies provided by the present application comprises the following steps.

[0008] First multi-modal data of an automobile body and second multi-modal data of a comprehensive detection tool are obtained respectively.

[0009] Based on a pre-established body-detection tool matching model, the automobile body and the comprehensive detection tool are matched according to the first multi-modal data and the second multi-modal data, and a matching result is obtained.

[0010] Based on the matching result, the matching degree is evaluated, and adjustment suggestions for the comprehensive detection tool are decided.

[0011] The matching result, the matching degree, and the adjustment suggestions are output.

[0012] Preferably, the output matching result, matching degree and adjustment suggestion include:

[0013] Based on the matching result and the matching degree, a first visual model is generated;

[0014] The first visual model is displayed to the user;

[0015] Model record information generated by the user based on the first visual model within a first time period is obtained; the starting time of the first time period is the time when the user starts to view the first visual model, and the ending time is the time when the user first generates a standard model viewing behavior;

[0016] Feature extraction is performed on the model record information to obtain information features;

[0017] Based on a feature division rule, the information features are divided into a feature set;

[0018] A corresponding indication strategy of the feature set is determined from an indication strategy library; the indication strategy includes setting area search rules and target suggestion search rules;

[0019] Based on the setting area search rules, a setting area is searched from the first visual model;

[0020] Based on the target suggestion search rules, a target suggestion is searched from the adjustment suggestion;

[0021] The target suggestion is continuously set in the setting area within a second time period; the length of the second time period is a preset length value, and the second time period is adjacent to the first time period.

[0022] Preferably, the feature division rule includes:

[0023] When a first target feature in the information features matches the trigger feature, a second target feature that is generated after the first target feature and meets the feature demand conditions corresponding to the trigger feature is determined from the information features;

[0024] The first target feature and the second target feature are combined into the feature set;

[0025] And / or,

[0026] The standard feature type set is called;

[0027] A third target feature in the information features is combined into the feature set, so that the feature type set composed of the feature types of the third target feature in the feature set matches the standard feature type set;

[0028] And / or,

[0029] The fourth target feature in the information feature is combined into a feature set, so that the fourth target feature in the feature set is the same or has a representation type correlation in the corresponding representation type in the representation type library.

[0030] Preferably, after the target suggestion is continuously set in the setting area in the second period, it further comprises:

[0031] When the user adopts the target suggestion, a second visualization model is generated based on the second multi-modal data;

[0032] Based on the target suggestion, the adjustment area search rule and the adjustment rule are determined;

[0033] Based on the adjustment area search rule, an adjustment area is searched from the second visualization model;

[0034] The setting area and the adjustment area are displayed to the user in cooperation;

[0035] The adjustment flow sequence of the adjustment rule is parsed;

[0036] According to the sequence order of the adjustment flow in the adjustment flow sequence, the adjustment flow is executed in the adjustment area in turn;

[0037] When the executed adjustment flow meets the standard flow condition and / or the user requests to modify the executed adjustment flow, a flow modification interface of the executed adjustment flow is generated;

[0038] The flow modification interface is displayed to the user;

[0039] The modification instruction input by the user based on the flow modification interface is obtained;

[0040] Based on the modification instruction, the executed adjustment flow is modified;

[0041] The modified executed adjustment flow is executed on the adjustment area.

[0042] Preferably, the standard flow condition comprises:

[0043] The flow weight of the executed adjustment flow is greater than or equal to a first weight threshold;

[0044] And / or,

[0045] The flow weight of the historically executed adjustment flow is greater than or equal to a weight sum threshold;

[0046] And / or,

[0047] The flow weight of the next adjustment flow of the executed adjustment flow in the adjustment flow sequence is greater than or equal to a second weight threshold; the second weight threshold is greater than the first weight threshold.

[0048] The embodiment of the present application provides a matching degree evaluation system of a vehicle body comprehensive testing fixture, which comprises:

[0049] An acquisition module is configured to acquire first multi-modal data of a vehicle body and second multi-modal data of a comprehensive testing fixture respectively.

[0050] A matching module is configured to match the vehicle body and the comprehensive testing fixture based on a pre-established vehicle body-testing fixture matching model according to the first multi-modal data and the second multi-modal data, and obtain a matching result.

[0051] An evaluation module is configured to evaluate the matching degree based on the matching result, and make an adjustment suggestion for the comprehensive testing fixture.

[0052] An output module is configured to output the matching result, the matching degree and the adjustment suggestion.

[0053] Preferably, the output module outputs the matching result, the matching degree and the adjustment suggestion, which comprises:

[0054] generating a first visual model based on the matching result and the matching degree;

[0055] displaying the first visual model to a user;

[0056] acquiring model record information generated by the user based on the first visual model within a first period; wherein a starting time of the first period is a time when the user starts to view the first visual model, and an ending time of the first period is a time when the user first generates a standard model viewing behavior;

[0057] extracting features from the model record information to obtain information features;

[0058] dividing the information features into a feature set based on a feature division rule;

[0059] determining an indication strategy corresponding to the feature set from an indication strategy library; the indication strategy comprises a setting area search rule and a target suggestion search rule;

[0060] searching a setting area from the first visual model based on the setting area search rule;

[0061] searching a target suggestion from the adjustment suggestion based on the target suggestion search rule;

[0062] continuously setting the target suggestion in the setting area within a second period; wherein a time length of the second period is a preset time length value, and the second period is adjacent to the first period.

[0063] Preferably, the feature division rule comprises:

[0064] When the first target feature in the information features matches the trigger feature, a second target feature is determined from the information features, which is generated after the first target feature and meets the feature requirement condition corresponding to the trigger feature;

[0065] The first target feature and the second target feature are combined into a feature set;

[0066] And / or,

[0067] The standard feature type set is called;

[0068] The third target feature in the information features is combined into the feature set, so that the feature type of the third target feature in the feature set is combined into the feature type set, which matches the standard feature type set;

[0069] And / or,

[0070] The fourth target feature in the information features is combined into the feature set, so that the fourth target feature in the feature set has the same representation type or has a representation type association relationship in the representation type library.

[0071] Preferably, the output module further comprises:

[0072] The interaction module is configured to:

[0073] When the user adopts the target suggestion, a second visualization model is generated based on the second multi-modal data;

[0074] Based on the target suggestion, the search rule of the adjustment area and the adjustment rule are determined;

[0075] Based on the search rule of the adjustment area, the adjustment area is searched from the second visualization model;

[0076] The setting area and the adjustment area are displayed to the user;

[0077] The adjustment sequence of the adjustment rule is analyzed;

[0078] According to the sequence order of the adjustment sequence in the adjustment sequence, the adjustment sequence is executed in the adjustment area in turn;

[0079] Each time the adjustment sequence is executed, when the executed adjustment sequence meets the standard sequence condition and / or the user requests to modify the executed adjustment sequence, a sequence modification interface of the executed adjustment sequence is generated;

[0080] The sequence modification interface is displayed to the user;

[0081] The modification instruction input by the user based on the sequence modification interface is obtained;

[0082] Based on the modification instruction, the executed adjustment process is modified;

[0083] The relay executes the modified executed adjustment process on the adjustment region.

[0084] Preferably, the standard process condition comprises:

[0085] The process weight of the executed adjustment process is greater than or equal to a first weight threshold value;

[0086] And / or,

[0087] The process weight of the historically executed adjustment process is greater than or equal to a weight sum threshold value;

[0088] And / or,

[0089] The process weight of the next adjustment process of the executed adjustment process in the adjustment process sequence is greater than or equal to a second weight threshold value; the second weight threshold value is greater than the first weight threshold value.

[0090] Other features and advantages of the present application will be set forth in the following description, and in part will become apparent to those skilled in the art upon examination of the following or can be learned by practice of the application. The objects and other advantages of the application can be realized and attained by the structure particularly pointed out in the written description and claims hereof as well as the appended drawings.

[0091] The technical solutions of the present application will be further described in detail below with the help of the accompanying drawings and examples. BRIEF DESCRIPTION OF DRAWINGS

[0092] The accompanying drawings are included to provide a further understanding of the present application and are incorporated in and constitute a part of this specification, illustrate embodiments of the present application and serve to explain the present application, and do not constitute a limitation of the present application. In the drawings:

[0093] Figure 1 It is a schematic diagram of a vehicle body comprehensive gauge matching degree evaluation method in an embodiment of the present application;

[0094] Figure 2 It is a schematic diagram of a vehicle body comprehensive gauge matching degree evaluation system in an embodiment of the present application. DETAILED DESCRIPTION

[0095] The preferred embodiments of the present application will be described below with reference to the accompanying drawings. It should be understood that the preferred embodiments described herein are only used to illustrate and explain the present application, and do not limit the present application.

[0096] The embodiment of the present application provides a vehicle body comprehensive gauge matching degree evaluation method, as shown in Figure 1 The method comprises the following steps:

[0097] S1, respectively acquire first multi-modal data of the automobile body and second multi-modal data of the comprehensive gauge;

[0098] S2, based on a pre-established body-gauge matching model, according to the first multi-modal data and the second multi-modal data, match the automobile body and the comprehensive gauge to obtain a matching result;

[0099] S3, based on the matching result, evaluate the matching degree and make adjustment suggestions for the comprehensive gauge;

[0100] S4, output the matching result, the matching degree and the adjustment suggestions.

[0101] The first multi-modal data includes size data, 3D scanning model, etc. of the automobile body; the second multi-modal data includes design specifications, size data, 3D scanning model, etc. of the comprehensive gauge; the pre-established body-gauge matching model can match the automobile body and the comprehensive gauge according to the first multi-modal data and the second multi-modal data to obtain a matching result; the body-gauge matching model can be matching rules of the automobile body and the comprehensive gauge, analysis standards of matching conditions, etc. set by technicians, for example, installing the 3D scanning model of the comprehensive gauge on the 3D scanning model of the automobile body and analyzing the fit degree, etc.; based on the matching result, the matching degree is evaluated and adjustment suggestions for the comprehensive gauge are made; when evaluating the matching degree, the matching degree evaluation standard set by technicians can be used, for example, when the fit degree is 100%, the output matching degree is 100%; when making adjustment suggestions, the deficiencies of the comprehensive gauge can be determined to provide adjustment suggestions according to the deficiencies; finally, the matching result, the matching degree and the adjustment suggestions are output.

[0102] Based on the pre-established body-gauge matching model, the automobile body and the comprehensive gauge are matched according to the first multi-modal data of the automobile body and the second multi-modal data of the comprehensive gauge to obtain a matching result; based on the matching result, the matching degree is evaluated and adjustment suggestions for the comprehensive gauge are made; without manual matching of the design model or sample of the comprehensive gauge and the automobile body by the staff according to experience, the labor cost is reduced, the design efficiency of the comprehensive gauge is improved, and the staff does not need to make adjustment decisions for the designed comprehensive gauge according to the matching conditions, which is very intelligent.

[0103] In one embodiment, the output matching result, matching degree and adjustment suggestions include:

[0104] Based on the matching result and the matching degree, a first visual model is generated;

[0105] display the first visual model to the user; the user can intuitively and comprehensively view the matching result and the matching degree by viewing the first visual model; when the first visual model is generated, a three-dimensional model of a part of the matching result that matches (a part of the comprehensive gauge that fits the automobile body, etc.) and a part of the matching result that does not match (a part of the comprehensive gauge that does not fit the automobile body, etc.) can be generated and used as the first visual model;

[0106] obtain model record information generated by the user based on the first visual model within a first time period; a starting time of the first time period is a time when the user starts to view the first visual model, and an ending time of the first time period is a time when the user first generates a standard model viewing behavior; the user can be a design manager of the comprehensive gauge or the like; the model record information can be viewing content viewed by the user in sequence, model operation generated when the user views the first visual model, etc.; when the user generates the standard model viewing behavior, it means that the user needs assistance for adjustment suggestions, for example: the standard model viewing behavior is that the user continuously views a part of the comprehensive gauge that does not fit the automobile body for more than 3 minutes, which means that the user is thinking about how to adjust the part of the comprehensive gauge and needs assistance for adjustment suggestions;

[0107] extract features from the model record information to obtain information features; the information features are features of the model record information, such as content types viewed in sequence, etc.;

[0108] divide the information features into a feature set based on a feature division rule;

[0109] determine an indication strategy corresponding to the feature set from an indication strategy library; the indication strategy includes setting a region search rule and a target suggestion search rule; one feature set represents one situation in which the user needs assistance for adjustment suggestions, and the indication strategy library has indication strategies corresponding to different feature sets; the indication strategy is a strategy for indicating how the system uses adjustment suggestions to assist in the future in this situation; the setting region search rule is a rule for searching a region set for a target suggestion, and the target suggestion search rule is a rule for searching a target suggestion in the adjustment suggestions that has value for user assistance, for example: the information feature in the feature set is a part of the automobile tail that does not match the comprehensive gauge, and the corresponding setting region is the tail part in the first visual model, and the target suggestion is a suggestion for adjusting the comprehensive gauge related to the tail part;

[0110] search the setting region from the first visual model based on the setting region search rule;

[0111] search the target suggestion from the adjustment suggestions based on the target suggestion search rule;

[0112] The target suggestion is continuously set in the setting area for a second period; a length of the second period is a preset length value, and the second period is adjacent to the first period. The preset length value can be 3 minutes.

[0113] The first visualization model is introduced when the matching result, the matching degree and the adjustment suggestion are output, the model record information is acquired, the indication strategy is determined based on the model record information, and the user is assisted based on the indication strategy, which greatly improves the humanization and is more intelligent. The user can quickly adjust the comprehensive gauge combined with the system output.

[0114] In one embodiment, the feature division rule includes:

[0115] When the first target feature that matches the trigger feature is present in the information feature, the second target feature that meets the feature requirement condition corresponding to the trigger feature is determined from the information feature and is generated after the first target feature; the first target feature that matches the trigger feature and the second target feature filtered out by the feature requirement condition can constitute a feature set, representing a situation in which the user needs to obtain adjustment suggestion assistance, for example: the trigger feature is to check the part of the car right rearview mirror on the car body that has a low fit with the comprehensive gauge, and the feature requirement condition is to filter out the feature of checking the part of the car left rearview mirror on the car body that has a low fit with the comprehensive gauge. In this way, the first target feature and the second target feature reflect a situation in which the user wants to obtain adjustment assistance for adjusting the parts of the left and right rearview mirrors on the comprehensive gauge.

[0116] The first target feature and the second target feature are combined into a feature set;

[0117] And / or,

[0118] The standard feature type set is called;

[0119] The third target feature in the information feature is combined into a feature set, so that the feature type set composed of the feature types of the third target features in the feature set matches the standard feature type set. The standard feature type set can also be set to combine the third target features in the information feature into a feature set, so that the feature type set composed of the feature types of the third target features in the feature set matches the standard feature type set. The third target features representing each feature type in the feature type set can collectively represent a situation in which the user needs to obtain adjustment assistance. For example, the feature types in the standard feature type set are to check the part of the car headlamp on the car body that does not fit the comprehensive gauge, to check the internal structure of the car headlamp, etc., which indicates that the user needs adjustment assistance for the part of the comprehensive gauge corresponding to the car headlamp.

[0120] And / or,

[0121] The fourth target feature in the information feature is combined into a feature set, so that the fourth target feature in the feature set is the same or has a representation type correlation in the corresponding representation type in the representation type library. The representation type corresponding to different fourth target features in the representation type library is an assistance type representing the assistance that the user hopes to obtain; when the representation types of different fourth target features have a representation type correlation, the different fourth target features can jointly represent a situation in which the user needs to obtain adjustment assistance; when the representation types of different fourth target features are the same, the different fourth target features can also jointly represent a situation in which the user needs to obtain adjustment assistance; for example: the representation types of the fourth target features in the feature set are all representation types representing the need to obtain adjustment assistance for the part of the automobile body corresponding to the comprehensive detector.

[0122] There are many information features in the model record information, and it is relatively complex to directly determine the situation in which the user needs to obtain adjustment assistance based on all the information features, and the efficiency is also relatively low. The embodiment of the present application can solve this problem; a plurality of feature division rules are introduced to divide the information features to form a feature set, so that each feature set represents a situation in which the user needs to obtain adjustment assistance, greatly improving the working efficiency of the system.

[0123] In one embodiment, after the target suggestion is continuously set in the setting area for the second time period, the method further comprises:

[0124] When the user adopts the target suggestion, a second visual model is generated based on the second multi-modal data; the second visual model can be a three-dimensional model of the comprehensive detector;

[0125] Based on the target suggestion, an adjustment area search rule and an adjustment rule are determined; the target suggestion indicates the area of the comprehensive detector that needs to be adjusted, so the adjustment area search rule can be determined, and indicates how to adjust, so the adjustment rule can be determined;

[0126] Based on the adjustment area search rule, an adjustment area is searched from the second visual model;

[0127] The setting area and the adjustment area are cooperatively displayed to the user;

[0128] The adjustment sequence of the adjustment rule is analyzed; the adjustment sequence has a plurality of adjustment processes when the adjustment rule is executed;

[0129] According to the sequence order of the adjustment processes in the adjustment sequence, the adjustment processes are executed on the adjustment area in sequence;

[0130] Each time the adjustment process is executed, when the executed adjustment process meets the standard process condition and / or the user requests to modify the executed adjustment process, a process modification interface of the executed adjustment process is generated.

[0131] displaying a process modification interface to the user; the process modification interface has multiple options for modifying the execution process, and modification instructions can be input based on the option selection;

[0132] obtaining the modification instructions input by the user based on the process modification interface;

[0133] modifying the execution adjustment process based on the modification instructions;

[0134] continuously executing the modified execution adjustment process on the adjustment area.

[0135] In one embodiment, the standard process condition includes:

[0136] the process weight of the execution adjustment process is greater than or equal to a first weight threshold;

[0137] and / or,

[0138] the process weight sum of the historical execution adjustment processes is greater than or equal to a weight sum threshold;

[0139] and / or,

[0140] the process weight of the next adjustment process in the adjustment process sequence is greater than or equal to a second weight threshold; the second weight threshold is greater than the first weight threshold.

[0141] When the execution adjustment process meets the standard process condition, it indicates that the user needs to be assisted to modify the execution adjustment process; in the standard process condition, the greater the adjustment weight of the adjustment process, the greater the degree of change to the comprehensive fixture after executing the adjustment process; the first weight threshold can be 8; the second weight threshold can be 12; the weight sum threshold can be 35; when the process weight of the execution adjustment process is greater than or equal to the first weight threshold, the degree of change is relatively large, and the user may need to adjust the process; when the process weight sum of the historical execution adjustment processes is greater than or equal to the weight sum threshold, it indicates that the overall degree of change in history is relatively large, and the user may need to adjust the process; when the process weight of the next adjustment process in the adjustment process sequence is greater than or equal to the second weight threshold, it indicates that the degree of change is relatively large when the next adjustment process is executed, and when the previous execution adjustment process is executed, the process execution needs to be reasonable, and the user may need to adjust the process. Setting multiple standard process conditions fully guarantees the accuracy and rationality of the timing of assisting the user to modify the process, and is more humanized.

[0142] The embodiment of the application provides a vehicle body comprehensive fixture matching degree evaluation system, as shown in Figure 2 , comprising:

[0143] An acquisition module 1 is configured to acquire first multi-modal data of a vehicle body and second multi-modal data of a comprehensive gauge respectively;

[0144] A matching module 2 is configured to match the vehicle body and the comprehensive gauge based on a pre-established vehicle body-gauge matching model according to the first multi-modal data and the second multi-modal data, and obtain a matching result;

[0145] An evaluation module 3 is configured to evaluate a matching degree based on the matching result, and make an adjustment suggestion for the comprehensive gauge;

[0146] An output module 4 is configured to output the matching result, the matching degree and the adjustment suggestion.

[0147] The output module outputs the matching result, the matching degree and the adjustment suggestion, including:

[0148] generating a first visualization model based on the matching result and the matching degree;

[0149] displaying the first visualization model to a user;

[0150] acquiring model record information generated by the user based on the first visualization model within a first time period; a starting time of the first time period is a time when the user starts to view the first visualization model, and an ending time of the first time period is a time when the user first generates a standard model viewing behavior;

[0151] performing feature extraction on the model record information to obtain information features;

[0152] dividing the information features into a feature set based on a feature division rule;

[0153] determining an indication strategy corresponding to the feature set from an indication strategy library; the indication strategy includes setting a region search rule and a target suggestion search rule;

[0154] searching for a setting region from the first visualization model based on the setting region search rule;

[0155] searching for a target suggestion from the adjustment suggestion based on the target suggestion search rule;

[0156] continuously setting the target suggestion in the setting region within a second time period; a time length of the second time period is a preset time length value, and the second time period is adjacent to the first time period.

[0157] The feature division rule includes:

[0158] when a first target feature in the information features matches a trigger feature, determining a second target feature from the information features, the second target feature being generated after the first target feature and meeting a feature requirement condition corresponding to the trigger feature;

[0159] combining the first target feature and the second target feature into a feature set;

[0160] and / or,

[0161] calling a standard feature type set;

[0162] combining a third target feature in the information feature into the feature set, so that the feature type of the third target feature in the feature set is combined into a feature type set that matches the standard feature type set;

[0163] and / or,

[0164] combining a fourth target feature in the information feature into the feature set, so that the fourth target feature in the feature set is the same in the corresponding representation type in the representation type library or has a representation type association relationship.

[0165] The output module further comprises:

[0166] The interaction module is configured to:

[0167] When the user adopts the target suggestion, a second visualization model is generated based on the second multi-modal data;

[0168] Based on the target suggestion, an adjustment area search rule and an adjustment rule are determined;

[0169] Based on the adjustment area search rule, an adjustment area is searched from the second visualization model;

[0170] The setting area and the adjustment area are displayed to the user in cooperation;

[0171] The adjustment flow sequence of the adjustment rule is parsed;

[0172] According to the sequence order of the adjustment flow in the adjustment flow sequence, the adjustment flow is executed on the adjustment area in turn;

[0173] Each time the adjustment flow is executed, when the executed adjustment flow meets the standard flow condition and / or the user requests to modify the executed adjustment flow, a flow modification interface of the executed adjustment flow is generated;

[0174] The flow modification interface is displayed to the user;

[0175] The modification instruction input by the user based on the flow modification interface is obtained;

[0176] Based on the modification instruction, the executed adjustment flow is modified;

[0177] The modified executed adjustment flow is executed on the adjustment area.

[0178] The standard flow condition comprises:

[0179] the procedure weight of the adjustment procedure executed to is greater than or equal to a first weight threshold;

[0180] and / or,

[0181] the procedure weight of the adjustment procedure executed to is greater than or equal to a first weight threshold;

[0182] and / or,

[0183] the procedure weight of the adjustment procedure executed to is greater than or equal to a first weight threshold;

[0184] It will be apparent to those skilled in the art that various modifications and variations can be made to the present application without departing from the spirit or scope of the application. Thus, it is intended that the present application cover modifications and variations of this application provided they come within the scope of the appended claims and their equivalents.

Claims

1. A method for evaluating the matching degree of a vehicle body comprehensive testing fixture, characterized in that, The method comprises the following steps: Based on a pre-established vehicle body-gauge matching model, the vehicle body and the comprehensive gauge are matched according to the first multi-modal data of the vehicle body and the second multi-modal data of the comprehensive gauge, and a matching result is obtained; Based on the matching result, the matching degree is evaluated, and an adjustment suggestion of the comprehensive gauge is decided; Based on the matching result and the matching degree, a first visualization model is generated; Based on a feature division rule, the information features of the model record information generated by the user based on the first visualization model within a first time period are divided into a feature set; the starting time of the first time period is the time when the user starts to view the first visualization model, and the ending time is the time when the user first generates a standard model viewing behavior; when the user generates a standard model viewing behavior, it represents that the user needs to get adjustment assistance; One feature set represents one situation in which the user needs to get adjustment assistance; From the indication strategy library, the setting area search rule and the target suggestion search rule corresponding to the feature set are determined; Within a second time period, the target suggestion searched from the adjustment suggestion based on the target suggestion search rule is continuously set in the setting area searched from the first visualization model based on the setting area search rule; The second time period is after the first time period and adjacent to the first time period; The feature division rule comprises: When there is a first target feature in the information feature that matches the trigger feature, a second target feature that meets the feature requirement condition corresponding to the trigger feature is determined from the information feature after the first target feature; The first target feature and the second target feature are combined into a feature set; And / or, The standard feature type set is called; The third target feature in the information feature is combined into a feature set, so that the feature type set combined by the feature type of the third target feature in the feature set matches the standard feature type set; And / or, The fourth target feature in the information feature is combined into a feature set, so that the corresponding representation type of the fourth target feature in the feature set is the same or has a representation type association relationship in the representation type library.

2. The method of claim 1, wherein the matching degree of the vehicle body comprehensive testing fixture is evaluated based on the matching degree of the vehicle body comprehensive testing fixture and the vehicle body comprehensive testing fixture. After continuously setting the target suggestion in the setting area within the second time period, the method further comprises the following steps: When the user adopts the target suggestion, a second visualization model is generated based on the second multi-modal data; Based on the target suggestion, the adjustment area search rule and the adjustment rule are determined; Based on the adjustment area search rule, the adjustment area is searched from the second visualization model; The setting area and the adjustment area are displayed to the user in cooperation; The adjustment flow sequence of the adjustment rule is analyzed; According to the sequence order of the adjustment flow in the adjustment flow sequence, the adjustment flow executed is executed on the adjustment area in turn; Each time the adjustment flow executed is executed, when the adjustment flow executed meets the standard flow condition and / or the user requests to modify the adjustment flow executed, a flow modification interface of the adjustment flow executed is generated; The flow modification interface is displayed to the user; The modification instruction input by the user based on the flow modification interface is obtained; Based on the modification instruction, the adjustment flow executed is modified; The modified adjustment flow executed is executed on the adjustment area.

3. The method of claim 2, wherein the matching degree of the vehicle body comprehensive testing fixture is evaluated based on the matching degree of the vehicle body comprehensive testing fixture and the vehicle body comprehensive testing fixture. The standard flow condition comprises: The flow weight of the adjustment flow executed is greater than or equal to a first weight threshold; And / or, A process weight of an adjustment process that has been executed historically and is greater than or equal to a weight and threshold value; And / or, A process weight of a next adjustment process in the adjustment process sequence that has been executed is greater than or equal to a second weight threshold value; the second weight threshold value is greater than the first weight threshold value.

4. A vehicle body comprehensive gauge matching degree evaluation system characterized by comprising: Comprise: A matching module, configured to match the automobile body and the comprehensive gauge based on first multi-modal data of the automobile body and second multi-modal data of the comprehensive gauge according to a pre-established automobile body-gauge matching model, and obtain a matching result; An evaluation module, configured to evaluate a matching degree based on the matching result, and make an adjustment suggestion for the comprehensive gauge; An output module, configured to generate a first visualization model based on the matching result and the matching degree; Divide information features of model record information generated by the user based on the first visualization model within a first time period into a feature set according to a feature division rule; a starting time of the first time period is a time when the user starts to view the first visualization model, and an ending time of the first time period is a time when the user first generates a standard model viewing behavior; when the user generates the standard model viewing behavior, it represents that the user needs assistance for adjustment suggestions; One feature set represents one situation in which the user needs assistance for adjustment suggestions; Determine a setting area search rule and a target suggestion search rule corresponding to the feature set from an instruction strategy library; Continuously set a target suggestion searched from the adjustment suggestions based on the target suggestion search rule in a setting area searched from the first visualization model based on the setting area search rule within a second time period; The second time period is after the first time period and adjacent to the first time period; The feature division rule comprises: When there is a first target feature in the information features that matches the trigger feature, determine a second target feature from the information features that is generated after the first target feature and meets a feature demand condition corresponding to the trigger feature; Combine the first target feature and the second target feature into the feature set; And / or, Call a standard feature type set; Combine a third target feature in the information features into the feature set, so that feature types of the third target feature in the feature set combine into a feature type set that matches the standard feature type set; And / or, Combine a fourth target feature in the information features into the feature set, so that the fourth target feature in the feature set has a same representation type or an associated relationship in a representation type library.

5. The vehicle body-in-white matching degree evaluation system according to claim 4, wherein After the output module continuously sets the target suggestion in the setting area within the second time period, the output module further comprises: An interaction module, configured to: When the user adopts the target suggestion, generate a second visualization model based on the second multi-modal data; Determine an adjustment area search rule and an adjustment rule based on the target suggestion; Search an adjustment area from the second visualization model based on the adjustment area search rule; Co-display the setting area and the adjustment area to the user; Analyze an adjustment process sequence of the adjustment rule; Execute the adjustment processes on the adjustment area in sequence according to a sequence order of the adjustment processes in the adjustment process sequence; Each time, when an executed adjustment process meets a standard process condition and / or the user requests to modify the executed adjustment process, generate a process modification interface of the executed adjustment process; Display the process modification interface to the user; Obtaining a modification instruction input by a user based on a process modification interface; Modifying the executed adjustment process based on the modification instruction; Executing the modified executed adjustment process on the adjustment region.

6. The vehicle body-in-white matching degree evaluation system according to claim 5, wherein The standard process condition includes: The process weight of the executed adjustment process is greater than or equal to a first weight threshold value; And / or, The process weight of the historically executed adjustment process is greater than or equal to a weight sum threshold value; And / or, The process weight of the next adjustment process of the executed adjustment process in the adjustment process sequence is greater than or equal to a second weight threshold value; the second weight threshold value is greater than the first weight threshold value.

Images