Process control methods, devices, electronic equipment and storage media

Abstract

Embodiments of the present application provide a process adjustment method and device, electronic equipment and storage medium. The process adjustment method comprises: obtaining a user state of a user in a preset business scenario, the preset business scenario comprising a plurality of business processes, each business process being composed of at least one business node; if the user is an experienced user, obtaining a score corresponding to a business process experienced by the user in the preset business scenario; and adjusting an allocation probability of an initial business node of the experienced business process based on the score corresponding to the experienced business process. Through the above method, the allocation probability of the initial business node of the experienced business process is adjusted according to the score corresponding to the experienced business process of the user in the preset business scenario. Compared with randomly selecting the initial business node of the business process, the present application can enable the user to experience the unexperienced business process with a greater probability, thereby improving the user experience.

Description

Technical Field

[0001] This application belongs to the field of computer technology, and specifically relates to a process regulation method, apparatus, electronic device and readable storage medium. Background Technology

[0002] In human-computer interaction scenarios, the system typically performs semantic understanding and intent recognition on the speaker's input speech, and then responds based on the intent recognition results. However, the system may randomly provide the user with a speech training process in the same scenario, which involves a great deal of randomness. This may result in a user experiencing the same process multiple times, leading to a poor user experience. Summary of the Invention

[0003] In view of the above problems, this application proposes a process regulation method, apparatus, electronic device, and storage medium to improve the above problems.

[0004] In a first aspect, this application provides a process adjustment method, the method comprising: obtaining a user's state in a preset business scenario, the preset business scenario including multiple business processes, each of the business processes consisting of at least one business node; if the user is a user who has already experienced the process, obtaining the score corresponding to the business process that the user has already experienced in the preset business scenario; and adjusting the allocation probability of the initial business node of the business process based on the score corresponding to the business process that has already been experienced.

[0005] Furthermore, obtaining the user's status in a preset business scenario includes: obtaining the user's login information in the preset business scenario; detecting whether there is historical timestamp information corresponding to the login information to determine the user's status in the preset business scenario, wherein the historical timestamp information is used to record the time information when the user has experienced the business process in the preset business scenario.

[0006] Furthermore, the step of detecting whether there is historical timestamp information corresponding to the login information to determine the user's user status in the preset business scenario includes: if historical timestamp information corresponding to the login information is detected, determining the user's user status in the preset business scenario as an experienced user; or, if historical timestamp information corresponding to the login information is not detected, determining the user's user status in the preset business scenario as an unexperienced user.

[0007] Furthermore, after determining that the user's status as an experienced user under the preset business scenario is a historical timestamp information corresponding to the login information is detected, the method further includes: if only one historical timestamp information corresponding to the login information is detected, obtaining the score of the experienced business process corresponding to the historical timestamp information; adjusting the allocation probability of the initial business node of the experienced business process based on the score of the experienced business process includes: determining the weight coefficient corresponding to the initial business node of the experienced business process based on the score of the experienced business process; and adjusting the allocation probability of the initial business node based on the weight coefficient. Through the above method, by adjusting the allocation probability of the initial business node of the business process based on the score of the experienced business process, users have a greater probability of experiencing business processes they have not yet experienced, thereby improving the user experience.

[0008] Furthermore, after determining that the user's status as an experienced user under the preset business scenario is a historical timestamp information corresponding to the login information, the method further includes: if multiple historical timestamp information corresponding to the login information is detected, obtaining multiple experienced business processes corresponding to the multiple historical timestamp information, wherein one historical timestamp information corresponds to one experienced business process; obtaining the score corresponding to each of the multiple experienced business processes to obtain multiple scores; adjusting the allocation probability of the initial business nodes of the experienced business processes based on the scores corresponding to the experienced business processes includes: determining the weight coefficient of the initial business nodes of each of the multiple experienced business processes based on the multiple scores; adjusting the allocation probability of the initial business nodes of each of the multiple experienced business processes based on the weight coefficient of the initial business nodes of each of the multiple experienced business processes. Through the above method, by adjusting the allocation probability of the initial business nodes of multiple experienced business processes based on the scores corresponding to each of the multiple experienced business processes, users have a greater probability of experiencing business processes they have not yet experienced, thereby improving the user experience.

[0009] Furthermore, determining the weight coefficient of the initial business node of each of the multiple experienced business processes based on the multiple scores includes: determining the average score of each of the multiple experienced business processes based on the multiple scores; and determining the weight coefficient of the initial business node of each of the multiple experienced business processes based on the average score.

[0010] Furthermore, if no historical timestamp information corresponding to the login information is detected, after determining that the user's user status in the preset business scenario is an inactive user, the process includes: if the user is determined to be an inactive user, initializing the allocation probability of the initial business nodes of each of the multiple business processes so that the probabilities of the initial business nodes of each of the multiple business processes are equal.

[0011] Furthermore, before obtaining the user's status in the preset business scenario, the process also includes: entering the preset business scenario in response to a login operation triggered by the user.

[0012] Secondly, this application provides a process adjustment device, comprising: a user status acquisition unit, a score acquisition unit, and a probability adjustment unit. The user status acquisition unit is used to acquire the user status in a preset business scenario, wherein the preset business scenario includes multiple business processes, each of which consists of multiple business nodes; the score acquisition unit is used to acquire, if the user is a user who has already experienced the process, the score corresponding to the business processes experienced by the user in the preset business scenario; the probability adjustment unit is used to adjust the allocation probability of the initial business nodes of the experienced business processes based on the scores corresponding to the experienced business processes.

[0013] Thirdly, embodiments of this application provide an electronic device, including one or more processors and a memory; one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the one or more processors, and the one or more programs are configured to perform the methods described above.

[0014] Fourthly, embodiments of this application provide a computer-readable storage medium storing program code, wherein the above-described method is executed when the program code is run.

[0015] This application provides a process adjustment method, apparatus, electronic device, and readable storage medium. The process adjustment method includes: first, obtaining the user's state in a preset business scenario; then, if the user is determined to be a user who has already experienced the service, obtaining the score corresponding to the business processes the user has already experienced in the preset business scenario; and adjusting the allocation probability of the initial business nodes of the already experienced business processes based on the scores of the already experienced business processes. Compared to randomly selecting the initial business nodes of a business process, this solution allows the user to have a greater probability of experiencing business processes they have not yet experienced, thereby improving the user experience. Attached Figure Description

[0016] To more clearly illustrate the technical solutions in the embodiments of this application, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0017] Figure 1 A flowchart of a process adjustment method according to an embodiment of this application is shown;

[0018] Figure 2 A flowchart of a process regulation method according to another embodiment of this application is shown;

[0019] Figure 3 This illustration shows a business process diagram of a process adjustment method according to another embodiment of this application;

[0020] Figure 4 A flowchart of a process adjustment method according to another embodiment of this application is shown;

[0021] Figure 5 A flowchart of a process adjustment method according to another embodiment of this application is shown;

[0022] Figure 6 This paper shows a structural block diagram of a process regulation method according to another embodiment of the present application;

[0023] Figure 7 This diagram illustrates a structural block diagram of an electronic device used to execute the process regulation method of the embodiments of this application in real time.

[0024] Figure 8 The present application shows a storage unit for storing or carrying program code that implements the process regulation method according to the embodiments of the present application. Detailed Implementation

[0025] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of this application.

[0026] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this application described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or server comprising a series of steps or units is not necessarily limited to those explicitly listed, but may include other steps or units not explicitly listed or inherent to these processes, methods, products, or devices.

[0027] During the human-machine interaction training, when a user enters a business process, the user randomly selects the business process through an electronic device. Then, within the business process, the electronic device selects a node in the business process through intent recognition.

[0028] The inventors discovered in their research on related process adjustment methods that, in general, electronic devices perform semantic understanding and intent recognition on the speaker's input speech, and then respond based on the intent recognition results. However, electronic devices may randomly provide users with a speech training process in the same scenario, which involves a great deal of randomness and may result in a user experiencing the same process multiple times, leading to a poor user experience.

[0029] Therefore, the inventors have proposed a process adjustment method, apparatus, electronic device, and storage medium in the embodiments of this application. First, the user's state in a preset business scenario is obtained. This preset business scenario includes multiple business processes, each consisting of at least one business node. If the user is a user who has already experienced the process, the scores corresponding to the business processes experienced by the user in the preset business scenario are obtained. Then, based on the scores corresponding to the experienced business processes, the allocation probability of the initial business nodes of the experienced business processes is adjusted. By adjusting the allocation probability of the initial business nodes of experienced business processes according to the scores corresponding to the business processes experienced by the user in the preset business scenario, compared to randomly selecting the initial business nodes of business processes, this solution allows users to have a greater probability of experiencing business processes they have not yet experienced, thereby improving the user experience.

[0030] The embodiments of this application will now be described in detail with reference to the accompanying drawings.

[0031] Please see Figure 1 This application provides a process adjustment method, the method comprising:

[0032] Step S110: Obtain the user status in a preset business scenario. The preset business scenario includes multiple business processes, and each business process consists of at least one business node.

[0033] In this embodiment, when a user login is detected in a preset business scenario, the user's status is obtained. The preset business scenario includes human-computer interaction scenarios and intelligent voice training scenarios, etc., and is not specifically limited here. In this preset business scenario, multiple business processes are pre-set by the administrator, and each business process consists of at least one business node. Each business process is preceded by a common starting node, which represents the node corresponding to when the electronic device responds to the user's operation and enters the preset business scenario. A business process represents the flow of business processing, and a business node represents a part of that process.

[0034] Step S120: If the user is a user who has already experienced the service, obtain the score corresponding to the service process that the user has experienced in the preset service scenario.

[0035] In this embodiment of the application, after obtaining the user's user status, if it is determined that the user's user status is "experienced user", it indicates that the user has experienced at least one of the multiple business processes included in the preset business scenario, and the score corresponding to the business process experienced by the user in the preset business scenario is obtained.

[0036] As one approach, when a user completes a business process, the electronic device determines that the user has already experienced it. At this point, the device retrieves the user's login information and adds a "completed" tag to that information. Experiencing multiple business processes does not increase the number of completed "completed" tags. When the user logs in again, the electronic device can directly determine the user's status as a "completed" user based on the completed "completed" tags included in the user's login information. The completed "completed" tag indicates that the user has already experienced a business process.

[0037] As one approach, within a business process, users can interact with electronic devices via voice. When a user speaks, the electronic device receives the voice and provides a corresponding voice response. Alternatively, users can interact with electronic devices via text. When a user inputs text, the electronic device receives the text and provides a corresponding text response. When a user experiences a business process, they need to interact with all the business nodes included in that process. Only after confirming the completion of interaction with a business node can they proceed to the next business node. After completing the interaction with the last business node in the process, the interaction with the business process is considered complete, and the electronic device marks the business process as experienced by the user. Simultaneously, when users experience the business process, they will interact with each business node in the process via voice. Since the preset business scenario is a human-machine interaction scenario, administrators have pre-set standard text for each business node. When a user interacts with any business node in the process via voice, the electronic device acquires the user's voice, converts it into text using Automatic Speech Recognition (ASR), and then converts the converted text into a structured representation that the electronic device can understand using Natural Language Understanding (NLU). Keywords are then extracted from the structured representation, and their similarity is compared with the standard text corresponding to that business node to determine the score for that business node. After obtaining the scores of all business nodes in the process, the scores for the entire process are summed to determine the overall score. For example, if a business process includes ten business nodes, the total score for each business node can be set to 10 points. The interaction information is used to represent the voice or text information generated during the interaction between the user and the electronic device. Obviously, if a business process includes only one business node, then the score corresponding to that business node can be directly used as the score of the business process.

[0038] Step S130: Based on the scores corresponding to the experienced business processes, adjust the allocation probability of the initial business nodes of the experienced business processes.

[0039] In this embodiment, after obtaining the score corresponding to the experienced business process, the allocation probability of the initial business node of the experienced business process is adjusted according to the obtained score. The initial business node represents the first business node when entering a business process, and the allocation probability represents the probability of selecting a business process when starting business processing.

[0040] As one approach, after a user completes a business process, the electronic device records the score and timestamp of that process, using this timestamp as historical timestamp information. When the user chooses to continue experiencing the business, the previously experienced process becomes a completed business process. This allows for dynamic adjustment of the initial node allocation probability of completed business processes based on the user's decision to continue.

[0041] As one approach, when a user enters the preset business scenario, they are at the initial node, not yet initiating business processing. Once the user begins processing, since multiple business processes exist within this scenario, the electronic device determines which process to select based on the probability of each process being assigned to an initial business node. Clearly, the higher the probability of an initial business node being assigned, the higher the probability of selecting the corresponding business process.

[0042] In one approach, the electronic device can adjust the allocation probability of the initial business node corresponding to the experienced business process based on the score level to which the experienced business process belongs. The electronic device pre-sets a first score threshold, a second score threshold, and a third score threshold, where the first score threshold is less than the second score threshold, the second score threshold is less than the third score threshold, the first score threshold is greater than 0, and the third score threshold is less than 100. The maximum score is set to 100, and the minimum score is 0. If the score corresponding to the experienced business process is determined to be greater than or equal to 0 and less than or equal to the first score threshold, the score is determined to belong to the first score level; if the score corresponding to the experienced business process is determined to be greater than the first score threshold and less than or equal to the second score threshold, the score is determined to belong to the second score level; if the score corresponding to the experienced business process is determined to be greater than the second score threshold and less than or equal to the third score threshold, the score is determined to belong to the third score level; and if the score corresponding to the experienced business process is determined to be greater than the third score threshold and less than or equal to 100, the score is determined to belong to the fourth score level. The electronic device is pre-set with probability adjustment values ​​corresponding to each score level. Since the score of a previously experienced business process reflects the user's understanding of that process, it can be determined that the higher the score, the greater the user's understanding. Therefore, the higher the score level, the larger the reduction in the allocation probability of the initial business node. Once the score level of a previously experienced business process is determined, the allocation probability of the initial business node is adjusted accordingly based on the probability adjustment value corresponding to that score level. For example, if the probability adjustment value is pre-set to +10% for the first score level, +5% for the second, -5% for the third, and -10% for the fourth, and the allocation probability of the initial business node of the previously experienced business process is 50%, and the score of the previously experienced business process belongs to the third score level, then the adjusted allocation probability of the initial business node can be determined to be 45%.

[0043] This application provides a process adjustment method. First, it obtains the user's state within a preset business scenario. This scenario includes multiple business processes, each consisting of at least one business node. If the user is determined to be an experienced user, the method obtains the scores corresponding to the business processes the user has already experienced within the preset scenario. Then, based on these scores, it adjusts the allocation probability of the initial business nodes for the experienced business processes. By adjusting the allocation probability of the initial business nodes for experienced business processes according to the user's scores within the preset scenario, this method allows users a greater probability of experiencing previously unexperienced business processes, thereby improving the user experience.

[0044] Please see Figure 2 This application provides a process adjustment method, the method comprising:

[0045] Step S210: In response to the login operation triggered by the user, enter the preset business scenario.

[0046] In this embodiment, when a user logs into an electronic device, the electronic device responds to the login operation triggered by the user and enters a preset business scenario. The login operation can be a user entering their account and password, SMS verification, or scanning a QR code, and is not specifically limited here.

[0047] Step S220: Obtain the user's login information under the preset business scenario.

[0048] In this embodiment, when a user enters a preset business scenario, the user needs to input login information on an electronic device. After the user inputs the login information and the electronic device successfully verifies the user's input login information, the electronic device obtains the user's corresponding login information. The login information is used to uniquely identify the user within the preset business scenario, and may include the user's account and phone number, etc., without specific limitations.

[0049] Step S230: Detect whether there is historical timestamp information corresponding to the login information to determine the user status of the user in the preset business scenario, wherein the historical timestamp information is used to record the time information when the user has experienced the business process in the preset business scenario.

[0050] In this embodiment, after obtaining the user's login information, the system queries the historical timestamp information corresponding to the login information in a preset storage area, and determines the user's status in a preset business scenario based on the historical event stamp information. The preset storage area can be the memory of an electronic device, a background manager, etc., and is not specifically limited here.

[0051] As one approach, after a user enters a preset business scenario and completes a business process, the experienced business process, its corresponding score, and its timestamp information are stored in a preset storage area. The timestamp information records the start and end times of the business process. When the user continues to experience business processes, the timestamp information corresponding to all previously experienced business processes is used as historical timestamp information.

[0052] Step S240: Based on whether historical timestamp information corresponding to the login information is detected, determine whether the user's user status is an experienced user. If yes, proceed to steps S250-S270; otherwise, proceed to steps S280-S290.

[0053] Step S250: If historical timestamp information corresponding to the login information is detected, determine that the user's user status in the preset business scenario is that of an experienced user.

[0054] In this embodiment of the application, if historical timestamp information corresponding to login information is detected in the preset storage area, it indicates that the user has previously experienced the business process under the preset business scenario, and the user status under the preset business scenario is determined to be an experienced user.

[0055] As one approach, electronic devices can determine whether to further determine the timestamp information of previously experienced business processes based on the presence or absence of filter tags. After a user completes a business process, the electronic device determines the score corresponding to that process and compares it to a pre-set score filter threshold. If the score is greater than or equal to the threshold, a filter tag is added; otherwise, it is not. When the electronic device checks historical timestamp information corresponding to login information, it first checks for filter tags on previously experienced business processes. If a filter tag is present, the timestamp information for those processes is determined; otherwise, the timestamp information for those processes is not retrieved. For example, in a preset storage area, there are three experienced business processes. Two of these processes have filter tags, while the third does not. When the electronic device performs detection, it only determines the historical timestamp information of the two experienced processes with filter tags, leaving the historical timestamp information of the third unmarked process undetermined. Therefore, although there are three experienced business processes, the electronic device determines that the user has experienced the service twice in this preset business scenario. When subsequently obtaining the scores for the experienced business processes, only the scores for the two processes with determined historical timestamp information are retrieved, excluding the score for the process without determined historical timestamp information. The score filtering threshold represents the threshold for determining the score of an experienced business process when it is marked with a filter tag, and the filter tag represents the tag used to determine whether the historical timestamp information of the experienced business process needs to be determined.

[0056] Step S260: If the user is determined to be a user who has already experienced the service, obtain the score corresponding to the service process that the user has experienced in the preset service scenario.

[0057] Step S270: Based on the scores corresponding to the experienced business processes, adjust the allocation probability of the initial business nodes of the experienced business processes.

[0058] Steps S260-S270 can be referred to in detail in the above embodiments, and therefore will not be repeated in this embodiment.

[0059] Step S280: If no historical timestamp information corresponding to the login information is detected, determine that the user's user status in the preset business scenario is an unexperienced user.

[0060] In this embodiment of the application, if no historical timestamp information corresponding to the login information is detected in the preset storage area, it indicates that the user has not experienced the business process under the preset business scenario before, and the user status under the preset business scenario is determined to be an unexperienced user.

[0061] Step S290: If the user is determined to be an unexperienced user, initialize the allocation probability of the initial business nodes of each of the multiple business processes so that the probability of the initial business nodes of each of the multiple business processes is equal.

[0062] In this embodiment, if a user's status in a preset business scenario is determined to be a "no-experience user," then it is determined that the user is using the service for the first time. Therefore, it is necessary to initialize the allocation probabilities of the initial business nodes corresponding to each of the multiple business processes. During the initialization process, the allocation probabilities of the initial business nodes are first normalized so that the sum of the allocation probabilities of the initial business nodes is 1. Then, the probabilities are evenly distributed according to the number of initial business nodes, ensuring that the probabilities of the initial business nodes corresponding to each of the multiple business processes are equal. For example, if there are five business processes, the allocation probabilities of the initial business nodes for each of the five business processes are first normalized, and then the probabilities are evenly distributed so that the probability of the initial business node corresponding to each business process is 20%.

[0063] As one approach, when a user needs to enter a preset service scenario, if the user has not used that scenario before, it means that the scenario does not store the user's login information. In this case, the user needs to register their login information to enter the preset service scenario. When the user chooses to register their login information, a registration signal is sent to the electronic device. The electronic device's response and receipt of the registration signal confirm that the user has not used that service scenario before, thus determining that the user is a non-user.

[0064] For example, steps S210-S290 can be as follows: Figure 3As shown, when an electronic device responds to a user's login operation and enters a preset business scenario, it is initially at node 0, and business processing has not yet begun. Within this preset business scenario, there are four business processes: Business Process A, Business Process B, Business Process C, and Business Process D. The initial business node for Business Processes A and B is node 1, and the initial business node for Business Processes C and D is node 2. When querying based on the user's login information, if Business Processes A, B, and D can be found, it can be determined that Business Processes A, B, and D are all experienced business processes, while Business Process C is an unexperienced business process.

[0065] This application provides a process adjustment method that first responds to a user-triggered login operation, enters a preset business scenario, obtains the user's login information within the preset business scenario, and then checks for historical timestamp information corresponding to the login information. If historical timestamp information is detected, the user is determined to be a user who has already experienced the service. The scores corresponding to the business processes experienced by the user within the preset business scenario are obtained, and the allocation probability of the initial business nodes of the experienced business processes is adjusted based on the scores. If no historical timestamp information is detected, the user is determined to be a user who has not yet experienced the service. The allocation probability of the initial business nodes of multiple business processes within the preset business scenario is then re-initialized to ensure that the probabilities of the initial business nodes of each business process are equal. By adjusting the allocation probability of the initial business nodes of experienced business processes based on the user's scores within the preset business scenario, compared to randomly selecting the initial business nodes, this solution allows users to have a greater probability of experiencing business processes they have not yet experienced, thereby improving the user experience.

[0066] Please see Figure 4 This application provides a process adjustment method, the method comprising:

[0067] Step S301: In response to the login operation triggered by the user, enter the preset business scenario.

[0068] Step S302: Obtain the user's login information under the preset business scenario.

[0069] Step S303: Detect whether there is historical timestamp information corresponding to the login information to determine the user status of the user in the preset business scenario, wherein the historical timestamp information is used to record the time information when the user has experienced the business process in the preset business scenario.

[0070] Step S304: If historical timestamp information corresponding to the login information is detected, determine that the user's user status in the preset business scenario is that of an experienced user.

[0071] Steps S301-S304 can be referred to the detailed explanation in the above embodiments, and therefore will not be repeated in this embodiment.

[0072] Step S305: Determine whether the detected historical timestamp information corresponding to the login information is one or multiple. If it is one, proceed to steps S306-S308; if it is multiple, proceed to steps S309-S312.

[0073] Step S306: If a historical timestamp corresponding to the login information is detected, obtain the score of the business process that has been experienced corresponding to the historical timestamp information.

[0074] In this embodiment of the application, when detecting a preset storage area, if a historical timestamp information corresponding to the login information is detected in the preset storage area, it indicates that the user has only experienced the service once before, that is, the number of service processes that have been experienced is one, and then the score of the experienced service process corresponding to the detected historical timestamp information is obtained.

[0075] Step S307: Based on the scores corresponding to the experienced business processes, determine the weight coefficients corresponding to the initial business nodes of the experienced business processes.

[0076] In this embodiment, once the score corresponding to a previously experienced business process is determined, the electronic device generates a weight coefficient corresponding to that business process based on a pre-set weight generation rule and the score. The weight generation rule characterizes the rules for generating the weight coefficients of the initial business nodes of the business process based on its score.

[0077] Step S308: Adjust the allocation probability of the initial service node based on the weight coefficient.

[0078] In this embodiment, after obtaining the weighting coefficient, the allocation probability of the initial business node of the experienced business process is adjusted according to the weighting coefficient. For example, if the weighting coefficient is 0.9 and the allocation probability of the initial business node of the experienced business process is 50%, then the adjusted allocation probability of the initial business node of the experienced business process can be set to 50% * 0.9, that is, the adjusted allocation probability is determined to be 45%. After adjusting the allocation probability of the initial business node of the experienced business process, the adjusted allocation probability of the initial business node is obtained. Since the probabilities of the initial business nodes of other unexperienced business processes have not been adjusted, the sum of the probabilities of all initial business nodes is less than 1. Therefore, it is necessary to normalize the adjusted allocation probability of the initial business node with the allocation probability of the initial business node of the unexperienced business process so that the sum of the probabilities of each business node is 1.

[0079] Step S309: If multiple historical timestamps are detected corresponding to the login information, obtain multiple experienced business processes corresponding to the multiple historical timestamps, wherein one historical timestamp corresponds to one experienced business process.

[0080] In this embodiment, if multiple historical timestamps corresponding to login information are detected in the preset storage area, it indicates that the user has previously experienced the service multiple times, and multiple experienced service processes are obtained based on the multiple historical timestamps. Each historical timestamp corresponds to one experienced service process, and multiple historical timestamps can correspond to the same experienced service process. For example, there may be five historical timestamps, where two correspond to service process A, one to service process B, one to service process C, and one to service process D.

[0081] Step S310: Obtain the scores corresponding to each of the multiple experienced business processes to obtain multiple scores.

[0082] In this embodiment, each experienced business process stored in a preset storage area records its corresponding historical timestamp information and score. When the electronic device detects that there are multiple historical timestamps corresponding to the login information and obtains the experienced business processes corresponding to these multiple historical timestamps, it obtains the scores corresponding to each of the multiple experienced business processes, thereby obtaining multiple scores.

[0083] Step S311: Based on the multiple scores, determine the weight coefficient of the initial business node for each of the multiple experienced business processes.

[0084] In this embodiment of the application, after obtaining multiple scores, the electronic device determines the weight coefficient of the initial business node of each of the multiple experienced business processes based on the scores of each of the multiple experienced business processes according to the pre-set weight generation rules.

[0085] One approach is to determine the weight coefficients of the initial business nodes for each of the multiple experienced business processes based on multiple scores. These weight coefficients can then be adjusted using the timestamp information of the experienced business processes. When designing business processes, administrators can pre-set the completion time for each process, limiting it to an experience time threshold. If the completion time exceeds this threshold, it indicates the user is unfamiliar with the process. After determining the weight coefficients of the initial business nodes for each of the multiple experienced business processes based on multiple scores, the start and end times of each process are determined using historical timestamp information. This determines the experience time for each process, and the weight coefficients of the initial business nodes are adjusted based on the comparison between the experience time and the preset experience time threshold. When the experience time of a previously experienced business process exceeds the experience time threshold, regardless of whether the score of the initial business node of that previously experienced business process is greater than or less than the score threshold, it indicates that the user may not be very familiar with the business process and needs to experience it multiple times. Therefore, the weight coefficient of the initial business node can be increased according to the first adjustment coefficient. When the experience time of a previously experienced business process is less than the experience time threshold, and the score of the initial business node of that previously experienced business process is greater than or equal to the preset score threshold, it indicates that the user is already quite familiar with the business process. The number of times the user experiences the business process can be reduced, while the number of times the user experiences other business processes can be increased. Therefore, the weight coefficient of the initial business node can be decreased according to the second adjustment coefficient. When the experience time of a previously experienced business process is less than the experience time threshold, and the score of the initial business node of that previously experienced business process is less than the preset score threshold, it indicates that the user is completely unfamiliar with the business process and needs to experience it multiple times. Therefore, the weight coefficient of the initial business node can be increased according to the first adjustment coefficient. If an initial business node involves multiple experienced business processes, the adjustment coefficients determined for each of the experienced business processes are multiplied together with the weight coefficient of the initial business node to obtain the final weight coefficient of the initial business node. Here, the experience time threshold represents the threshold time required to complete the business process when the weight coefficient of the initial business node needs to be increased by a preset adjustment coefficient; the score threshold represents the score threshold for the experienced business processes; the experience time represents the time required to experience the business process; the first adjustment coefficient represents the coefficient for increasing the weight coefficient; and the second adjustment coefficient represents the coefficient for decreasing the weight coefficient.

[0086] For example, consider three business processes that have already been experienced: Business Process A, Business Process B, and Business Process C. The initial business node for Business Processes A and B is Node 1, and the initial business node for Business Process C is Node 2. The first adjustment coefficient is 1.2, and the second adjustment coefficient is 0.8. The pre-set experience time threshold is 30 minutes, and the score threshold is 70 points. If Business Process A scores 80 points with a 45-minute experience time; Business Process B scores 85 points with a 20-minute experience time; and Business Process C scores 60 points with a 35-minute experience time, then Business Process A corresponds to the first adjustment coefficient, Business Process B to the second adjustment coefficient, and Business Process C to the first adjustment coefficient. If the weight coefficient of node 1 is determined to be 0.5 based on the scores of business process A and business process B respectively, and the weight coefficient of node 2 is determined to be 0.9 based on the score of business process C, after adjusting according to the first adjustment coefficient and the second adjustment coefficient, the final weight coefficient of node 1 can be determined to be 0.5*1.2*0.8, and the final weight coefficient of node 2 can be determined to be 0.9*1.2.

[0087] Step S312: Based on the weight coefficients of the initial business nodes of the multiple experienced business processes, adjust the allocation probability of the initial business nodes of the multiple experienced business processes.

[0088] In this embodiment, after obtaining the weight coefficients of the initial business nodes for each of the multiple experienced business processes, the allocation probabilities of the initial business nodes for each of the multiple experienced business processes are adjusted according to the weight coefficients. Since the allocation probabilities of the initial business nodes corresponding to the experienced business processes are multiplied by the weight coefficients under multiple initial business nodes in the preset scenario, while the allocation probabilities of the initial business nodes for the unexperienced business processes remain unchanged, the sum of the probabilities of all initial business nodes under the preset business scenario is not 1. Therefore, normalization processing can be applied to the probabilities of all initial business nodes to make the sum of the probabilities of all initial business nodes equal to 1. For example, in a preset business scenario, there are three initial business nodes: node 1, node 2, and node 3. Their weight coefficients are 0.2, 0.4, and 0.8, respectively, and their allocation probabilities are 40%, 40%, and 20%, respectively. Then, the allocation probabilities adjusted according to the weight coefficients are 0.2*40%, 0.4*40%, and 0.8*20%, which are 8%, 16%, and 16%, respectively. Then, the adjusted allocation probabilities are uniformized, resulting in the final allocation probabilities of node 1, node 2, and node 3 being 20%, 40%, and 40%, respectively.

[0089] As one approach, after adjusting the allocation probabilities of the initial business nodes of multiple experienced business processes based on their respective weight coefficients, the adjusted allocation probabilities can be further adjusted using the timestamp information of the experienced business processes. When designing business processes, managers can pre-set the completion time for each process, limiting the completion time to a threshold. If the completion time exceeds this threshold, it indicates the user is unfamiliar with the process. After adjusting the allocation probabilities of the initial business nodes of multiple experienced business processes based on their respective weight coefficients, the corresponding experience time for each process is determined using its historical timestamp information. This experience time is then compared to the experience time threshold, allowing for a further adjustment of the allocation probabilities of the initial business nodes for each process. If the experience time corresponding to a previously experienced business process is greater than or equal to the experience time threshold, it indicates that the user may be unfamiliar with the previously experienced business process. The adjustment allocation probability of the initial business node of the previously experienced business process can be increased according to the first adjustment coefficient. If the experience time corresponding to a previously experienced business process is less than the experience time threshold, it indicates that the user may be relatively familiar with the previously experienced business process. The adjustment allocation probability of the initial business node of the previously experienced business process can be decreased according to the second adjustment coefficient. If an initial business node involves multiple previously experienced business processes, the adjusted allocation probability of the initial business node is multiplied by the adjustment coefficients corresponding to each of the multiple previously experienced business processes to obtain the final allocation probability of the initial business node.

[0090] For example, consider three business processes that have already been experienced: Business Process A, Business Process B, and Business Process C. The initial business node for Business Process A and Business Process B is Node 1, and the initial business node for Business Process C is Node 2. The first adjustment coefficient is 1.2, the second adjustment coefficient is 0.8, and the pre-set experience time threshold is 30 minutes. If we determine that the experience time for Business Process A is 45 minutes, the experience time for Business Process B is 20 minutes, and the experience time for Business Process C is 35 minutes, then we can determine that Business Process A corresponds to the first adjustment coefficient, Business Process B corresponds to the second adjustment coefficient, and Business Process C corresponds to the first adjustment coefficient. If the adjustment allocation probability of node 1 is determined to be 70% and the adjustment allocation probability of node 2 is determined to be 30%, then the adjusted allocation probability of node 1 after adjustment is determined to be 70% * 1.2 * 0.8 and the adjusted allocation probability of node 2 after adjustment is determined to be 30% * 1.2. After determining the adjusted allocation probabilities of node 1 and node 2 respectively, the adjusted allocation probabilities of each node are normalized to obtain the target allocation probability of node 1 and the target allocation probability of node 2.

[0091] This application provides a process adjustment method. If only one historical timestamp is detected corresponding to login information, the method obtains the score of the experienced business process corresponding to that historical timestamp. Then, based on the score of the experienced business process, it determines the weight coefficient of the initial business node of that experienced business process and adjusts the allocation probability of the initial business node based on this weight coefficient. If multiple historical timestamps are detected corresponding to login information, the method obtains multiple experienced business processes corresponding to these multiple timestamps and their respective scores, resulting in multiple scores. Then, based on these multiple scores, it determines the weight coefficient of the initial business node of each of the multiple experienced business processes and adjusts the allocation probability of the initial business node based on this weight coefficient. By determining that the user is an experienced user in a preset business scenario, obtaining the score of the experienced business process in that scenario, and adjusting the allocation probability of the initial business node of the experienced business process based on this score, this solution allows users to experience business processes they have not yet experienced, thus improving the user experience, compared to randomly selecting the initial business node of a business process.

[0092] Please see Figure 5 This application provides a process adjustment method, the method comprising:

[0093] Step S401: In response to the login operation triggered by the user, enter the preset business scenario.

[0094] Step S402: Obtain the user's login information under the preset business scenario.

[0095] Step S403: Detect whether there is historical timestamp information corresponding to the login information to determine the user status of the user in the preset business scenario, wherein the historical timestamp information is used to record the time information when the user has experienced the business process in the preset business scenario.

[0096] Step S404: If historical timestamp information corresponding to the login information is detected, determine that the user's user status in the preset business scenario is that of an experienced user.

[0097] Step S405: Determine whether the detected historical timestamp information corresponding to the login information is one or multiple. If it is one, proceed to steps S406-S408; if it is multiple, proceed to steps S409-S412.

[0098] Step S406: If a historical timestamp corresponding to the login information is detected, obtain the score of the business process that has been experienced corresponding to the historical timestamp information.

[0099] Step S407: Based on the scores corresponding to the experienced business processes, determine the weight coefficients corresponding to the initial business nodes of the experienced business processes.

[0100] Step S408: Adjust the allocation probability of the initial service node based on the weight coefficient.

[0101] Step S409: If multiple historical timestamps are detected corresponding to the login information, obtain multiple experienced business processes corresponding to the multiple historical timestamps, wherein one historical timestamp corresponds to one experienced business process.

[0102] Step S410: Obtain the scores corresponding to each of the multiple experienced business processes to obtain multiple scores.

[0103] Steps S401-S410 can be referred to in detail in the above embodiments, and therefore will not be repeated in this embodiment.

[0104] Step S411: Based on the multiple scores, determine the average score of each of the multiple experienced business processes.

[0105] In this embodiment, after a business process has been experienced multiple times, it can have multiple scores. Once multiple scores are obtained, the business processes to which each score belongs are determined, thereby establishing the average score for each of the experienced business processes. For example, if an electronic device obtains five scores: 50, 80, 70, 90, and 70, and determines that 50 belongs to business process A, 80 and 70 both belong to business process B, and the remaining 90 and 70 belong to business process C, then the average score for business process A is determined to be 50, the average score for business process B to be 75, and the average score for business process C to be 80.

[0106] Step S412: Based on the average score, determine the weight coefficient of the initial business node for each of the multiple experienced business processes.

[0107] In this embodiment, after obtaining the average scores of multiple experienced business processes, the average scores are sorted sequentially by size to obtain a score sequence. The electronic device then determines the node score of the initial business node for each of the experienced business processes based on this score sequence, resulting in multiple node scores. The node score with the lowest score among these node scores is used as the benchmark score, and the initial business node corresponding to the benchmark score is used as the benchmark node. The other node scores are used as reference scores, and the initial business node corresponding to the reference scores is used as the reference node. The reference scores are subtracted from the benchmark scores to obtain a reference score difference, ensuring that each reference node corresponds to a reference score difference. Based on a pre-set weighting rule and the reference score difference for each reference node, a weight coefficient is determined for each reference node. The weight coefficient of the benchmark node is set to 1, thus determining the weight coefficients of the initial business nodes for each of the experienced business processes. A larger reference score difference results in a smaller generated weight coefficient, thus lowering the probability of the initial business node.

[0108] For example, there are five business processes: business process A, business process B, business process C, business process D, and business process E. The initial business node of business process A is node 1, the initial business node of business processes B and C is node 2, and the initial business node of business processes D and E is node 3. Simultaneously, the average score for business process A is determined to be 80, the average score for business process B is 70, the average score for business process C is 85, the average score for business process D is 95, and the average score for business process E is 50. Therefore, the score sequence is determined as [Business Process D: 95, Business Process C: 85, Business Process A: 80, Business Process B: 70, Business Process E: 50]. Based on this score sequence, the electronic device determines the node score for node 1 to be 75, the node score for node 2 to be 78, and the node score for node 3 to be 70. Since node 3 has the lowest node score, it is determined as the baseline node, and its node score is the baseline score. Nodes 1 and 2 are both reference nodes, with node 1 designated as the first reference node and node 2 as the second reference node. The node scores corresponding to each of nodes 1 and 2 are also reference scores, with the node score corresponding to node 1 designated as the first reference score and the node score corresponding to node 2 designated as the second reference score. Subtracting the first reference score from the benchmark score, the reference score difference for the first reference node is determined to be 5. Subtracting the second reference score from the benchmark score, the reference score difference for the second reference node is determined to be 8. Since the reference score difference for the second reference node is greater than that for the first reference node, the weight coefficient of the second reference node is determined to be less than that for the first reference node. According to the pre-set weight generation rules, the weight coefficients for the first and second reference nodes are generated based on the score differences for the first and second reference nodes. The weight coefficient for the first reference node is determined to be 0.7, i.e., the weight coefficient for node 1 is 0.7. The weight coefficient for the second reference node is determined to be 0.6, i.e., the weight coefficient for node 2 is 0.6. Simultaneously, the weight coefficient for the benchmark reference node is determined to be 1, i.e., the weight coefficient for node 3 is 1.

[0109] Step S413: Based on the weight coefficients of the initial business nodes of the multiple experienced business processes, adjust the allocation probability of the initial business nodes of the multiple experienced business processes.

[0110] Step S413 can be found in the detailed explanation in the above embodiments, and therefore will not be repeated in this embodiment.

[0111] This application provides a process adjustment method that, after determining the scores of multiple experienced business processes, determines the average score of each of the experienced business processes, and then determines the weight coefficient of the initial business node for each of the experienced business processes based on the average score. Based on this weight coefficient, the allocation probability of the initial business node for each of the experienced business processes is adjusted. By obtaining the scores of the experienced business processes in a given business scenario and adjusting the allocation probability of the initial business node based on these scores, this method, compared to randomly selecting the initial business node, gives users a greater probability of experiencing previously unexperienced business processes, thereby improving the user experience.

[0112] Please see Figure 6 This application provides a process adjustment device 500, which includes:

[0113] User status acquisition unit 510 is used to acquire the user status of a user in a preset business scenario. The preset business scenario includes multiple business processes, and each business process consists of at least one business node.

[0114] In one manner, the user status acquisition unit 510 is also used to acquire the user's login information in the preset business scenario; detect whether there is historical timestamp information corresponding to the login information, so as to determine the user status of the user in the preset business scenario, wherein the historical timestamp information is used to record the time information when the user has experienced the business process in the preset business scenario.

[0115] Optionally, the user status acquisition unit 510 is further configured to determine the user's status as an experienced user in the preset business scenario if historical timestamp information corresponding to the login information is detected; or, if no historical timestamp information corresponding to the login information is detected, determine the user's status as an unexperienced user in the preset business scenario.

[0116] Optionally, the user status acquisition unit 510 is also used to enter the preset business scenario in response to the login operation triggered by the user.

[0117] The scoring unit 520 is used to obtain the score corresponding to the business process that the user has experienced in the preset business scenario if the user is an experienced user.

[0118] In one manner, the scoring unit 520 is also used to obtain the score of the business process that has been experienced corresponding to the historical timestamp information if a historical timestamp information corresponding to the login information is detected.

[0119] Optionally, the score acquisition unit 520 is further configured to, if multiple historical timestamps corresponding to the login information are detected, acquire multiple experienced business processes corresponding to the multiple historical timestamps, wherein one historical timestamp corresponds to one experienced business process; and acquire the score corresponding to each of the multiple experienced business processes to obtain multiple scores.

[0120] The probability adjustment unit 530 is used to adjust the allocation probability of the initial business node of the experienced business process based on the score corresponding to the experienced business process.

[0121] In one manner, the probability adjustment unit 530 is also used to determine the weight coefficient corresponding to the initial business node of the experienced business process based on the score corresponding to the experienced business process; and to adjust the allocation probability of the initial business node based on the weight coefficient.

[0122] Optionally, the probability adjustment unit 530 is further configured to determine the weight coefficient of the initial business node of each of the multiple experienced business processes based on the multiple scores; and adjust the allocation probability of the initial business node of each of the multiple experienced business processes based on the weight coefficient of the initial business node of each of the multiple experienced business processes.

[0123] Optionally, the probability adjustment unit 530 is further configured to determine the average score of each of the multiple experienced business processes based on the multiple scores; and to determine the weight coefficient of the initial business node of each of the multiple experienced business processes based on the average score.

[0124] Optionally, the probability adjustment unit 530 is further configured to initialize the allocation probability of the initial business nodes of the multiple business processes if it is determined that the user is an unexperienced user, so as to make the probability of the initial business nodes of the multiple business processes equal.

[0125] It should be noted that the device embodiments in this application correspond to the aforementioned method embodiments. The specific principles in the device embodiments can be found in the content of the aforementioned method embodiments, and will not be repeated here.

[0126] The following will combine Figure 7 This application describes an electronic device.

[0127] Please see Figure 7Based on the aforementioned data processing methods and apparatus, this application also provides another electronic device 600 capable of executing the aforementioned data processing methods. The electronic device 600 includes one or more (only one shown in the figure) processors 602, a memory 604, and a network module 606 coupled together. The memory 604 stores programs capable of executing the contents of the aforementioned embodiments, and the processor 602 can execute the programs stored in the memory 604.

[0128] The processor 602 may include one or more processing cores. The processor 602 connects to various parts within the electronic device 600 using various interfaces and lines, and performs various functions and processes data by running or executing instructions, programs, code sets, or instruction sets stored in the memory 604, and by calling data stored in the memory 604. Optionally, the processor 602 may be implemented using at least one hardware form of Digital Signal Processing (DSP), Field-Programmable Gate Array (FPGA), or Programmable Logic Array (PLA). The processor 602 may integrate one or a combination of several of the following: Central Processing Unit (CPU), Graphics Processing Unit (GPU), and modem. The CPU primarily handles the operating system, user interface, and applications; the GPU is responsible for rendering and drawing the displayed content; and the modem handles wireless communication. It is understood that the modem may also not be integrated into the processor 602 and may be implemented separately using a communication chip.

[0129] The memory 604 may include random access memory (RAM) or read-only memory (ROM). The memory 604 can be used to store instructions, programs, code, code sets, or instruction sets. The memory 604 may include a program storage area and a data storage area. The program storage area may store instructions for implementing an operating system, instructions for implementing at least one function (such as touch functionality, sound playback functionality, image playback functionality, etc.), and instructions for implementing the various method embodiments described below. The data storage area may also store data created by the electronic device 600 during use (such as phonebook data, audio and video data, chat log data, etc.).

[0130] The network module 606 is used to receive and transmit electromagnetic waves, realizing the mutual conversion between electromagnetic waves and electrical signals, thereby communicating with communication networks or other devices, such as audio playback devices. The network module 606 may include various existing circuit elements for performing these functions, such as antennas, radio frequency transceivers, digital signal processors, encryption / decryption chips, user identity modules (SIM cards), memory, etc. The network module 606 can communicate with various networks such as the Internet, corporate intranets, and wireless networks, or communicate with other devices through wireless networks. The aforementioned wireless networks may include cellular telephone networks, wireless local area networks (WLANs), or metropolitan area networks (MANs). For example, the network module 606 can interact with base stations.

[0131] Please refer to Figure 8 This diagram illustrates a structural block diagram of a computer-readable storage medium provided in an embodiment of this application. The computer-readable storage medium 700 stores program code that can be called by a processor to execute the methods described in the above method embodiments.

[0132] The computer-readable storage medium 700 may be an electronic memory such as flash memory, EEPROM (Electrically Erasable Programmable Read-Only Memory), EPROM, hard disk, or ROM. Optionally, the computer-readable storage medium 700 includes a non-transitory computer-readable storage medium. The computer-readable storage medium 700 has storage space for program code 710 that performs any of the method steps described above. This program code can be read from or written to one or more computer program products. The program code 710 may, for example, be compressed in a suitable form.

[0133] This application provides a process adjustment method, apparatus, electronic device, and storage medium. The process adjustment method includes: obtaining a user's state in a preset business scenario, where the preset business scenario includes multiple business processes, each business process consisting of multiple business nodes; if the user is a user who has already experienced the process, obtaining the score corresponding to the business processes the user has already experienced in the preset business scenario; and adjusting the allocation probability of the initial business nodes of the experienced business processes based on the scores corresponding to the experienced business processes. By adjusting the allocation probability of the initial business nodes of experienced business processes according to the scores corresponding to the business processes the user has already experienced in the preset business scenario, compared to randomly selecting the initial business nodes of business processes, this solution allows users to have a greater probability of experiencing business processes they have not yet experienced, thereby improving the user experience.

[0134] The embodiments of the present invention have been described above with reference to the accompanying drawings. However, the present invention is not limited to the specific embodiments described above. The specific embodiments described above are merely illustrative and not restrictive. Those skilled in the art can make many other forms under the guidance of the present invention without departing from the spirit and scope of the claims, and all of these forms are within the protection scope of the present invention.

Claims

1. A process adjustment method characterized by, The method comprises: acquiring a user state of a user in a preset business scenario, wherein the preset business scenario comprises a plurality of business processes, and each of the business processes is composed of at least one business node; if it is determined that the user is an experienced user, acquiring a score corresponding to a business process experienced by the user in the preset business scenario, wherein the score corresponding to the business process comprises scores of all business nodes of the business process, and the score of each business node is determined based on a similarity between a voice input by the user in the business node and a standard text corresponding to the business node; based on the score corresponding to the experienced business process, adjusting a distribution probability of an initial business node of the experienced business process, wherein the distribution probability of the initial business node of the experienced business process is adjusted based on a score level to which the score corresponding to the experienced business process belongs, and the distribution probability of the initial business node of the experienced business process is adjusted according to a probability adjustment value corresponding to the score level.

2. The method of claim 1, wherein, The acquiring of the user state of the user in the preset business scenario comprises: acquiring login information of the user in the preset business scenario; detecting whether there is historical timestamp information corresponding to the login information to determine the user state of the user in the preset business scenario, wherein the historical timestamp information is used to record time information of a business process experienced by the user in the preset business scenario.

3. The method of claim 2, wherein, The detecting of whether there is historical timestamp information corresponding to the login information to determine the user state of the user in the preset business scenario comprises: if it is detected that there is historical timestamp information corresponding to the login information, determining that the user state of the user in the preset business scenario is that of an experienced user; or if it is detected that there is no historical timestamp information corresponding to the login information, determining that the user state of the user in the preset business scenario is that of an inexperienced user.

4. The method of claim 3, wherein, The method further comprises: if it is detected that there is one piece of historical timestamp information corresponding to the login information, acquiring a score of a business process corresponding to the historical timestamp information; The adjusting of the distribution probability of the initial business node of the experienced business process based on the score corresponding to the experienced business process comprises: based on the score corresponding to the experienced business process, determining a weight coefficient corresponding to the initial business node of the experienced business process; and based on the weight coefficient, adjusting the distribution probability of the initial business node.

5. The method of claim 3, wherein, The method further comprises: if it is detected that there are a plurality of pieces of historical timestamp information corresponding to the login information, acquiring a plurality of experienced business processes corresponding to the plurality of pieces of historical timestamp information, wherein one piece of historical timestamp information corresponds to one experienced business process. obtaining scores corresponding to the experienced business processes respectively, to obtain a plurality of scores; adjusting the allocation probability of the initial business node of the experienced business process based on the scores corresponding to the experienced business process, comprising: determining a weight coefficient of the initial business node of each of the experienced business processes based on the plurality of scores; adjusting the allocation probability of the initial business node of each of the experienced business processes based on the weight coefficient of the initial business node of each of the experienced business processes.

6. The method of claim 5, wherein, determining a weight coefficient of the initial business node of each of the experienced business processes based on the plurality of scores, comprising: determining a score mean of each of the experienced business processes based on the plurality of scores; determining a weight coefficient of the initial business node of each of the experienced business processes based on the score mean.

7. The method of claim 3, wherein, if it is detected that there is no historical timestamp information corresponding to the login information, determining that the user state of the user in the preset business scenario is an inexperienced user, and then comprising: if it is determined that the user is an inexperienced user, initializing the allocation probability of the initial business node of each of the business processes, so that the probabilities of the initial business nodes of the business processes are equal.

8. The method of claim 1, wherein, before the user state of the user in the preset business scenario is obtained, further comprising: in response to a login operation triggered by the user, entering the preset business scenario.

9. A flow regulating device, characterized by The apparatus comprises: a user state obtaining unit configured to obtain a user state of a user in a preset business scenario, the preset business scenario comprising a plurality of business processes, each of the business processes comprising at least one business node; a score obtaining unit configured to, if the user is an experienced user, obtain scores corresponding to business processes experienced by the user in the preset business scenario, the scores corresponding to the business processes comprising scores of all business nodes of the business processes, each of the scores of the business nodes being determined based on a similarity between a voice input by the user in the business node and a standard text corresponding to the business node; a probability adjusting unit configured to adjust an allocation probability of an initial business node of the experienced business process based on the scores corresponding to the experienced business process, the allocation probability of the initial business node of the experienced business process being adjusted based on a score level to which the scores corresponding to the experienced business process belong, and the allocation probability of the initial business node of the experienced business process being adjusted according to a probability adjustment value corresponding to the score level.

10. An electronic device, comprising: one or more processors and a memory, one or more programs stored in the memory and configured to be executed by the one or more processors to perform the method of any one of claims 1-8.

11. A computer readable storage medium, characterized in that, The computer-readable storage medium stores program code, and the program code comprises instructions for performing the method of any one of claims 1-8.

Images