User pain point identification method and device, electronic equipment and storage medium

Abstract

The embodiment of the invention provides a user pain point identification method and device, electronic equipment and a storage medium, and belongs to the technical field of computers. The method comprises the following steps: acquiring operation process logs of a plurality of target users, and determining an operation path of each target user according to the operation process logs; obtaining user feedback data of the target users, and determining the satisfaction degree of each target user according to the user feedback data; determining a plurality of key operation nodes according to the operation path, and determining a satisfaction difference value of each key operation node according to the satisfaction; and according to the satisfaction difference value, screening from the key operation nodes to obtain a to-be-optimized operation node, and according to the to-be-optimized operation node, generating user pain point information. According to the embodiment of the invention, the accuracy of user pain point recognition and the user experience can be improved.

Description

Technical Field

[0001] The present application relates to the field of computer technology, and in particular to a method and device for identifying user pain points, an electronic device, and a storage medium. Background Art

[0002] In the field of financial technology, transaction-based banking services such as transfers and payments need to focus on user experience, so it is crucial to obtain user feedback and optimize and improve the operation process, but how to understand the user's true thoughts is the difficulty of this process. User feedback usually only includes scores, fixed options and a few supplementary contents. Most users are reluctant to describe too many pain points when giving feedback, or even if they do, they only focus on the appearance and usage experience. Many feedback information only has a general description, and it is impossible to obtain valuable analysis results through feedback information.

[0003] The common user feedback automatic recognition systems in the industry are mostly based on user feedback texts, and they extract keywords and high-frequency words to understand the feedback points that appear frequently. The problem with this method is that most user feedback is vague and not precise enough, resulting in most of the extracted keywords being complaints, which makes it impossible to accurately identify user pain points and optimize and improve the operation process based on user pain points, thus affecting the user experience. Summary of the invention

[0004] The main purpose of the embodiments of the present application is to propose a user pain point identification method and device, an electronic device and a storage medium, aiming to improve the accuracy of user pain point identification and user experience.

[0005] To achieve the above purpose, a first aspect of an embodiment of the present application proposes a method for identifying user pain points, the method comprising:

[0006] Acquire operation process logs of multiple target users, and determine the operation path of each of the target users according to the operation process logs;

[0007] Acquire user feedback data of the target users, and determine the satisfaction level of each of the target users according to the user feedback data;

[0008] Determine a number of key operation nodes according to the operation path, and determine a satisfaction difference value of each of the key operation nodes according to the satisfaction;

[0009] The operation nodes to be optimized are screened from the key operation nodes according to the satisfaction difference values, and user pain point information is generated according to the operation nodes to be optimized.

[0010] In some embodiments, in response to the first interaction event of the terminal, obtaining operation process logs of multiple target users, and determining the operation path of each of the target users according to the operation process logs includes:

[0011] Obtain a preset process tree, and perform tracking on multiple operation nodes of the process tree;

[0012] Monitor the operation behavior of the target user, and record the target operation node corresponding to the operation behavior to obtain the operation process log;

[0013] The arrangement order of the target operation nodes is determined according to the execution order of the operation behaviors, and then the target operation nodes are sorted to obtain the operation path.

[0014] In some embodiments, the user feedback data includes at least one of text feedback information, voice feedback information, and feedback option information, and determining the satisfaction of each target user according to the user feedback data includes at least one of the following:

[0015] Performing semantic recognition on the text feedback information, and obtaining the satisfaction of the target user according to the semantic recognition result;

[0016] Performing speech recognition on the speech feedback information, and obtaining the satisfaction level of the target user according to the speech recognition result;

[0017] The target user's feedback evaluation on a plurality of preset feedback items is counted according to the feedback option information, and the target user's satisfaction is obtained according to the feedback evaluation.

[0018] In some embodiments, determining a number of key operation nodes according to the operation path includes:

[0019] Determine a plurality of target operation nodes corresponding to each of the operation paths, and count the occurrence frequencies of each of the target operation nodes in all of the operation paths;

[0020] A preset frequency threshold is obtained, and the target operation node whose occurrence frequency is greater than or equal to the frequency threshold is selected as the key operation node.

[0021] In some embodiments, determining the satisfaction difference value of each of the key operation nodes according to the satisfaction includes:

[0022] Screening out satisfied users and dissatisfied users from the target users according to the satisfaction;

[0023] Determining, according to the target users corresponding to each of the operation paths, a first number of satisfied users and a second number of dissatisfied users corresponding to each of the key operation nodes;

[0024] Determining a ratio of satisfied users at each of the key operation nodes according to a ratio of the first number to the total number of satisfied users;

[0025] Determining a proportion of dissatisfied users at each of the key operation nodes according to a ratio of the second number to the total number of dissatisfied users;

[0026] The satisfaction difference value of each of the key operation nodes is determined according to the difference between the proportion of dissatisfied users and the proportion of satisfied users.

[0027] In some embodiments, the step of selecting the operation nodes to be optimized from the key operation nodes according to the satisfaction difference value includes:

[0028] Determine the satisfaction difference threshold corresponding to each of the key operation nodes;

[0029] When the satisfaction difference value of the key operation node is greater than or equal to the corresponding satisfaction difference threshold, the key operation node is determined to be the operation node to be optimized.

[0030] In some embodiments, determining the satisfaction difference threshold corresponding to each of the key operation nodes includes:

[0031] Screening out very satisfied users and generally satisfied users from the target users according to the satisfaction;

[0032] Determining, according to the target users corresponding to each of the operation paths, a third number of the very satisfied users and a fourth number of the generally satisfied users corresponding to each of the key operation nodes;

[0033] determining a proportion of very satisfied users at each of the key operation nodes according to a ratio of the third number to the total number of very satisfied users;

[0034] Determining the proportion of generally satisfied users at each of the key operation nodes according to the ratio of the fourth number to the total number of generally satisfied users;

[0035] The satisfaction difference threshold corresponding to each of the key operation nodes is determined according to the difference between the proportion of generally satisfied users and the proportion of very satisfied users.

[0036] To achieve the above-mentioned purpose, a second aspect of an embodiment of the present application provides a user pain point identification device, the device comprising:

[0037] An operation path determination module, used to obtain operation process logs of multiple target users, and determine the operation path of each target user according to the operation process logs;

[0038] A satisfaction determination module, used to obtain user feedback data of the target users, and determine the satisfaction of each of the target users according to the user feedback data;

[0039] A satisfaction difference value determination module, used to determine a number of key operation nodes according to the operation path, and determine the satisfaction difference value of each key operation node according to the satisfaction;

[0040] A screening module is used to screen the operation nodes to be optimized from the key operation nodes according to the satisfaction difference value, and generate user pain point information according to the operation nodes to be optimized.

[0041] To achieve the above-mentioned purpose, the third aspect of an embodiment of the present application proposes an electronic device, which includes a memory, a processor, a program stored on the memory and executable on the processor, and a data bus for realizing connection and communication between the processor and the memory. When the program is executed by the processor, the user pain point identification method described in the first aspect above is implemented.

[0042] To achieve the above-mentioned purpose, the fourth aspect of an embodiment of the present application proposes a storage medium, which is a computer-readable storage medium used for computer-readable storage, and the storage medium stores one or more programs, and the one or more programs can be executed by one or more processors to implement the user pain point identification method as described in the first aspect above.

[0043] The user pain point identification method and device, electronic device and storage medium proposed in the present application obtain the operation process logs of multiple target users, determine the operation path of each target user according to the operation process logs, obtain the user feedback data of the target users, determine the satisfaction of each target user according to the user feedback data, and then determine a number of key operation nodes according to the operation path, and determine the satisfaction difference value of each key operation node according to the satisfaction, and finally filter out the operation nodes to be optimized from the key operation nodes according to the satisfaction difference value, and generate user pain point information according to the operation nodes to be optimized. The embodiment of the present application counts the key operation nodes according to the user's operation path, determines the satisfaction difference value of each key operation node according to the user's satisfaction, thereby filtering out the operation nodes to be optimized that cause user dissatisfaction, improving the accuracy of user pain point identification, and optimizing the user operation process based on the operation nodes to be optimized, thereby improving user experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] Figure 1 This is a flow chart of a method for identifying user pain points provided by an embodiment of the present application;

[0045] Figure 2 yes Figure 1A flow chart of step S101 in FIG.

[0046] Figure 3 It is a schematic diagram of embedding points in a process tree provided in an embodiment of the present application;

[0047] Figure 4 yes Figure 1 A flow chart of step S102 in FIG.

[0048] Figure 5 yes Figure 1 A flow chart of step S103 in FIG.

[0049] Figure 6 yes Figure 1 Another flow chart of step S103 in ;

[0050] Figure 7 yes Figure 1 A flow chart of step S104 in FIG.

[0051] Figure 8 yes Figure 7 A flow chart of step S1041 in FIG.

[0052] Fig. 9 is a structural schematic diagram of a user pain point identification device provided in an embodiment of the present application;

[0053] Fig.10 It is a schematic diagram of the hardware structure of the electronic device provided in the embodiment of the present application. DETAILED DESCRIPTION

[0054] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0055] It should be noted that, although the functional modules are divided in the device schematic diagram and the logical order is shown in the flowchart, in some cases, the steps shown or described may be performed in a different order than the module division in the device or the order in the flowchart. The terms "first", "second", etc. in the specification, claims and the above drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence.

[0056] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art to which this application belongs. The terms used herein are only for the purpose of describing the embodiments of this application and are not intended to limit this application.

[0057] First, some nouns involved in this application are analyzed:

[0058] Human-Computer Interaction (HCI): It is a discipline that studies the interactive relationship between systems and users. Systems can be various machines or computerized systems and software. The human-computer interaction interface usually refers to the part visible to users. Users communicate with the system and operate it through the human-computer interaction interface, which can be as small as the play button on a radio or as large as the dashboard on an airplane or the control room of a power plant. Human-computer interaction events refer to the information exchange process between people and computers using a certain dialogue language and a certain interactive method to complete a certain task.

[0059] Artificial intelligence (AI) is a new technical science that studies and develops theories, methods, technologies and application systems for simulating, extending and expanding human intelligence. AI is a branch of computer science that attempts to understand the essence of intelligence and produce a new type of intelligent machine that can respond in a similar way to human intelligence. Research in this field includes robotics, speech recognition, image recognition, natural language processing and expert systems. AI can simulate the information process of human consciousness and thinking. AI is also a theory, method, technology and application system that uses digital computers or machines controlled by digital computers to simulate, extend and expand human intelligence, perceive the environment, acquire knowledge and use knowledge to obtain the best results.

[0060] Natural language processing (NLP): NLP uses computers to process, understand and apply human languages ​​(such as Chinese, English, etc.). NLP is a branch of artificial intelligence and an interdisciplinary subject between computer science and linguistics. It is often referred to as computational linguistics. Natural language processing includes grammatical analysis, semantic analysis, and text understanding. Natural language processing is often used in technical fields such as machine translation, handwritten and printed character recognition, speech recognition and text-to-speech conversion, information intent recognition, information extraction and filtering, text classification and clustering, public opinion analysis and opinion mining. It involves data mining related to language processing, machine learning, knowledge acquisition, knowledge engineering, artificial intelligence research, and linguistic research related to language computing.

[0061] User pain points: refers to the problems or dissatisfaction that users encounter when using products or services. For example, when using a financial app to handle a business, users may encounter many problems such as cumbersome operations, repeated verification, page freezes, etc. The operation nodes involved in these problems are user pain points. If user pain points can be effectively solved, the competitiveness of products or services and user loyalty can be improved.

[0062] Process Tree: A process model that describes the operation process through a tree structure, which can intuitively display the logical relationship between the various operation nodes of the operation process.

[0063] In the field of financial technology, transaction-based banking services such as transfers and payments need to focus on user experience, so it is crucial to obtain user feedback and optimize and improve the operation process, but how to understand the user's true thoughts is the difficulty of this process. User feedback usually only includes scores, fixed options and a few supplementary contents. Most users are reluctant to describe too many pain points when giving feedback, or even if they do, they only focus on the appearance and usage experience. Many feedback information only has a general description, and it is impossible to obtain valuable analysis results through feedback information.

[0064] The common user feedback automatic recognition systems in the industry are mostly based on user feedback texts, and they extract keywords and high-frequency words to understand the feedback points that appear frequently. The problem with this method is that most user feedback is vague and not precise enough, resulting in most of the extracted keywords being complaints, which makes it impossible to accurately identify user pain points and optimize and improve the operation process based on user pain points, thus affecting the user experience.

[0065] Based on this, the embodiments of the present application provide a method and device for identifying user pain points, an electronic device, and a storage medium, aiming to improve the accuracy of user pain point identification and user experience. The embodiments of the present application use the user's specific operation process to realize automatic analysis of behavior data, deeply explore the reasons that affect the user experience, and thus truly improve the user experience.

[0066] The user pain point identification method and device, electronic device and storage medium provided in the embodiments of the present application are specifically illustrated through the following embodiments. First, the user pain point identification method in the embodiments of the present application is described.

[0067] The embodiments of the present application can acquire and process relevant data based on artificial intelligence technology. Among them, artificial intelligence (AI) is the theory, method, technology and application system that uses digital computers or machines controlled by digital computers to simulate, extend and expand human intelligence, perceive the environment, acquire knowledge and use knowledge to obtain the best results.

[0068] AI basic technologies generally include sensors, dedicated AI chips, cloud computing, distributed storage, big data processing technology, operation / interaction systems, mechatronics, etc. AI software technologies mainly include computer vision technology, robotics technology, biometrics technology, speech processing technology, natural language processing technology, and machine learning / deep learning.

[0069] The user pain point identification method provided in the embodiment of the present application relates to the field of computer technology. The user pain point identification method provided in the embodiment of the present application can be applied to a terminal, can be applied to a server side, or can be software running in a terminal or a server side. In some embodiments, the terminal can be a smart phone, a tablet computer, a laptop computer, a desktop computer, etc.; the server side can be configured as an independent physical server, or a server cluster or distributed system composed of multiple physical servers, or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, CDN, and big data and artificial intelligence platforms; the software can be an application that implements the user pain point identification method, etc., but is not limited to the above forms.

[0070] The present application can be used in many general or special computer system environments or configurations. For example: personal computers, server computers, handheld or portable devices, tablet devices, multiprocessor systems, microprocessor-based systems, set-top boxes, programmable consumer electronics, network PCs, minicomputers, mainframe computers, distributed computing environments including any of the above systems or devices, etc. The present application can be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform specific tasks or implement specific abstract data types. The present application can also be practiced in distributed computing environments, in which tasks are performed by remote processing devices connected through a communication network. In a distributed computing environment, program modules can be located in local and remote computer storage media including storage devices.

[0071] It should be noted that in each specific implementation of the present application, when it comes to the need to perform relevant processing based on data related to user identity or characteristics such as user information, user behavior data, user historical data, and user location information, the user's permission or consent will be obtained first, and the collection, use, and processing of these data will comply with relevant laws, regulations, and standards. In addition, when the embodiment of the present application needs to obtain the user's sensitive personal information, the user's separate permission or consent will be obtained through a pop-up window or by jumping to a confirmation page. After clearly obtaining the user's separate permission or consent, the necessary user-related data for the normal operation of the embodiment of the present application will be obtained.

[0072] Figure 1 is an optional flow chart of the user pain point identification method provided in an embodiment of the present application. Figure 1 The method may include but is not limited to steps S101 to S104.

[0073] Step S101, obtaining operation process logs of multiple target users, and determining the operation path of each target user according to the operation process logs;

[0074] Step S102, obtaining user feedback data of target users, and determining the satisfaction of each target user according to the user feedback data;

[0075] Step S103, determining a number of key operation nodes according to the operation path, and determining a satisfaction difference value of each key operation node according to the satisfaction;

[0076] Step S104, filtering out operation nodes to be optimized from key operation nodes according to the satisfaction difference value, and generating user pain point information according to the operation nodes to be optimized.

[0077] In steps S101 to S104 shown in the embodiment of the present application, key operation nodes are counted according to the user's operation path, and the satisfaction difference value of each key operation node is determined according to the user's satisfaction, so as to screen out the operation nodes to be optimized that cause user dissatisfaction, thereby improving the accuracy of user pain point identification, and the user operation process can be optimized based on the operation nodes to be optimized, thereby improving the user experience.

[0078] See also Figure 2 In some embodiments, step S101 may include but is not limited to steps S1011 to S1013:

[0079] Step S1011, obtaining a preset process tree, and performing tracking on multiple operation nodes of the process tree;

[0080] Step S1012, monitoring the operation behavior of the target user, and recording the target operation node corresponding to the operation behavior to obtain an operation process log;

[0081] Step S1013, determining the arrangement order of the target operation nodes according to the execution order of the operation behaviors, and then sorting the target operation nodes to obtain the operation path.

[0082] In step S1011 of some embodiments, for products and services that require user pain point identification, such as transfer, payment, fund purchase, balance inquiry and other services of financial apps, a process tree can be pre-built based on all the steps and operation nodes that may be involved in the user operation process, and each operation node can be embedded to facilitate monitoring and capturing of user operation behaviors.

[0083] In step S1012 of some embodiments, the user's operation behavior is monitored, and relevant information such as the target operation node and operation time, operation result, etc. corresponding to each operation behavior is recorded to obtain an operation process log.

[0084] In step S1013 of some embodiments, the target operation nodes are sorted according to the execution order of the operation behavior to obtain the operation path, and the user's operation process log and operation path are uploaded to the server, and the server is used to save and subsequently identify and analyze the user's pain points. It can be understood that the operation path of the embodiment of the present application is related to the process tree but not completely the same. When constructing the process tree, it is necessary to consider various possible operation steps involved, and the user's actual operation path may only be a combination of some operation nodes in the process tree.

[0085] like Figure 3 The figure is a schematic diagram of embedding points in a process tree provided by an embodiment of the present application. Figure 3 A part of the process tree for performing transfer operations in a financial APP is shown, including the operation nodes "Enter page A", "Whether to manually enter the payee information", "Select the payment information through the user", "Manually enter the information", "Submit the information", "Need to adjust the limit", "Need to adjust", "No adjustment is required", "Adjust through a manual seat", "Manual seat adjustment of the limit", "No need for manual seat adjustment" and "Operation successful". You can select "Select the payment information through the user", "Manually enter the information", "Submit the information", "Need to adjust the limit", "Need to adjust", "No adjustment is required", "Adjust through a manual seat", "Manual seat adjustment of the limit" and "Operation successful" as the operation nodes for tracking. From entering the page to the end of the entire process, the log of each operation node is monitored and recorded to form an operation process log, and the operation path is obtained based on the operation process log.

[0086] In some optional embodiments, the operation nodes can be divided into two categories: 1) conventional log nodes; 2) nodes that may cause user complaints, such as some abnormal reminders, time-consuming operations (supplementary identity verification, limit setting, etc.). For conventional log nodes, it can be determined whether to embed nodes according to actual conditions, and nodes that may cause user complaints are embedded.

[0087] It can be understood that the embodiment of the present application can quickly and accurately obtain the user's operation process log and operation path by constructing a process tree and performing tracking, thereby improving the efficiency and accuracy of user pain point identification.

[0088] See also Figure 4 In some embodiments, the user feedback data includes at least one of text feedback information, voice feedback information, and feedback option information. The step of determining the satisfaction of each target user according to the user feedback data in step S102 may include, but is not limited to, at least one of steps S1021 to S1023:

[0089] Step S1021, performing semantic recognition on the text feedback information, and obtaining the target user's satisfaction according to the semantic recognition result;

[0090] Step S1022, performing speech recognition on the speech feedback information, and obtaining the target user's satisfaction according to the speech recognition result;

[0091] Step S1023: Count the target user's feedback evaluation on a number of preset feedback items according to the feedback option information, and obtain the target user's satisfaction according to the feedback evaluation.

[0092] In step S1021 of some embodiments, text feedback information of the user after completing the current operation process is obtained, and the text feedback information is input into a semantic analysis model for semantic analysis and recognition, so as to obtain the satisfaction of the target user.

[0093] It is understandable that semantic analysis is a branch of artificial intelligence and a core task of natural language processing (NLP), involving multiple disciplines such as linguistics, computational linguistics, machine learning, and cognitive language. Semantic analysis refers to the use of various methods to learn and understand the semantic content represented by a text. Any understanding of language can be classified as semantic analysis. A text is usually composed of words, sentences, and paragraphs. According to the different language units of the object of understanding, semantic analysis can be further decomposed into lexical semantic analysis, sentence semantic analysis, and text semantic analysis. Generally speaking, lexical semantic analysis focuses on how to obtain or distinguish the semantics of words, sentence semantic analysis attempts to analyze the semantics expressed by the entire sentence, and text semantic analysis aims to study the internal structure of natural language texts and understand the semantic relationship between text units (which can be sentence clauses or paragraphs). Simply put, the goal of semantic analysis is to achieve automatic semantic analysis in various language units (including words, sentences, and texts) by establishing effective models and systems, so as to understand the true semantics expressed by the entire text.

[0094] The semantic analysis model of the embodiment of the present application can adopt the existing semantic analysis system framework, or can be obtained through deep learning training. After the semantic analysis model performs semantic analysis on the text feedback information, a semantic recognition result can be obtained, which can quantify the user's satisfaction with the current operation process to a certain extent.

[0095] In step S1022 of some embodiments, voice feedback information of the user is obtained after completing the current operation process, and the voice feedback information is input into the voice recognition model for voice recognition to obtain feedback text information, and then the feedback text information is input into the aforementioned semantic analysis model for semantic analysis and recognition to obtain the satisfaction of the target user.

[0096] In the embodiment of the present application, the speech recognition model can adopt the existing speech recognition system framework, including acoustic analysis (Signal Analysis), acoustic model (Acoustic Model), dictionary (Lexicon), language model (LanguageModel), search / decoding (Search / Decoding).

[0097] In step S1023 of some embodiments, several feedback items and corresponding evaluation options (such as dissatisfied, generally satisfied, very satisfied, etc.) are pre-set, feedback option information of the user is obtained after completing the current operation process, and the user's feedback evaluation on different feedback items is counted to calculate the user's overall satisfaction with the current operation process.

[0098] It is understandable that the embodiment of the present application can provide the user with one or more of the three feedback methods of text feedback, voice feedback and option feedback after the current operation process ends, and the user can choose whether to provide feedback and in what form. The presentation of satisfaction can be intuitively dissatisfied, generally satisfied, very satisfied, etc., or it can be presented in the form of a score, such as within the range of 0 to 100 points. The higher the score, the higher the satisfaction. The embodiment of the present application does not limit this.

[0099] See also Figure 5 In some embodiments, the step of determining a number of key operation nodes according to the operation path in step S103 may include, but is not limited to, steps S1031 to S1032:

[0100] Step S1031, determining multiple target operation nodes corresponding to each operation path, and counting the occurrence frequency of each target operation node in all operation paths;

[0101] Step S1032: Obtain a preset frequency threshold, and select a target operation node whose occurrence frequency is greater than or equal to the frequency threshold as a key operation node.

[0102] In step S1031 of some embodiments, the operation node on the operation path of each user is used as the target operation node corresponding to the user, and statistics are counted to see whether the target operation node also appears in the operation paths of other users, so as to obtain the appearance frequency of the target operation node in all operation paths. The appearance frequency actually reflects the frequency with which the user encounters the target operation node during the operation process.

[0103] It should be noted that the target operation node in the embodiment of the present application has a different meaning from the operation node in the aforementioned process tree. The operation node in the process tree is the operation node that the user may encounter, while the target operation node is the operation node actually encountered by the user determined based on the user's operation path.

[0104] In step S1032 of some embodiments, considering that the target operation nodes with too low frequency of occurrence are only encountered by a very small number of users, the process of identifying user pain points is relatively random, and it is impossible to accurately evaluate whether the corresponding operation nodes need to be optimized. Therefore, the embodiment of the present application pre-sets a frequency threshold (such as 10%) and selects the target operation nodes with a frequency exceeding the frequency threshold as the key operation nodes.

[0105] It can be appreciated that the embodiment of the present application selects key operation nodes for subsequent user pain point identification based on the frequency of occurrence of the target operation nodes in the entire operation path, which can filter out operation nodes that are only encountered by a very small number of users, avoid user pain point identification from being affected by randomness, and improve the accuracy of user pain point identification.

[0106] It should be noted that although some target operation nodes are abandoned during the current user pain point identification process, the frequency of occurrence of each target operation node will be recalculated and key operation nodes will be selected during the next user pain point identification and operation node optimization process. Based on different user batches, the selected key operation nodes will also be different, and ultimately all operation nodes that may need to be optimized will be covered.

[0107] See also Figure 6 In some embodiments, the step of determining the satisfaction difference value of each key operation node according to the satisfaction in step S103 may include but is not limited to steps S1033 to S1037:

[0108] Step S1033, screening out satisfied users and dissatisfied users from the target users according to their satisfaction;

[0109] Step S1034, determining a first number of satisfied users and a second number of dissatisfied users corresponding to each key operation node according to the target users corresponding to each operation path;

[0110] Step S1035, determining the proportion of satisfied users at each key operation node according to the ratio of the first number to the total number of satisfied users;

[0111] Step S1036, determining the proportion of dissatisfied users at each key operation node according to the ratio of the second number to the total number of dissatisfied users;

[0112] Step S1037, determining the satisfaction difference value of each key operation node according to the difference between the proportion of dissatisfied users and the proportion of satisfied users.

[0113] In step S1033 of some embodiments, the target users are divided into satisfied users and dissatisfied users according to their satisfaction, wherein satisfied users can be further divided into generally satisfied users and very satisfied users, and the specific division rules are not limited in the embodiments of the present application.

[0114] In step S1034 of some embodiments, after the target users are divided into satisfied users and dissatisfied users, a first number of satisfied users and a second number of dissatisfied users corresponding to each key operation node may be counted based on whether the user corresponding to each operation path is a satisfied user or dissatisfied user.

[0115] In step S1035 of some embodiments, the proportion of satisfied users for each key operation node is determined based on the ratio of the first number to the total number of satisfied users. The proportion of satisfied users reflects the proportion of satisfied users who encounter the key operation node in the satisfied user group, that is, the probability of a satisfied user encountering the key operation node.

[0116] In step S1036 of some embodiments, the proportion of dissatisfied users at each key operation node is determined based on the ratio of the second number to the total number of dissatisfied users. The proportion of dissatisfied users reflects the proportion of dissatisfied users who encounter the key operation node in the dissatisfied user group, that is, the probability of dissatisfied users encountering the key operation node.

[0117] In step S1037 of some embodiments, the satisfaction difference value of each key operation node is determined based on the difference between the proportion of dissatisfied users and the proportion of satisfied users. If the satisfaction difference value of a key operation node is too large, it means that for this key operation node, the probability that an dissatisfied user encounters this operation node is much greater than the probability that a satisfied user encounters this key operation node, that is, the probability that this key operation node causes user dissatisfaction is relatively high.

[0118] In the embodiment of the present application, the percentage of satisfied users / percentage of dissatisfied users of the satisfied user group / unsatisfied user group at each key operation node is counted, and the difference value of satisfaction at each key operation node is calculated, as shown in Table 1 below.

[0119] Table 1

[0120] Serial number Key Nodes Percentage of satisfied users Percentage of dissatisfied users Satisfaction Difference 1 Buried point A6 N1％ N2％ (N2-N1)% 2 Buried point A1 N3％ N4％ (N4-N3)% 3 Buried point A7 N5％ N6％ (N6-N5)% … … … … …

[0121] By sorting according to the satisfaction difference values, we can get the key operation node set A{A6, A1, A7…}.

[0122] It can be appreciated that the embodiment of the present application can accurately determine the probability of each key operation node causing user dissatisfaction through the calculation of the satisfaction difference value, thereby improving the accuracy of user pain point identification.

[0123] See also Figure 7 In some embodiments, the step of generating a user pain point identification file according to the first text information and the first image information in step S104 may include, but is not limited to, steps S1041 to S1042:

[0124] Step S1041, determining the satisfaction difference threshold corresponding to each key operation node;

[0125] Step S1042: When the satisfaction difference value of the key operation node is greater than or equal to the corresponding satisfaction difference threshold, the key operation node is determined to be an operation node to be optimized.

[0126] In step S1041 of some embodiments, for each key operation node, its corresponding satisfaction difference threshold can be determined in advance; the satisfaction difference threshold of each key operation node can be set to the same preset value, or the satisfaction difference threshold corresponding to each key operation node can be dynamically generated according to the real-time data of the current operation process.

[0127] In step S1042 of some embodiments, when the satisfaction difference value of a key operation node is greater than or equal to the corresponding satisfaction difference value, it indicates that the probability of the key operation node causing user dissatisfaction is too high, and the key operation node is used as an operation node to be optimized. The set of operation nodes to be optimized is the user pain point information output by the embodiment of the present application.

[0128] In some optional embodiments, the operation nodes to be optimized may be sorted according to the satisfaction difference values ​​to obtain a list of operation nodes to be optimized. This list may be sorted from large to small according to the satisfaction difference values. The higher the ranking, the higher the optimization weight.

[0129] See also Figure 8 In some embodiments, step S1041 may include but is not limited to steps S10411 to S10415:

[0130] Step S10411, filtering out very satisfied users and generally satisfied users from the target users according to their satisfaction;

[0131] Step S10412, determining a third number of very satisfied users and a fourth number of generally satisfied users corresponding to each key operation node according to the target users corresponding to each operation path;

[0132] Step S10413, determining the proportion of very satisfied users at each key operation node according to the ratio of the third number to the total number of very satisfied users;

[0133] Step S10414, determining the proportion of generally satisfied users of each key operation node according to the ratio of the fourth number to the total number of generally satisfied users;

[0134] Step S10415, determining the satisfaction difference threshold corresponding to each key operation node according to the difference between the proportion of generally satisfied users and the proportion of very satisfied users.

[0135] In step S10411 of some embodiments, satisfied users are further divided into generally satisfied users and very satisfied users according to their satisfaction, and the specific division rules are not limited in the embodiments of the present application.

[0136] In step S10412 of some embodiments, after further dividing satisfied users into very satisfied users and generally satisfied users, based on whether the users corresponding to each operation path are very satisfied users or generally satisfied users, the third number of very satisfied users and the fourth number of generally satisfied users corresponding to each key operation node can be counted.

[0137] In step S10413 of some embodiments, the proportion of very satisfied users for each key operation node is determined based on the ratio of the third number to the total number of very satisfied users. The proportion of very satisfied users reflects the proportion of very satisfied users who encounter the key operation node in the very satisfied user group, that is, the probability of very satisfied users encountering the key operation node.

[0138] In step S10414 of some embodiments, the proportion of generally satisfied users for each key operation node is determined based on the ratio of the fourth number to the total number of generally satisfied users. The proportion of generally satisfied users reflects the proportion of generally satisfied users who encounter the key operation node in the generally satisfied user group, that is, the probability of a generally satisfied user encountering the key operation node.

[0139] In step S10415 of some embodiments, the satisfaction difference threshold corresponding to each key operation node is determined according to the difference between the proportion of generally satisfied users and the proportion of very satisfied users. If the difference between the proportion of dissatisfied users and the proportion of satisfied users for a certain key operation node is greater than or equal to the satisfaction difference threshold, it means that for the key operation node, the probability difference between dissatisfied users and satisfied users is not less than the probability difference between generally satisfied users and very satisfied users, that is, the probability of the key operation node causing user dissatisfaction is relatively high.

[0140] The embodiment of the present application determines the satisfaction difference threshold T according to the difference between the proportion of generally satisfied users and the proportion of very satisfied users, and obtains a threshold list T{T6, T1, T7...}. When the satisfaction difference value of a key operation node is not less than the corresponding threshold, the key operation node is retained; if it is less than the corresponding threshold, the key operation node is eliminated, and the final list of operation nodes to be optimized N{An|An>Tn, An∈A} is obtained.

[0141] The embodiment of the present application dynamically determines the satisfaction difference threshold corresponding to each key operation node according to the difference between the proportion of generally satisfied users and the proportion of very satisfied users, so that the satisfaction difference threshold is more in line with the real-time situation of each key operation node, further improving the accuracy of user pain point identification.

[0142] It can be recognized that the embodiment of the present application obtains the operation process logs of multiple target users, determines the operation path of each target user according to the operation process log, obtains the user feedback data of the target users, determines the satisfaction of each target user according to the user feedback data, and then determines a number of key operation nodes according to the operation path, and determines the satisfaction difference value of each key operation node according to the satisfaction, and finally selects the operation nodes to be optimized from the key operation nodes according to the satisfaction difference value, and generates user pain point information according to the operation nodes to be optimized. The embodiment of the present application counts the key operation nodes according to the user's operation path, determines the satisfaction difference value of each key operation node according to the user's satisfaction, thereby selecting the operation nodes to be optimized that cause user dissatisfaction, improves the accuracy of user pain point identification, and can optimize the user operation process based on the operation nodes to be optimized, thereby improving the user experience.

[0143] In addition, the embodiments of the present application can accurately collect user behavior data, and intelligently analyze the key operation nodes that cause user experience pain points based on user behavior data and user feedback data, and as more user data is accumulated, the more accurate the analysis results are; user pain points can be accurately analyzed without detailed user feedback, providing a basis for optimizing operation processes and improving user experience.

[0144] Compared with the traditional user feedback keyword intelligent analysis solution, the embodiment of the present application is more convenient. It can complete active intelligent analysis without the user describing the complaint points in detail, and the analysis results are more accurate. The traditional user feedback analysis system can only rely on text analysis of user feedback, and the text expression itself will have errors and generalizations. The embodiment of the present application starts from the user operation process, and the final analysis results also fall into each key operation node, and the identified user pain points are more accurate.

[0145] See also Fig. 9 The embodiment of the present application further provides a user pain point identification device, which can implement the above-mentioned user pain point identification method, and the user pain point identification device includes:

[0146] An operation path determination module is used to obtain operation process logs of multiple target users and determine the operation path of each target user according to the operation process logs;

[0147] A satisfaction determination module is used to obtain user feedback data of target users and determine the satisfaction of each target user based on the user feedback data;

[0148] A satisfaction difference value determination module is used to determine a number of key operation nodes according to the operation path, and determine the satisfaction difference value of each key operation node according to the satisfaction;

[0149] The screening module is used to screen the operation nodes to be optimized from the key operation nodes according to the satisfaction difference value, and generate user pain point information according to the operation nodes to be optimized.

[0150] The specific implementation of the user pain point identification device is basically the same as the specific implementation of the above-mentioned user pain point identification method, and will not be repeated here.

[0151] The embodiment of the present application also provides an electronic device, the electronic device comprising: a memory, a processor, a program stored in the memory and executable on the processor, and a data bus for realizing connection and communication between the processor and the memory, and the program is executed by the processor to realize the above-mentioned user pain point identification method. The electronic device can be any intelligent terminal including a tablet computer, a car computer, etc.

[0152] See also Fig.10 , Fig.10 The hardware structure of an electronic device of another embodiment is illustrated, and the electronic device includes:

[0153] The processor 1001 may be implemented by a general-purpose CPU (Central Processing Unit), a microprocessor, an application-specific integrated circuit (ASIC), or one or more integrated circuits, and is used to execute relevant programs to implement the technical solutions provided in the embodiments of the present application;

[0154] The memory 1002 can be implemented in the form of a read-only memory (ROM), a static storage device, a dynamic storage device, or a random access memory (RAM). The memory 1002 can store an operating system and other application programs. When the technical solution provided in the embodiment of this specification is implemented by software or firmware, the relevant program code is stored in the memory 1002, and the processor 1001 calls and executes the user pain point identification method of the embodiment of this application;

[0155] Input / output interface 1003, used to implement information input and output;

[0156] The communication interface 1004 is used to realize the communication interaction between the device and other devices. The communication can be realized through a wired manner (such as USB, network cable, etc.) or a wireless manner (such as mobile network, WIFI, Bluetooth, etc.);

[0157] A bus 1005 , which transmits information between various components of the device (e.g., the processor 1001 , the memory 1002 , the input / output interface 1003 , and the communication interface 1004 );

[0158] The processor 1001 , the memory 1002 , the input / output interface 1003 and the communication interface 1004 are connected to each other in communication within the device via the bus 1005 .

[0159] An embodiment of the present application also provides a storage medium, which is a computer-readable storage medium used for computer-readable storage. The storage medium stores one or more programs, and the one or more programs can be executed by one or more processors to implement the above-mentioned user pain point identification method.

[0160] The memory, as a non-transient computer-readable storage medium, can be used to store non-transient software programs and non-transient computer executable programs. In addition, the memory may include a high-speed random access memory, and may also include a non-transient memory, such as at least one disk storage device, a flash memory device, or other non-transient solid-state storage device. In some embodiments, the memory may optionally include a memory remotely disposed relative to the processor, and these remote memories may be connected to the processor via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0161] The user pain point identification method and device, electronic device and storage medium provided by the embodiment of the present application obtain the operation process logs of multiple target users, determine the operation path of each target user according to the operation process log, obtain the user feedback data of the target users, determine the satisfaction of each target user according to the user feedback data, and then determine a number of key operation nodes according to the operation path, and determine the satisfaction difference value of each key operation node according to the satisfaction, and finally filter out the operation nodes to be optimized from the key operation nodes according to the satisfaction difference value, and generate user pain point information according to the operation nodes to be optimized. The embodiment of the present application counts the key operation nodes according to the user's operation path, determines the satisfaction difference value of each key operation node according to the user's satisfaction, thereby filtering out the operation nodes to be optimized that cause user dissatisfaction, improves the accuracy of user pain point identification, and can optimize the user operation process based on the operation nodes to be optimized, thereby improving the user experience.

[0162] The embodiments described in the embodiments of the present application are intended to more clearly illustrate the technical solutions of the embodiments of the present application and do not constitute a limitation on the technical solutions provided in the embodiments of the present application. Those skilled in the art will appreciate that with the evolution of technology and the emergence of new application scenarios, the technical solutions provided in the embodiments of the present application are also applicable to similar technical problems.

[0163] Those skilled in the art will appreciate that the technical solutions shown in the figures do not constitute a limitation on the embodiments of the present application, and may include more or fewer steps than shown in the figures, or a combination of certain steps, or different steps.

[0164] The device embodiments described above are merely illustrative, and the units described as separate components may or may not be physically separated, that is, they may be located in one place or distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0165] Those skilled in the art will appreciate that all or some of the steps in the methods disclosed above, and the functional modules / units in the systems and devices may be implemented as software, firmware, hardware, or a suitable combination thereof.

[0166] The terms "first", "second", "third", "fourth", etc. (if any) in the specification of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0167] It should be understood that in the present application, "at least one (item)" means one or more, and "plurality" means two or more. "And / or" is used to describe the association relationship of associated objects, indicating that three relationships may exist. For example, "A and / or B" can mean: only A exists, only B exists, and A and B exist at the same time, where A and B can be singular or plural. The character " / " generally indicates that the objects associated before and after are in an "or" relationship. "At least one of the following" or similar expressions refers to any combination of these items, including any combination of single or plural items. For example, at least one of a, b or c can mean: a, b, c, "a and b", "a and c", "b and c", or "a and b and c", where a, b, c can be single or multiple.

[0168] In the several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the above units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0169] The units described above as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0170] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0171] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including multiple instructions to enable a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of various embodiments of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (Read-Only Memory, referred to as ROM), random access memory (Random Access Memory, referred to as RAM), disk or optical disk and other media that can store programs.

[0172] The preferred embodiments of the present invention are described above with reference to the accompanying drawings, but the scope of the rights of the present invention is not limited thereto. Any modification, equivalent substitution and improvement made by a person skilled in the art without departing from the scope and essence of the present invention should be within the scope of the rights of the present invention.

Claims

1. A method for identifying user pain points, characterized in that: The method comprises: Acquire operation process logs of multiple target users, and determine the operation path of each of the target users according to the operation process logs; Acquire user feedback data of the target users, and determine the satisfaction level of each of the target users according to the user feedback data; Determine a number of key operation nodes according to the operation path, and determine a satisfaction difference value of each of the key operation nodes according to the satisfaction; The operation nodes to be optimized are screened from the key operation nodes according to the satisfaction difference value, and user pain point information is generated according to the operation nodes to be optimized.

2. The user pain point identification method according to claim 1, characterized in that: The obtaining operation process logs of multiple target users and determining the operation path of each target user according to the operation process logs includes: Obtain a preset process tree, and perform tracking on multiple operation nodes of the process tree; Monitor the operation behavior of the target user, and record the target operation node corresponding to the operation behavior to obtain the operation process log; The arrangement order of the target operation nodes is determined according to the execution order of the operation behaviors, and then the target operation nodes are sorted to obtain the operation path.

3. The user pain point identification method according to claim 1, characterized in that: The user feedback data includes at least one of text feedback information, voice feedback information, and feedback option information. The determining the satisfaction of each target user according to the user feedback data includes at least one of the following: Performing semantic recognition on the text feedback information, and obtaining the satisfaction of the target user according to the semantic recognition result; Performing speech recognition on the speech feedback information, and obtaining the satisfaction level of the target user according to the speech recognition result; The target user's feedback evaluation on a plurality of preset feedback items is counted according to the feedback option information, and the target user's satisfaction is obtained according to the feedback evaluation.

4. The user pain point identification method according to claim 1, characterized in that: Determining a number of key operation nodes according to the operation path includes: Determine a plurality of target operation nodes corresponding to each of the operation paths, and count the occurrence frequencies of each of the target operation nodes in all of the operation paths; A preset frequency threshold is obtained, and the target operation node whose occurrence frequency is greater than or equal to the frequency threshold is selected as the key operation node.

5. The user pain point identification method according to claim 1, characterized in that: The determining of the satisfaction difference value of each of the key operation nodes according to the satisfaction includes: Screening out satisfied users and dissatisfied users from the target users according to the satisfaction; Determining, according to the target users corresponding to each of the operation paths, a first number of satisfied users and a second number of dissatisfied users corresponding to each of the key operation nodes; Determining a ratio of satisfied users at each of the key operation nodes according to a ratio of the first number to the total number of satisfied users; Determining a proportion of dissatisfied users at each of the key operation nodes according to a ratio of the second number to the total number of dissatisfied users; The satisfaction difference value of each of the key operation nodes is determined according to the difference between the proportion of dissatisfied users and the proportion of satisfied users.

6. The method for identifying user pain points according to any one of claims 1 to 5, characterized in that: The step of selecting the operation nodes to be optimized from the key operation nodes according to the satisfaction difference value includes: Determine the satisfaction difference threshold corresponding to each of the key operation nodes; When the satisfaction difference value of the key operation node is greater than or equal to the corresponding satisfaction difference threshold, the key operation node is determined to be the operation node to be optimized.

7. The user pain point identification method according to claim 6, characterized in that: The determining of the satisfaction difference threshold corresponding to each of the key operation nodes includes: Screening out very satisfied users and generally satisfied users from the target users according to the satisfaction; Determining, according to the target users corresponding to each of the operation paths, a third number of the very satisfied users and a fourth number of the generally satisfied users corresponding to each of the key operation nodes; determining a proportion of very satisfied users at each of the key operation nodes according to a ratio of the third number to the total number of very satisfied users; Determining the proportion of generally satisfied users at each of the key operation nodes according to the ratio of the fourth number to the total number of generally satisfied users; The satisfaction difference threshold corresponding to each of the key operation nodes is determined according to the difference between the proportion of generally satisfied users and the proportion of very satisfied users.

8. A user pain point identification device, characterized in that: The device comprises: An operation path determination module, used to obtain operation process logs of multiple target users, and determine the operation path of each target user according to the operation process logs; A satisfaction determination module, used to obtain user feedback data of the target users, and determine the satisfaction of each of the target users according to the user feedback data; A satisfaction difference value determination module, used to determine a number of key operation nodes according to the operation path, and determine the satisfaction difference value of each key operation node according to the satisfaction; A screening module is used to screen the operation nodes to be optimized from the key operation nodes according to the satisfaction difference value, and generate user pain point information according to the operation nodes to be optimized.

9. An electronic device, characterized in that: The electronic device includes a memory, a processor, a program stored in the memory and executable on the processor, and a data bus for realizing connection and communication between the processor and the memory. When the program is executed by the processor, the steps of the user pain point identification method as described in any one of claims 1 to 7 are realized.

10. A storage medium, the storage medium being a computer-readable storage medium, used for computer-readable storage, characterized in that: The storage medium stores one or more programs, and the one or more programs can be executed by one or more processors to implement the steps of the user pain point identification method as described in any one of claims 1 to 7.

Images