Intelligent cockpit interaction system evaluation method, device, electronic device and storage medium

Abstract

Embodiments of the present invention provide a method, apparatus, electronic device, and storage medium for evaluating an intelligent cockpit interaction system. The intelligent cockpit interaction system evaluation method includes: comparing a directed graph corresponding to interactive behavior data with a preset flowchart to obtain an interactive behavior path; sorting the interactive behavior paths in descending order according to their average time loss values ​​to obtain an interactive behavior path sequence; and processing the interactive behavior paths corresponding to the ends of the interactive behavior path sequence to obtain an intelligent cockpit interaction system evaluation solution. Through these steps, a system evaluation can be performed during iteration of the intelligent cockpit interaction system based on user interactive behaviors, thereby improving the user experience of the intelligent cockpit interaction process.

Description

Technical Field

[0001] Embodiments of the present invention relate to the field of interactive technology, and in particular to a method, device, electronic device, and storage medium for evaluating an intelligent cockpit interactive system. Background Art

[0002] With the rapid development of vehicle technology, users can now use applications installed on in-vehicle terminals to perform a variety of business operations, such as navigation, in-car entertainment, payment, and shopping. After an application is released, developers often update it to fix defects or optimize the current version. Improving the user experience during this update process has become a pressing issue.

[0003] Existing technology primarily evaluates smart cockpit interaction systems using A / B testing, which uses macro indicators to determine whether to retain A or B, thereby advancing software version iterations. This approach can provide macro-level insights, but struggles to grasp the micro-level user experience and behavioral paths.

[0004] At the micro level, the commonly used method in the industry is to display the behavioral path in the form of a Sange diagram. The Sange diagram can show the user's experience path statistics, but it cannot merge the same behavior and can only be displayed in layers. Operational behaviors can be repeated between layers, which makes the behavioral network dimension too large and can only be observed, making data mining difficult. Since it is impossible to match and compare individual branches or compare with the initial evaluation plan, the existing technology cannot effectively evaluate the intelligent cockpit interaction system during software iteration. Summary of the Invention

[0005] In view of this, embodiments of the present invention provide a method, device, electronic device, and storage medium for evaluating an intelligent cockpit interaction system to at least partially solve the above-mentioned problems.

[0006] According to a first aspect of an embodiment of the present invention, a method for evaluating an intelligent cockpit interaction system is provided, comprising: comparing a directed graph corresponding to interaction behavior data with a preset flowchart to obtain an interaction behavior path; sorting the interaction behavior paths in descending order according to the average time loss value to obtain an interaction behavior path sequence; and processing the interaction behavior path corresponding to the end of the interaction behavior path sequence to obtain an intelligent cockpit interaction system evaluation scheme.

[0007] In another implementation of the present invention, the interactive behavior paths are sorted in descending order according to the average time loss value, including: selecting a preset behavior path according to a preset flowchart; performing loss calculation on the interactive behavior path according to the preset behavior path to obtain the average time loss value corresponding to the interactive behavior path; and sorting the average time loss values ​​corresponding to the interactive behavior paths in descending order.

[0008] In another implementation of the present invention, the loss calculation is performed on the interactive behavior path according to the preset behavior path to obtain the average time loss value corresponding to the interactive behavior path, including: determining the behavior node according to the preset behavior path; determining the number of behavior occurrences of adjacent behavior nodes corresponding to the interactive behavior path and the time interval corresponding to adjacent behavior nodes; performing loss calculation according to the total number of events, occurrence probability, number of behavior occurrences and time interval corresponding to the interactive behavior path to obtain the average time loss value corresponding to the interactive behavior path.

[0009] In another implementation of the present invention, the intelligent cockpit interaction system evaluation method further includes: classifying the interactive behavior paths to obtain a first path set and a second path set; calculating the expected loss values ​​of the first path set and the second path set based on the average time loss value and occurrence probability corresponding to the interactive behavior paths in the first path set and the second path set respectively; comparing the expected loss values ​​of the first path set and the second path set, selecting the path set with a lower expected loss value, and obtaining an intelligent cockpit interaction system evaluation plan based on the path set with a lower expected loss value.

[0010] In another implementation of the present invention, the intelligent cockpit interaction system evaluation method further includes: classifying the interactive behavior paths corresponding to the preset flowchart to obtain a third path set; calculating the average time loss value and occurrence probability corresponding to the interactive behavior paths in the third path set to obtain the loss expected value of the third path set; comparing the loss expected values ​​of the first path set, the second path set and the third set, selecting the path set with a lower loss expected value, and obtaining the intelligent cockpit interaction system evaluation plan based on the path set with a lower loss expected value.

[0011] In another implementation of the present invention, the smart cockpit interaction system evaluation method further includes: acquiring interaction behavior data; performing process mining on the acquired interaction behavior data to obtain a directed graph corresponding to the interaction behavior data.

[0012] In another implementation of the present invention, the process mining processing of the acquired interactive behavior data to obtain a directed graph corresponding to the interactive behavior data includes: formatting the interactive behavior data to obtain formatted interactive behavior data; and data processing the formatted interactive behavior data according to a process mining algorithm to obtain a directed graph corresponding to the interactive behavior data.

[0013] According to a second aspect of an embodiment of the present invention, a smart cockpit interaction system evaluation device is provided, including: a comparison module, used to compare a directed graph corresponding to interactive behavior data with a preset flowchart to obtain an interactive behavior path; a sorting module, used to sort the interactive behavior paths in descending order according to the average time loss value to obtain an interactive behavior path sequence; and a processing module, used to process the interactive behavior path corresponding to the end of the interactive behavior path sequence to obtain an intelligent cockpit interaction system evaluation plan.

[0014] According to a third aspect of an embodiment of the present invention, an electronic device is provided, comprising: a processor, a memory, a communication interface and a communication bus, wherein the processor, the memory and the communication interface communicate with each other via the communication bus; the memory is used to store at least one executable instruction, and the executable instruction enables the processor to perform an operation corresponding to the method described in the first aspect.

[0015] According to a fourth aspect of an embodiment of the present invention, a computer storage medium is provided, on which a computer program is stored. When the program is executed by a processor, the method according to the first aspect is implemented.

[0016] In this embodiment of the present invention, the directed graph corresponding to the interaction behavior data is first compared with a preset flow chart to obtain the interaction behavior path. These interaction behavior paths are then sorted in descending order by average time loss to obtain an interaction behavior path sequence. Finally, the interaction behavior path corresponding to the end of the interaction behavior path sequence is processed to obtain an intelligent cockpit interaction system evaluation scheme. These steps enable systematic evaluation of user interaction behaviors within the intelligent cockpit interaction system iteration, improving the user experience during intelligent cockpit interaction. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments recorded in the embodiments of the present invention. For ordinary technicians in this field, other drawings can also be obtained based on these drawings.

[0018] Figure 1 The following is a schematic block diagram of an example user experience system.

[0019] Figure 2 The figure is a flowchart of the steps of a method for evaluating an intelligent cockpit interaction system according to an embodiment of the present invention.

[0020] Figure 3 The figure is a schematic block diagram of an intelligent cockpit interaction system evaluation device according to an embodiment of the present invention.

[0021] Figure 4 FIG. 1 is a schematic structural diagram of an electronic device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0022] In order to enable those skilled in the art to better understand the technical solutions in the embodiments of the present invention, the technical solutions in the embodiments of the present invention will be clearly and detailedly described below in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of them. All other embodiments obtained by those skilled in the art based on the embodiments in the embodiments of the present invention should fall within the scope of protection of the embodiments of the present invention.

[0023] It should be understood that the terms "first," "second," and "third," etc. in the claims, specification, and drawings of this disclosure are used to distinguish different objects rather than to describe a specific order. The terms "include" and "comprising" used in the specification and claims of this disclosure indicate the presence of the described features, integers, steps, operations, elements, and / or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and / or combinations thereof.

[0024] It should also be understood that the terminology used in this disclosure is for the purpose of describing specific embodiments only and is not intended to limit the disclosure. As used in this disclosure and the claims, the singular forms "a," "an," and "the" are intended to include the plural forms unless the context clearly indicates otherwise. It should be further understood that the term "and / or" as used in this disclosure and the claims refers to any and all possible combinations of one or more of the associated listed items, including and including these combinations.

[0025] Figure 1The following is a schematic block diagram of an example user experience system. The user experience system of this example includes: a dimension extractor construction module 101, which is used to construct a dimension extractor according to the preset test requirements of the access party system; an AB test scheme configuration module 102, which is used to configure an AB test scheme according to the preset test requirements of the access party system, and then return the unique identification information of the AB test scheme to the access party system, wherein configuring the AB test scheme includes: configuring one or more sub-test schemes according to the preset test requirements of the access party system, selecting a corresponding dimension extractor for each sub-test scheme, and setting a corresponding dimension matching value; an AB test scheme matching module 103, which is used to, after receiving a service request from the access party system, obtain a corresponding AB test scheme based on the unique identification information of the AB test scheme contained in the service request, determine whether the service request complies with the sub-test scheme of the AB test scheme, and output the judgment result.

[0026] The user experience system in this example performs user experience evaluation during software iteration, achieving relatively good results. However, because the user experience system analysis primarily relies on A / B testing, it uses identification information to determine whether to retain solution A or B, thereby selecting solution for software version iteration. This system can make solution selections at a macro level, but it struggles to grasp the user's experience behavior path. For example, during software iteration A / B testing, selecting solution A based solely on identification information cannot directly discover and quantify the specific differences between the two solutions, nor can it compare individual branches.

[0027] Figure 2 An exemplary process of an intelligent cockpit interactive system evaluation method according to an embodiment of the present invention is shown. The embodiment of the present application is applied to the field of interactive technology and is applicable to vehicles with interactive behavior functions. The interactive behavior function refers to the evaluation and analysis of user experience through interactive behavior. This embodiment can be used in the fields of intelligent cockpits, vehicle software, robots, assembly line software, etc., wherein the intelligent cockpit refers to a vehicle cockpit with a digital platform. The traditional vehicle cockpit is only used to indicate various driving working conditions, while the intelligent cockpit has interactive behavior functions such as touch or voice chat. The algorithm involved in the intelligent cockpit interactive system evaluation method of this embodiment is a process mining algorithm.

[0028] The intelligent cockpit interaction system evaluation method of this embodiment includes:

[0029] S210: Compare the directed graph corresponding to the interactive behavior data with the preset flow chart to obtain an interactive behavior path.

[0030] It should be understood that the interaction behavior data herein refers to the recorded data of a user's touch behavior when using the smart cockpit interactive interface. The recorded data includes, but is not limited to, user ID, touched buttons or areas, and touch timestamps. A directed graph herein refers to a directional graph consisting of a set of vertices and a set of directed edges. Each directed edge connects an ordered pair of vertices. A directed edge points from the first vertex to the second vertex. In a directed graph, the out-degree of a vertex is the total number of edges pointed to by the vertex; the in-degree of a vertex is the total number of edges pointing to the vertex. The first vertex of a directed edge is called its head, and the second vertex is called its tail. Each directed edge represents an independent interaction behavior, and the two vertices of the edge represent the initiation time and termination time of the independent interaction behavior, respectively. The preset flowchart herein refers to a flowchart set based on human experience. The interaction behavior path herein refers to the comparison between the directed graph corresponding to the interaction behavior data and the preset flowchart. The interaction behavior path of the directed graph corresponding to the interaction behavior data is different from the interaction behavior path of the preset flowchart. If there is a missing interaction behavior path between the interaction behavior path and the interaction behavior path of the preset flowchart, the interaction behavior path is supplemented according to the interaction behavior path of the preset flowchart.

[0031] By comparing the directed graph corresponding to the interactive behavior data with the preset flowchart, the interactive behavior path is obtained. The differences in the interactive behaviors of the same terminal can be directly compared and observed, thereby improving the accuracy of the intelligent cockpit interaction system evaluation.

[0032] S220: Sort the interactive behavior paths in descending order according to the average time loss value to obtain an interactive behavior path sequence.

[0033] It should be understood that the average time loss value here refers to the statistical value of the time loss corresponding to each interactive behavior path. The smaller the average time loss value, the shorter the corresponding interactive behavior path. The interactive behavior path sequence here refers to the ordering of the corresponding interactive behavior paths from large to small according to the average time loss value. It should be noted that it is also possible to only calculate the average time loss value for the interactive behavior paths here without performing the sorting process.

[0034] Specifically, the interaction paths can be annotated, and repeated behaviors at the end can be screened and annotated. The time spent on all interaction paths is then statistically calculated. The time spent and frequency of interaction paths in the pre-set flow chart (directed graphs with no return from the end) are also calculated. Ultimately, the interaction path with the lowest average time loss is the optimal path, allowing for the discovery of commonly used functions.

[0035] By sorting the interactive behavior paths in descending order according to the average time loss value, an interactive behavior path sequence is obtained. The interactive behavior paths can be compared and sorted according to the average time loss value, and the quality of the interactive behavior paths can be quantitatively counted.

[0036] S230: According to the interactive behavior path corresponding to the end of the interactive behavior path sequence, an intelligent cockpit interaction system evaluation scheme is obtained.

[0037] It should be understood that the term "end" of the interaction behavior path sequence here refers to the interaction behavior path corresponding to the last position in the interaction behavior path sequence, arranged in descending order. The smart cockpit interaction system evaluation solution here refers to the smart cockpit interaction solution evaluated based on the interaction behavior path with the smallest average time loss value. It should be noted that, since step S220 only calculates the average time loss value for the interaction behavior paths without performing any sorting, this step can directly process the interaction behavior path with the smallest average time loss value to obtain the smart cockpit interaction system evaluation solution.

[0038] By processing the interaction behavior path corresponding to the end of the interaction behavior path sequence, an evaluation plan for the intelligent cockpit interaction system is obtained. All interaction behaviors can be accurately screened, and the behavior path with the lowest time loss can be selected as the interaction system evaluation plan to improve the user experience.

[0039] In this embodiment of the present invention, the directed graph corresponding to the interaction behavior data is first compared with a pre-set flow chart to obtain the interaction behavior path. The interaction behavior paths are then sorted in descending order by average time loss to obtain an interaction behavior path sequence. Finally, the interaction behavior path corresponding to the end of the interaction behavior path sequence is processed to obtain an intelligent cockpit interaction system evaluation scheme. These steps enable systematic evaluation of user interaction behaviors within the intelligent cockpit interaction system iteration, improving the user experience during intelligent cockpit interaction.

[0040] In one possible implementation, the interactive behavior paths are sorted in descending order according to their average time loss values, including: selecting a preset behavior path according to a preset flowchart; performing loss calculation on the interactive behavior path according to the preset behavior path to obtain the average time loss value corresponding to the interactive behavior path; and sorting the average time loss values ​​corresponding to the interactive behavior paths in descending order.

[0041] It should be understood that the preset behavior path here refers to the behavior path with the lowest time loss in the preset flow chart, selected based on manual experience. Calculating the loss of the interactive behavior path based on the preset behavior path here refers to using the preset behavior path as a reference and calculating the loss of the interactive behavior paths that include or partially include the preset behavior path.

[0042] By selecting a preset behavior path according to a preset flow chart and then calculating the loss of the interactive behavior path based on the preset behavior path, multiple interactive behavior paths can be compared with the preset behavior path as a reference to improve the accuracy of user experience evaluation.

[0043] In one possible implementation, a loss calculation is performed on the interactive behavior path according to a preset behavior path to obtain an average time loss value corresponding to the interactive behavior path, including: determining a behavior node according to the preset behavior path; determining the number of behavior occurrences of adjacent behavior nodes corresponding to the interactive behavior path and the time interval corresponding to the adjacent behavior nodes; performing a loss calculation based on the total number of events, occurrence probability, number of behavior occurrences and time interval corresponding to the interactive behavior path to obtain the average time loss value corresponding to the interactive behavior path.

[0044] It should be understood that the behavior node here refers to the expansion of the preset behavior path according to a directed graph or flowchart, and each directed edge represents each independent interactive behavior in the preset behavior path. The two vertices of the edge are behavior nodes, which are used to represent the initiation time and termination time of the independent interactive behavior respectively. The adjacent nodes here refer to the two adjacent vertices in the interactive behavior path expanded according to the directed graph or flowchart. The number of behavior occurrences here refers to the number of occurrences of interactive behaviors between two adjacent vertices in the interactive behavior path, and the time interval here refers to the average time spent on interactive behaviors between two adjacent vertices in the interactive behavior path. The total number of events here refers to the number of times a certain interactive behavior path occurs, and the probability of occurrence here refers to the ratio of a certain interactive behavior path to all interactive behavior paths.

[0045] By calculating the loss based on the total number of events, occurrence probability, number of behavior occurrences, and time interval corresponding to the interactive behavior path, the average time loss value corresponding to the interactive behavior path can be obtained to accurately compare the time losses of different interactive behavior paths.

[0046] In one possible implementation, the intelligent cockpit interaction system evaluation method also includes: classifying the interactive behavior paths to obtain a first path set and a second path set; calculating the expected loss values ​​of the first path set and the second path set based on the average time loss values ​​and occurrence probabilities corresponding to the interactive behavior paths in the first path set and the second path set, respectively; comparing the expected loss values ​​of the first path set and the second path set, selecting the path set with a lower expected loss value, and obtaining the intelligent cockpit interaction system evaluation plan based on the path set with a lower expected loss value.

[0047] It should be understood that the first and second path sets herein refer to two classifications of all interaction paths. The classification criteria can be based on different software test versions, or other indicators, and the classification criteria are not limited here. The expected loss value of the path set herein refers to the expected loss value of all interactions in the path set as a whole.

[0048] By dividing the interactive behavior paths into two categories and calculating the expected loss values ​​of the two types of path sets respectively, the software test version represented by a certain type of path set with a lower overall expected loss value can be effectively screened out, making the evaluation of the intelligent cockpit interaction system more efficient.

[0049] In one possible implementation, the intelligent cockpit interaction system evaluation method also includes: classifying the interactive behavior paths corresponding to the preset flowchart to obtain a third path set; calculating the average time loss value and occurrence probability corresponding to the interactive behavior paths in the third path set to obtain the loss expectation value of the third path set; comparing the loss expectation values ​​of the first path set, the second path set, and the third set, selecting the path set with a lower loss expectation value, and obtaining the intelligent cockpit interaction system evaluation plan based on the path set with a lower loss expectation value.

[0050] It should be understood that the third path set herein refers to the entire set of interaction behavior paths pre-defined in the preset flow chart based on human experience. The expected loss value for the third path set is calculated in the same manner as the expected loss value for the first path set or the second path set.

[0051] Specifically, the information contained in the directed graph generated by process mining can be analyzed, and an end behavior in the interactive behavior path can be selected. The interactive behavior path here can be a single-branch interactive behavior path. The end behavior of the corresponding interactive behavior path in the preset flowchart is used as a reference; the starting node and the end node in the first path set and the second path set are expanded according to the preset behavior path, the nodes of the interactive behavior path are completed, and the nodes that do not appear are set to zero according to the frequency of occurrence; the average time loss value of the interactive behavior path is calculated, and the average time of the interactive behavior path in the first path set, the second path set and the third path set is calculated respectively. The average time is calculated as follows: the number of occurrences of adjacent behavior nodes multiplied by the average time interval between adjacent nodes, and then the sum of the time of the interactive behavior path is calculated and divided by the total number of events sent by the interactive behavior path. The average time loss value T of the interactive behavior path of the three different path sets is obtained. am 、T bm 、T cm, used to represent the average time loss value of a certain interactive behavior path in the first path set, the second path set, and the third path set; calculate the expected value of the loss of the path set, assuming that the number of interactive behavior paths in the first path set is m, and the probability of occurrence of the mth branch is P am , the average time loss value T of this interactive behavior path am , then the expected loss value of the first path set is: E A =∑ m T am P am Similarly, the expected loss values ​​of the second and third path sets are calculated using the same method as the first path set, that is, E B =∑ m T bm P bm ;E C =∑ m T cm P cm ; Compare the expected loss values ​​of three different path sets, find out the advantages and disadvantages of different path sets, decide to retain the solution represented by the superior path set, and roll back the inferior solution. And perform deviation evaluation on the solution represented by the preset flowchart. Among them, preferably, all the interactive behavior paths of the first path set and the second path set are sorted, and the solution represented by the optimal interactive behavior path is found. If the solution represented by the optimal interactive behavior path appears in the inferior solution, then record this optimal branch, and optimize the corresponding branch of this branch in the optimal solution. At the same time, the interactive behavior path corresponding to the worst average time loss value in the superior solution is optimized.

[0052] By comparing the expected loss values ​​of the first path set, the second path set, and the third path set, a path set with a lower expected loss value can be selected, and an intelligent cockpit interaction system evaluation scheme is obtained based on the path set with a lower expected loss value, thereby achieving efficient intelligent cockpit interaction system evaluation.

[0053] In one possible implementation, the intelligent cockpit interaction system evaluation method further includes: acquiring interaction behavior data; performing process mining on the acquired interaction behavior data to obtain a directed graph corresponding to the interaction behavior data.

[0054] Specifically, to obtain interactive behavior data, tracking points can be performed during software user interaction evaluation and a data transmission interface can be established. The interactive behavior data detected by tracking points can be obtained through the data transmission interface. Tracking points here refer to a data collection algorithm. Tracking points can completely record the user's touch behavior when the user uses the interactive interface. The record content includes user number, touched button or area, and touch timestamp. The obtained log data (interactive behavior data) is then transmitted from the terminal to the cloud platform in JSON format for storage. Finally, the log data is extracted and cleaned. The user number needs to be self-numbered at a fixed interval, and the fixed interval is bounded by the sleep time.

[0055] Preferably, the directed graph corresponding to the interactive behavior data can be graphically processed and output and displayed on the front end.

[0056] It should be understood that data processing here refers to data extraction and data cleaning of the interactive behavior data to remove irrelevant data in the interactive behavior data that does not participate in the directed graph calculation. The above method can improve the data processing accuracy.

[0057] In one possible implementation, process mining is performed on the acquired interaction behavior data to obtain a directed graph corresponding to the interaction behavior data, including: formatting the interaction behavior data to obtain the formatted interaction behavior data; and data processing is performed on the formatted interaction behavior data according to a process mining algorithm to obtain a directed graph corresponding to the interaction behavior data.

[0058] It should be understood that formatting here refers to processing the interaction behavior data into a data format suitable for directed graph computation. The process mining algorithm here can be an inductive algorithm within a data mining algorithm, including but not limited to inductive algorithms and heuristic algorithms. This process mining algorithm can be used to merge identical interactions, reducing the network dimensionality of the interaction behavior data and facilitating observation and data mining.

[0059] Specifically, the interaction behavior data is converted into XES format. The process mining algorithm within the PM4PY tool is then used to read and calculate the XES file data, outputting the data in the form of a Petri-net graph. The process mining algorithm effectively avoids low-frequency events. XES and PM4PY are both data mining software and tools. A Petri-net is a directed bipartite graph with two types of nodes: locations and transitions. Locations and transitions in a Petri net are represented by circles and rectangles, respectively. Directed arcs connect locations to transitions and vice versa. A location connected to a transition is called its input location.

[0060] Figure 3 FIG2 is a schematic block diagram of an intelligent cockpit interaction system evaluation device according to another embodiment of the present invention. The solution of the embodiment of the present invention can be applied to electronic devices, including but not limited to: terminal devices with communication functions or electronic devices with interactive behavior capabilities.

[0061] The intelligent cockpit interaction system evaluation device of this embodiment includes: a comparison module 310, which is used to compare the directed graph corresponding to the interactive behavior data with the preset flow chart to obtain the interactive behavior path; a sorting module 320, which is used to sort the interactive behavior paths in descending order according to the average time loss value to obtain an interactive behavior path sequence; and a processing module 330, which is used to process the interactive behavior path corresponding to the end of the interactive behavior path sequence to obtain the optimal intelligent cockpit interaction system evaluation plan.

[0062] In other examples, the sorting module 320 is specifically used to: select a preset behavior path according to a preset flowchart; calculate the loss of the interactive behavior path according to the preset behavior path to obtain the average time loss value corresponding to the interactive behavior path; and sort the average time loss values ​​corresponding to the interactive behavior path in descending order.

[0063] In other examples, the sorting module 320 is specifically used to: determine the behavior nodes according to the preset behavior path; determine the number of behavior occurrences of adjacent behavior nodes corresponding to the interactive behavior path and the time interval corresponding to the adjacent behavior nodes; perform loss calculation based on the total number of events, occurrence probability, number of behavior occurrences and time interval corresponding to the interactive behavior path to obtain the average time loss value corresponding to the interactive behavior path.

[0064] In other examples, the sorting module 320 is specifically used to: classify the interactive behavior paths to obtain a first path set and a second path set; calculate the expected loss values ​​of the first path set and the second path set based on the average time loss values ​​and occurrence probabilities corresponding to the interactive behavior paths in the first path set and the second path set, respectively; compare the expected loss values ​​of the first path set and the second path set, select the path set with a lower expected loss value, and obtain an intelligent cockpit interaction system evaluation plan based on the path set with a lower expected loss value.

[0065] In other examples, the sorting module 320 is specifically used to: classify the interactive behavior paths corresponding to the preset flowchart to obtain a third path set; calculate the average time loss value and occurrence probability corresponding to the interactive behavior paths in the third path set to obtain the expected loss value of the third path set; compare the expected loss values ​​of the first path set, the second path set and the third set, select the path set with a lower expected loss value, and obtain an intelligent cockpit interaction system evaluation plan based on the path set with a lower expected loss value.

[0066] In other examples, the comparison module 310 is specifically used to: obtain interactive behavior data; and perform process mining on the obtained interactive behavior data to obtain a directed graph corresponding to the interactive behavior data.

[0067] In other examples, the comparison module 310 is specifically used to: perform process mining on the acquired interactive behavior data to obtain a directed graph corresponding to the interactive behavior data, including: formatting the interactive behavior data to obtain formatted interactive behavior data; performing data processing on the formatted interactive behavior data according to a process mining algorithm to obtain a directed graph corresponding to the interactive behavior data.

[0068] Reference Figure 4 , shows a schematic structural diagram of an electronic device according to another embodiment of the present invention. The specific embodiment of the present invention does not limit the specific implementation of the electronic device.

[0069] like Figure 4 As shown, the electronic device may include: a processor (processor) 402 , a communication interface (Communications Interface) 404 , a memory (memory) 406 storing a program 410 , and a communication bus 408 .

[0070] The processor, communication interface, and memory communicate with each other via a communication bus. The communication interface is used to communicate with other electronic devices or servers. The processor is used to execute a program, specifically, the steps of the above-described method embodiments. Specifically, the program may include program code, which includes computer operating instructions.

[0071] The processor may be a CPU, an ASIC (Application Specific Integrated Circuit), or one or more integrated circuits configured to implement the embodiments of the present invention. The one or more processors included in the smart device may be processors of the same type, such as one or more CPUs, or processors of different types, such as one or more CPUs and one or more ASICs.

[0072] Memory is used to store programs. The memory may include high-speed RAM memory, and may also include non-volatile memory (non-volatile memory), such as at least one disk storage.

[0073] The program can be specifically used to enable the processor to perform the following operations: comparing the directed graph corresponding to the interactive behavior data with the preset flow chart to obtain the interactive behavior path; sorting the interactive behavior paths in descending order according to the average time loss value to obtain an interactive behavior path sequence; and processing the interactive behavior path corresponding to the end of the interactive behavior path sequence to obtain an intelligent cockpit interactive system evaluation plan.

[0074] The above embodiments are only used to illustrate the embodiments of the present invention, and are not intended to limit the embodiments of the present invention. Ordinary technicians in the relevant technical field can make various changes and modifications without departing from the spirit and scope of the embodiments of the present invention. Therefore, all equivalent technical solutions also fall within the scope of the embodiments of the present invention, and the scope of patent protection of the embodiments of the present invention should be defined by the claims. The systems, devices, modules or units described in the above embodiments can be implemented by computer chips or entities, or by products with certain functions.

[0075] For the convenience of description, the above device is described as being divided into various units according to their functions. Of course, when implementing the present invention, the functions of each unit can be implemented in the same or multiple software and / or hardware.

[0076] It will be understood by those skilled in the art that embodiments of the present invention may be provided as methods, systems, or computer program products. Thus, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0077] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowcharts and / or block diagrams, as well as combinations of processes and / or blocks in the flowcharts and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowcharts and / or block diagrams. Figure 1 a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0078] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.

[0079] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0080] In a typical configuration, a computing device includes one or more processors (CPUs), input / output interfaces, network interfaces, and memory. Memory may include non-permanent storage in a computer-readable medium, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. Memory is an example of a computer-readable medium.

[0081] Computer-readable media includes permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. The information can be computer-readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disc read-only memory (CD-ROM), digital versatile disc (DVD) or other optical storage, magnetic cassettes, magnetic tape, magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer-readable media does not include transitory computer-readable media (transitory media), such as modulated data signals and carrier waves.

[0082] It should also be noted that the terms "comprises," "includes," or any other variations thereof are intended to encompass non-exclusive inclusion, such that a process, method, commodity, or apparatus that includes a series of elements includes not only those elements but also other elements not explicitly listed, or includes elements inherent to such process, method, commodity, or apparatus. In the absence of further limitations, an element defined by the phrase "comprises a ..." does not exclude the presence of other identical elements in the process, method, commodity, or apparatus that includes the element.

[0083] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Thus, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0084] The present invention may be described in the general context of computer-executable instructions, such as program modules, executed by a computer. Generally, program modules include routines, programs, objects, components, data structures, and the like that perform specific tasks or implement specific abstract data types. The present invention may also be practiced in distributed computing environments where tasks are performed by remote processing devices connected via a communications network. In a distributed computing environment, program modules may be located in both local and remote computer storage media, including storage devices.

[0085] The various embodiments in this specification are described in a progressive manner. Similar parts between the various embodiments can be referred to in conjunction with each other. Each embodiment focuses on the differences between the other embodiments. In particular, the system embodiments are generally similar to the method embodiments, so the description is relatively simple. For relevant parts, refer to the description of the method embodiments.

Claims

1. A method for evaluating an intelligent cockpit interaction system, comprising: Compare the directed graph corresponding to the interactive behavior data with the preset flow chart to obtain the interactive behavior path; Sorting the interaction behavior paths in descending order according to the average time loss value to obtain an interaction behavior path sequence; According to the interactive behavior path corresponding to the end of the interactive behavior path sequence, an evaluation scheme of the intelligent cockpit interaction system is obtained; Classifying the interaction behavior paths to obtain a first path set and a second path set; Calculating expected loss values ​​of the first path set and the second path set according to the average time loss values ​​and occurrence probabilities corresponding to the interaction behavior paths in the first path set and the second path set, respectively; Compare the loss expected values ​​of the first path set and the second path set, select the path set with the lower loss expected value, and obtain an intelligent cockpit interaction system evaluation plan based on the path set with the lower loss expected value.

2. The method according to claim 1, wherein The step of sorting the interaction behavior paths in descending order according to the average time loss value includes: According to the preset flow chart, select the preset behavior path; Calculating the loss of the interactive behavior path according to the preset behavior path to obtain an average time loss value corresponding to the interactive behavior path; The average time loss values ​​corresponding to the interaction behavior paths are sorted in descending order.

3. The method according to claim 2, wherein: The performing loss calculation on the interactive behavior path according to the preset behavior path to obtain an average time loss value corresponding to the interactive behavior path includes: Determining a behavior node according to the preset behavior path; Determine the number of behavior occurrences of adjacent behavior nodes corresponding to the interactive behavior path and the time intervals corresponding to adjacent behavior nodes; The loss is calculated based on the total number of events, the probability of occurrence, the number of times the behavior occurs, and the time interval corresponding to the interactive behavior path to obtain an average time loss value corresponding to the interactive behavior path.

4. The method according to claim 1, wherein The method further comprises: Classifying the interactive behavior paths corresponding to the preset flowchart to obtain a third path set; Calculating an average time loss value and an occurrence probability corresponding to the interactive behavior paths in the third path set to obtain an expected loss value of the third path set; Compare the expected loss values ​​of the first path set, the second path set, and the third path set, select the path set with the lower expected loss value, and obtain an intelligent cockpit interaction system evaluation plan based on the path set with the lower expected loss value.

5. The method according to claim 1, wherein The method further comprises: Obtain interactive behavior data; Process mining is performed on the acquired interaction behavior data to obtain a directed graph corresponding to the interaction behavior data.

6. The method according to claim 5, wherein: The performing process mining on the acquired interaction behavior data to obtain a directed graph corresponding to the interaction behavior data includes: Formatting the interactive behavior data to obtain formatted interactive behavior data; The interactive behavior data processed in the format is processed according to a process mining algorithm to obtain a directed graph corresponding to the interactive behavior data.

7. An intelligent cockpit interaction system evaluation device, comprising: A comparison module is used to compare the directed graph corresponding to the interactive behavior data with the preset flow chart to obtain the interactive behavior path; a sorting module, configured to sort the interaction behavior paths in descending order according to average time loss values ​​to obtain an interaction behavior path sequence; a processing module, configured to obtain an intelligent cockpit interaction system evaluation scheme based on the interaction behavior path corresponding to the end of the interaction behavior path sequence; A sorting module is used to classify the interactive behavior paths to obtain a first path set and a second path set; calculate the expected loss values ​​of the first path set and the second path set based on the average time loss values ​​and occurrence probabilities corresponding to the interactive behavior paths in the first path set and the second path set respectively; compare the expected loss values ​​of the first path set and the second path set, select the path set with a lower expected loss value, and obtain an intelligent cockpit interaction system evaluation plan based on the path set with a lower expected loss value.

8. An electronic device comprising: A processor, a memory, a communication interface, and a communication bus, wherein the processor, the memory, and the communication interface communicate with each other via the communication bus; The memory is used to store at least one executable instruction, where the executable instruction enables the processor to perform an operation corresponding to the method according to any one of claims 1 to 6.

9. A computer storage medium having a computer program stored thereon, wherein when the program is executed by a processor, the method according to any one of claims 1 to 6 is implemented.

Images