Artificial intelligence customer service management method and system based on enterprise knowledge base

Abstract

The invention is suitable for the technical field of artificial intelligence customer service, and provides an artificial intelligence customer service management method and system based on an enterprise knowledge base. The method comprises the following steps: updating and obtaining an actual live broadcast customer service video, carrying out entry identification, exit identification and time period judgment, and intercepting a plurality of live broadcast standard segment videos; commodity recognition and voice recognition are carried out on the multiple live broadcast standard video segments, and an enterprise knowledge base is updated and constructed; receiving a virtual customer service task, and performing sequential virtual customer service live broadcast; obtaining user interaction information, and selecting a required standard segment video; and inserting virtual customer service live broadcast into the required standard segment video. A plurality of live broadcast standard segment videos can be intercepted from an actual live broadcast customer service video, an enterprise knowledge base is updated and constructed, virtual customer service tasks are received, sequential virtual customer service live broadcast is performed, user interaction information is acquired, and a required standard segment video is selected to insert virtual customer service live broadcast, so that the virtual customer service live broadcast is performed on the basis of the actual live broadcast customer service video. And more immersive and vivid video customer service is carried out.

Description

Technical Field

[0001] The present invention belongs to the technical field of artificial intelligence customer service, and in particular, relates to an artificial intelligence customer service management method and system based on an enterprise knowledge base. Background Art

[0002] Artificial intelligence customer service uses artificial intelligence technology to simulate human customer service representatives to provide users with automated services. Through text chat, voice dialogue and other methods, it understands user needs and provides information query, problem answering, business processing, product recommendation and other services. Artificial intelligence customer service has shown great value in improving service efficiency, reducing costs, and improving user experience. It is widely used in many industries such as banking, telecommunications, e-commerce, medical care, and education.

[0003] In the existing technology, artificial intelligence customer service can usually only realize text communication and voice communication. However, with the rapid development of short videos and live broadcasts, video live broadcast customer service also has broad prospects. The existing video live broadcast customer service only conducts simple communication through AI images, which is essentially another manifestation of voice communication customer service and cannot provide more immersive and vivid video customer service. Summary of the invention

[0004] The purpose of the embodiments of the present invention is to provide an artificial intelligence customer service management method and system based on an enterprise knowledge base, aiming to solve the technical problems existing in the prior art mentioned in the background technology.

[0005] The embodiment of the present invention is implemented as follows:

[0006] An artificial intelligence customer service management method based on an enterprise knowledge base, the method specifically comprising the following steps:

[0007] Periodically update and obtain the actual live customer service video, perform entry identification, exit identification and time period judgment, and intercept multiple live standard segment videos from the actual live customer service video;

[0008] Perform product recognition and voice recognition on a plurality of live standard segment videos, record a plurality of corresponding standard segment annotation information, and update and construct an enterprise knowledge base;

[0009] receiving a virtual customer service task, selecting a plurality of relevant standard segment videos and corresponding relevant annotation information from the enterprise knowledge base, and sequentially performing virtual customer service live broadcasts on the plurality of relevant standard segment videos;

[0010] Based on artificial intelligence technology, live broadcast interaction guidance is carried out to obtain user interaction information, and based on multiple related annotation information, required video matching is carried out to select required standard segment videos;

[0011] Plan the demand insertion time, and insert the demand standard segment video into the virtual customer service live broadcast at the demand insertion time.

[0012] As a further limitation of the technical solution of the embodiment of the present invention, the periodic updating and obtaining of the actual live customer service video, performing entry identification, exit identification and time period judgment, and intercepting multiple live standard segment videos from the actual live customer service video specifically include the following steps:

[0013] According to the preset live broadcast update cycle, the actual live customer service video is periodically obtained;

[0014] Extracting an initialization segment video from the actual live customer service video;

[0015] Perform customer service facial recognition on the initialization video segment to obtain customer service facial feature data;

[0016] Processing the initialization segment video frame by frame to obtain multiple initialization frame images;

[0017] According to the customer service facial feature data, feature matching and image elimination are performed on the multiple initialization frame images to obtain an actual live broadcast background image;

[0018] According to the actual live broadcast background image, entry recognition, exit recognition and time period judgment are performed on the actual live broadcast customer service video, and multiple live broadcast standard segment videos are intercepted.

[0019] As a further limitation of the technical solution of the embodiment of the present invention, the step of performing entry recognition, exit recognition and time period judgment on the actual live customer service video according to the actual live background image, and intercepting multiple live standard segment videos specifically includes the following steps:

[0020] According to the actual live broadcast background image, the actual live broadcast customer service video is identified for entry and exit, and multiple customer service entry times and multiple customer service exit times are recorded;

[0021] Determine a plurality of corresponding customer service presence time periods according to the plurality of customer service entry times and the plurality of customer service exit times;

[0022] comparing the plurality of customer service presence periods with a preset standard presence period;

[0023] Selecting a plurality of qualified presence time periods from the plurality of customer service presence time periods;

[0024] According to the multiple qualified presence time periods, multiple live standard segment videos are captured from the actual live customer service video.

[0025] As a further limitation of the technical solution of the embodiment of the present invention, the performing of commodity recognition and voice recognition on the plurality of live standard segment videos, recording a plurality of corresponding standard segment annotation information, and updating and constructing the enterprise knowledge base specifically comprises the following steps:

[0026] According to a preset commodity database, commodity identification is performed on the plurality of live standard segment videos, and a plurality of corresponding commodity segment annotation information is recorded;

[0027] Performing voice recognition on a plurality of live standard segment videos, and recording a plurality of corresponding voice segment annotation information;

[0028] Comprehensively sorting out the plurality of commodity segment annotation information and the plurality of voice segment annotation information to generate a plurality of comprehensive segment annotation information;

[0029] Performing key identification and information screening on the plurality of comprehensive segment annotation information to generate a plurality of standard segment annotation information;

[0030] According to the plurality of live standard segment videos and corresponding standard segment annotation information, the enterprise knowledge base is updated and constructed.

[0031] As a further limitation of the technical solution of the embodiment of the present invention, the updating and constructing of the enterprise knowledge base according to the plurality of live standard segment videos and the corresponding standard segment annotation information specifically comprises the following steps:

[0032] Based on the enterprise knowledge base before updating, the plurality of standard segment annotation information are classified and identified to divide the plurality of existing segment annotation information into a plurality of existing segment annotation information and a plurality of unavailable segment annotation information;

[0033] According to the plurality of existing segment annotation information and the plurality of non-existing segment annotation information, the plurality of live standard segment videos are classified into a plurality of existing standard segment videos and a plurality of non-existing standard segment videos;

[0034] Updating the enterprise knowledge base according to the plurality of existing standard segment videos;

[0035] The enterprise knowledge base is supplemented and updated based on the plurality of non-standard segment videos.

[0036] As a further limitation of the technical solution of the embodiment of the present invention, the receiving of the virtual customer service task, selecting a plurality of relevant standard segment videos and corresponding relevant annotation information from the enterprise knowledge base, and sequentially performing virtual customer service live broadcasts on the plurality of relevant standard segment videos specifically include the following steps:

[0037] Receive virtual customer service tasks;

[0038] Identify the virtual customer service task, and determine a plurality of customer service display commodities and a plurality of customer service display items;

[0039] According to the plurality of customer service products displayed, a plurality of relevant standard segment videos and corresponding relevant annotation information are selected from the enterprise knowledge base;

[0040] According to the plurality of customer service display projects, screening a plurality of project standard segment videos from the plurality of related standard segment videos;

[0041] Plan the customer service live broadcast sequence of multiple standard segment videos of the project;

[0042] According to the customer service live broadcast sequence, a virtual customer service live broadcast is performed on a plurality of the project standard segment videos.

[0043] As a further limitation of the technical solution of the embodiment of the present invention, the live interactive guidance based on artificial intelligence technology, obtaining user interaction information, matching the required videos based on the multiple related annotation information, and selecting the required standard segment videos specifically include the following steps:

[0044] Based on artificial intelligence technology, conduct interactive guidance for live broadcasts;

[0045] Get user interaction information in real time;

[0046] Performing key identification on the user interaction information and extracting key interaction information;

[0047] According to the interactive key information, matching target annotation information from a plurality of related annotation information;

[0048] According to the target annotation information, a corresponding required standard segment video is selected from a plurality of related standard segment videos.

[0049] As a further limitation of the technical solution of the embodiment of the present invention, the planning of the demand insertion time and inserting the demand standard segment video into the virtual customer service live broadcast at the demand insertion time specifically include the following steps:

[0050] Based on the customer service live broadcast sequence, perform sequence positioning to determine the current live broadcast sequence;

[0051] According to the current live broadcast sequence, plan the required insertion time;

[0052] Creating a demand insertion task according to the demand insertion time;

[0053] Insert tasks according to the requirements and insert the required standard segment video to conduct virtual customer service live broadcast.

[0054] An artificial intelligence customer service management system based on an enterprise knowledge base, the system comprises an actual live broadcast processing module, a live broadcast video recognition module, a sequential virtual live broadcast module, a demand video matching module and an inserted virtual live broadcast module, wherein:

[0055] The actual live broadcast processing module is used to periodically update and obtain the actual live broadcast customer service video, perform entry recognition, exit recognition and time period judgment, and intercept multiple live broadcast standard segment videos from the actual live broadcast customer service video;

[0056] A live video recognition module, used to perform commodity recognition and voice recognition on a plurality of live standard segment videos, record a plurality of corresponding standard segment annotation information, and update and construct an enterprise knowledge base;

[0057] A sequential virtual live broadcast module is used to receive a virtual customer service task, select a plurality of relevant standard segment videos and corresponding relevant annotation information from the enterprise knowledge base, and perform sequential virtual customer service live broadcast on the plurality of relevant standard segment videos;

[0058] A demand video matching module is used to guide live broadcast interaction based on artificial intelligence technology, obtain user interaction information, match demand videos based on multiple related annotation information, and select demand standard segment videos;

[0059] The virtual live broadcast module is inserted to plan the demand insertion time, and at the demand insertion time, the demand standard segment video is inserted into the virtual customer service live broadcast.

[0060] As a further limitation of the technical solution of the embodiment of the present invention, the actual live broadcast processing module specifically includes:

[0061] A video acquisition unit, used to periodically acquire actual live customer service videos according to a preset live update cycle;

[0062] A segment video extraction unit, used to extract an initialization segment video from the actual live customer service video;

[0063] A facial recognition unit, used to perform customer service facial recognition on the initialization video segment to obtain customer service facial feature data;

[0064] A frame-by-frame processing unit, used to process the initialization segment video frame by frame to obtain a plurality of initialization frame images;

[0065] A background acquisition unit, configured to perform feature matching and image elimination on the plurality of initialization frame images according to the customer service facial feature data, to acquire an actual live broadcast background image;

[0066] The video segment capture unit is used to perform entry recognition, exit recognition and time period judgment on the actual live customer service video according to the actual live background image, and capture multiple live standard video segments.

[0067] Compared with the prior art, the present invention has the following beneficial effects:

[0068] The embodiment of the present invention updates and obtains the actual live customer service video, performs entry identification, exit identification and time period judgment, intercepts multiple live standard segment videos; performs commodity identification and voice recognition on multiple live standard segment videos, updates and builds the enterprise knowledge base; receives virtual customer service tasks, performs sequential virtual customer service live broadcasts; obtains user interaction information, selects required standard segment videos; and inserts required standard segment videos into virtual customer service live broadcasts. It is possible to intercept multiple live standard segment videos from the actual live customer service video, update and build the enterprise knowledge base, receive virtual customer service tasks, perform sequential virtual customer service live broadcasts, obtain user interaction information, select required standard segment videos to insert into virtual customer service live broadcasts, thereby providing more immersive and vivid video customer service services based on the actual live customer service video. BRIEF DESCRIPTION OF THE DRAWINGS

[0069] Figure 1 A flowchart of an artificial intelligence customer service management method based on an enterprise knowledge base provided by an embodiment of the present invention is shown;

[0070] Figure 2 A flowchart showing actual live customer service video processing in the method provided by an embodiment of the present invention is shown;

[0071] Figure 3 A flowchart of intercepting a live standard segment video in a method provided by an embodiment of the present invention is shown;

[0072] Figure 4 A flowchart of live standard segment video recognition in the method provided by an embodiment of the present invention is shown;

[0073] Figure 5 A flowchart of updating and constructing an enterprise knowledge base in a method provided by an embodiment of the present invention is shown;

[0074] Figure 6 It shows a flowchart of sequential virtual customer service live broadcast in the method provided by an embodiment of the present invention;

[0075] Figure 7 A flowchart of performing demand video matching in a method provided by an embodiment of the present invention is shown;

[0076] Figure 8 A flowchart of inserting a virtual customer service live broadcast in a method provided by an embodiment of the present invention is shown;

[0077] Fig. 9 An application architecture diagram of an artificial intelligence customer service management system based on an enterprise knowledge base provided by an embodiment of the present invention is shown;

[0078] Fig.10 The application architecture diagram of the actual live broadcast processing module in the system provided by an embodiment of the present invention is shown. DETAILED DESCRIPTION

[0079] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention 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 invention and are not intended to limit the present invention.

[0080] It is understandable that artificial intelligence customer service has broad application prospects. In the existing technology, artificial intelligence customer service can usually only realize text communication and voice communication. However, with the rapid development of short videos and live broadcasts, video live broadcast customer service also has broad prospects. The existing video live broadcast customer service only conducts simple communication through AI images, which is essentially another manifestation of voice communication customer service and cannot provide more immersive and vivid video customer service.

[0081] To solve the above problems, an artificial intelligence customer service management method and system based on an enterprise knowledge base disclosed in an embodiment of the present invention obtains actual live customer service videos through periodic updates, performs entry identification, exit identification and time period judgment, and intercepts multiple live standard segment videos from the actual live customer service videos; performs commodity identification and voice recognition on multiple live standard segment videos, records multiple corresponding standard segment annotation information, and updates and builds an enterprise knowledge base; receives virtual customer service tasks, screens multiple relevant standard segment videos and corresponding relevant annotation information from the enterprise knowledge base, and performs sequential virtual customer service live broadcasts on multiple relevant standard segment videos; based on artificial intelligence technology, conducts live interactive guidance, obtains user interaction information, performs demand video matching based on multiple relevant annotation information, and selects demand standard segment videos; plans demand insertion time, and inserts virtual customer service live broadcasts into demand standard segment videos at the demand insertion time. It is possible to intercept multiple live standard segment videos from the actual live customer service videos, update and build an enterprise knowledge base, receive virtual customer service tasks, perform sequential virtual customer service live broadcasts, obtain user interaction information, and select demand standard segment videos to insert into virtual customer service live broadcasts, thereby providing more immersive and vivid video customer service based on actual live customer service videos.

[0082] Specifically, Figure 1 A flow chart of an artificial intelligence customer service management method based on an enterprise knowledge base provided in an embodiment of the present invention is shown.

[0083] In a preferred embodiment of the present invention, an artificial intelligence customer service management method based on an enterprise knowledge base comprises the following steps:

[0084] Step S101, periodically update and obtain the actual live customer service video, perform entry identification, exit identification and time period judgment, and capture multiple live standard segment videos from the actual live customer service video.

[0085] In an embodiment of the present invention, live broadcast recording is performed during the actual live broadcast process. According to a preset live broadcast update cycle, the recorded actual live customer service video is periodically obtained. Then, according to a preset initialization period, an initialization segment video is extracted from the actual live customer service video. By dynamically identifying the initialization segment video, the live customer service performing the actual live broadcast is determined, and the model model, poster model, etc. in the initialization segment video are eliminated. Then, customer service facial recognition is performed on the live customer service performing the actual live broadcast to obtain customer service facial feature data, and then the initialization segment video is processed frame by frame to obtain multiple initialization frame images. According to the multiple customer service facial feature data, the initialization frame image with live customer service is identified and eliminated from the multiple initialization frame images, and then the initialization frame image with live customer service is eliminated from the remaining multiple initialization frame images. Among the initialization frame images, the clearest initialization frame image is selected and marked as the actual live broadcast background image. With the actual live broadcast background image as a reference, entry and exit identification is performed on the actual live customer service video, and multiple customer service entry times and multiple customer service exit times of the live customer service in the actual live customer service video are recorded. According to the multiple customer service entry times and the multiple corresponding customer service exit times, multiple corresponding customer service presence time periods are determined, and then the multiple customer service presence time periods are compared with the preset standard presence time periods, and the customer service presence time periods that are shorter than the standard presence time periods are marked as qualified presence time periods, thereby screening and obtaining multiple qualified presence time periods, and then according to the multiple qualified presence time periods, multiple corresponding live standard segment videos are intercepted from the actual live customer service video.

[0086] It is understandable that a live broadcast test is required during the initialization period of the actual live broadcast, and the initialization period for each live broadcast test can be set consistently; the initialization period is the length of time for the live broadcast test, which is determined by the test start time and the test end time.

[0087] It can be understood that entry recognition and exit recognition are the recognition of the picture with only the actual live background image in the actual live customer service video, so as to determine multiple customer service entry times and multiple customer service exit times. Specifically: when the picture with only the actual live background image is recognized for the first time in the actual live customer service video, the last time with only the actual live background image is recorded, and determined as the customer service entry time; when the picture with only the actual live background image is recognized for the second time in the actual live customer service video, the start time with only the actual live background image is recorded, and determined as the customer service exit time; when the picture with only the actual live background image is recognized for the third time in the actual live customer service video, the last time with only the actual live background image is recorded, and determined as the customer service entry time; ...; alternately in this way, multiple customer service entry times and multiple customer service exit times are determined.

[0088] Specifically, Figure 2 A flowchart of actual live customer service video processing in the method provided by an embodiment of the present invention is shown.

[0089] Among them, in the preferred embodiment provided by the present invention, the periodic update of obtaining the actual live customer service video, performing entry identification, exit identification and time period judgment, and intercepting multiple live standard segment videos from the actual live customer service video specifically includes the following steps:

[0090] Step S1011: periodically obtain the actual live customer service video according to the preset live update cycle.

[0091] Step S1012: extracting an initialization segment video from the actual live customer service video.

[0092] Step S1013: Perform customer service facial recognition on the initialization video segment to obtain customer service facial feature data.

[0093] Step S1014: Process the initialization segment video frame by frame to obtain a plurality of initialization frame images.

[0094] Step S1015: perform feature matching and image elimination on the multiple initialization frame images according to the customer service facial feature data to obtain an actual live broadcast background image.

[0095] Step S1016: according to the actual live broadcast background image, perform entry recognition, exit recognition and time period judgment on the actual live broadcast customer service video, and capture multiple live broadcast standard segment videos.

[0096] Specifically, Figure 3 A flow chart of capturing live standard segment video in the method provided by an embodiment of the present invention is shown.

[0097] Among them, in the preferred implementation mode provided by the present invention, the actual live customer service video is subjected to entry recognition, exit recognition and time period judgment according to the actual live background image, and the multiple live standard segment videos are intercepted, which specifically includes the following steps:

[0098] Step S10161: perform entry and exit recognition on the actual live customer service video according to the actual live background image, and record multiple customer service entry times and multiple customer service exit times.

[0099] Step S10162: Determine a plurality of corresponding customer service presence time periods according to the plurality of customer service entry times and the plurality of customer service exit times.

[0100] Step S10163: compare the plurality of customer service presence time periods with a preset standard presence time period.

[0101] Step S10164: Filter multiple qualified presence time periods from the multiple customer service presence time periods.

[0102] Step S10165: According to the multiple qualified presence time periods, a plurality of live standard segment videos are captured from the actual live customer service video.

[0103] Furthermore, the artificial intelligence customer service management method based on the enterprise knowledge base also includes the following steps:

[0104] Step S102: perform product recognition and voice recognition on the plurality of live standard segment videos, record a plurality of corresponding standard segment annotation information, and update and construct an enterprise knowledge base.

[0105] In an embodiment of the present invention, according to a preset commodity database, commodity identification is performed on multiple live standard segment videos, and multiple corresponding commodity segment annotation information is recorded. Then, voice recognition of live customer service is performed on multiple live standard segment videos, and multiple corresponding voice segment annotation information is recorded. According to a preset annotation information sorting format, multiple commodity segment annotation information and multiple corresponding voice segment annotation information are comprehensively sorted to generate multiple comprehensive segment annotation information. Then, key identification is performed on the multiple comprehensive segment annotation information, and non-key information irrelevant to the commodity is eliminated. Multiple standard segment annotation information is screened from the multiple comprehensive segment annotation information to generate multiple standard segment annotation information. Based on the enterprise knowledge base before updating, relevant matching is performed on the multiple standard segment annotation information, and according to the relevant matching results, multiple standard The segment annotation information is classified and marked into multiple existing segment annotation information and multiple non-segment annotation information, and the live standard segment videos corresponding to the multiple existing segment annotation information are marked as existing standard segment videos, and the live standard segment videos corresponding to the multiple non-segment annotation information are marked as non-standard segment videos, thereby classifying the multiple live standard segment videos into multiple existing standard segment videos and multiple non-standard segment videos, and then according to the multiple existing standard segment videos and the multiple existing segment annotation information, the corresponding segment videos and annotation information in the enterprise knowledge base are replaced to realize the upgrade and update of the enterprise knowledge base. At the same time, according to the multiple non-standard segment videos and the multiple non-segment annotation information, the segment videos and annotation information are supplemented to the enterprise knowledge base to realize the supplement and update of the enterprise knowledge base.

[0106] It is understandable that the product segment annotation information includes product name, product style, product number and product brand, etc.

[0107] Specifically, Figure 4 A flow chart of live standard segment video recognition in the method provided by an embodiment of the present invention is shown.

[0108] Among them, in the preferred embodiment provided by the present invention, the performing of commodity recognition and voice recognition on a plurality of live standard segment videos, recording a plurality of corresponding standard segment annotation information, and updating and constructing an enterprise knowledge base specifically comprises the following steps:

[0109] Step S1021: According to a preset product database, the products are identified for the plurality of live standard segment videos, and a plurality of corresponding product segment annotation information is recorded.

[0110] Step S1022: perform voice recognition on the plurality of live standard segment videos, and record a plurality of corresponding voice segment annotation information.

[0111] Step S1023: Comprehensively organize the plurality of product segment annotation information and the plurality of voice segment annotation information to generate a plurality of comprehensive segment annotation information.

[0112] Step S1024: perform key identification and information screening on the multiple comprehensive segment annotation information to generate multiple standard segment annotation information.

[0113] Step S1025: update and construct the enterprise knowledge base according to the plurality of live standard segment videos and corresponding standard segment annotation information.

[0114] Specifically, Figure 5 A flow chart of updating and constructing an enterprise knowledge base in the method provided by an embodiment of the present invention is shown.

[0115] Among them, in the preferred implementation manner provided by the present invention, the updating and constructing of the enterprise knowledge base according to the plurality of live standard segment videos and the corresponding standard segment annotation information specifically comprises the following steps:

[0116] Step S10251: Based on the enterprise knowledge base before updating, the plurality of standard segment annotation information are classified and identified, and divided into a plurality of existing segment annotation information and a plurality of missing segment annotation information.

[0117] Step S10252: Classify the plurality of live standard segment videos into a plurality of existing standard segment videos and a plurality of non-standard segment videos according to the plurality of existing segment annotation information and the plurality of non-standard segment annotation information.

[0118] Step S10253: Upgrade and update the enterprise knowledge base based on the multiple existing standard segment videos.

[0119] Step S10254: supplement and update the enterprise knowledge base based on the plurality of non-standard segment videos.

[0120] Furthermore, the artificial intelligence customer service management method based on the enterprise knowledge base also includes the following steps:

[0121] Step S103: receiving a virtual customer service task, screening a plurality of relevant standard segment videos and corresponding relevant annotation information from the enterprise knowledge base, and sequentially performing virtual customer service live broadcasts on the plurality of relevant standard segment videos.

[0122] In an embodiment of the present invention, when a virtual customer service application for artificial intelligence customer service is required, a virtual customer service task is received, and then the virtual customer service task is identified to determine a plurality of customer service display products and a plurality of customer service display projects that need to be displayed for customer service in the virtual customer service task. According to the plurality of customer service display products, a plurality of relevant standard segment videos and corresponding relevant annotation information are screened from an enterprise knowledge base, and then according to the plurality of customer service display projects, a plurality of project standard segment videos are screened from a plurality of relevant standard segment videos, and a customer service live broadcast sequence of the plurality of project standard segment videos is planned, and then virtual customer service live broadcast is performed for the plurality of project standard segment videos according to the customer service live broadcast sequence.

[0123] It is understandable that customer service display projects can include basic product introduction, clothing product matching display, product after-sales introduction, food product tasting display, etc.

[0124] Specifically, Figure 6 A flowchart of sequential virtual customer service live broadcast in the method provided by an embodiment of the present invention is shown.

[0125] Among them, in the preferred implementation mode provided by the present invention, the receiving of the virtual customer service task, selecting a plurality of relevant standard segment videos and corresponding relevant annotation information from the enterprise knowledge base, and sequentially performing virtual customer service live broadcasts on the plurality of relevant standard segment videos specifically comprises the following steps:

[0126] Step S1031, receiving a virtual customer service task.

[0127] Step S1032: Identify the virtual customer service task, and determine a plurality of customer service display products and a plurality of customer service display items.

[0128] Step S1033: According to the plurality of customer service product displaying methods, a plurality of relevant standard segment videos and corresponding relevant annotation information are screened from the enterprise knowledge base.

[0129] Step S1034: Filter multiple project standard segment videos from the multiple related standard segment videos according to the multiple customer service display projects.

[0130] Step S1035: planning the customer service live broadcast sequence of multiple standard segment videos of the project.

[0131] Step S1036: Perform virtual customer service live broadcast for the plurality of project standard segment videos according to the customer service live broadcast sequence.

[0132] Furthermore, the artificial intelligence customer service management method based on the enterprise knowledge base also includes the following steps:

[0133] Step S104: Based on artificial intelligence technology, live broadcast interaction guidance is carried out to obtain user interaction information, and based on the multiple related annotation information, required video matching is carried out to select required standard segment videos.

[0134] In an embodiment of the present invention, during the live broadcast of virtual customer service, based on artificial intelligence technology, live interaction guidance is provided to users in the virtual live broadcast room, user interaction information is obtained in real time, and key interaction information is extracted by performing key identification on the user interaction information. Then, based on the key interaction information, corresponding target annotation information is matched from multiple related annotation information, and then, based on the target annotation information, the corresponding required standard segment video is selected from multiple related standard segment videos.

[0135] Specifically, Figure 7 A flow chart of performing demand video matching in the method provided by an embodiment of the present invention is shown.

[0136] Among them, in the preferred implementation mode provided by the present invention, the live interactive guidance based on artificial intelligence technology, obtaining user interactive information, matching the required videos based on the plurality of related annotation information, and selecting the required standard segment videos specifically include the following steps:

[0137] Step S1041: Conduct live interactive guidance based on artificial intelligence technology.

[0138] Step S1042: Obtain user interaction information in real time.

[0139] Step S1043: perform key identification on the user interaction information and extract interaction key information.

[0140] Step S1044: Match target annotation information from multiple related annotation information according to the interactive key information.

[0141] Step S1045: Select a corresponding required standard segment video from a plurality of related standard segment videos according to the target annotation information.

[0142] Furthermore, the artificial intelligence customer service management method based on the enterprise knowledge base also includes the following steps:

[0143] Step S105: planning the demand insertion time, and inserting the demand standard segment video into the virtual customer service live broadcast at the demand insertion time.

[0144] In an embodiment of the present invention, based on the customer service live broadcast sequence, the virtual customer service live broadcast is sequentially positioned, the current live broadcast sequence of the virtual customer service live broadcast is determined, and then the demand insertion time is planned according to the current live broadcast sequence, and the demand insertion task is created according to the demand insertion time, and then the demand standard segment video is inserted according to the demand insertion task to carry out virtual customer service live broadcast, so that during the virtual customer service live broadcast, the live broadcast is changed according to the needs of users in the virtual live broadcast room, thereby making the virtual live broadcast more user-friendly. For example: when the virtual customer service live broadcast is showing the wearing of clothing products, if a user needs to know about the delivery, exchange, etc., the user can choose to insert the demand standard segment video corresponding to the after-sales introduction of the corresponding product for display.

[0145] Specifically, Figure 8 A flow chart of inserting a virtual customer service live broadcast in the method provided in an embodiment of the present invention is shown.

[0146] Among them, in the preferred implementation manner provided by the present invention, the planning of the demand insertion time, and inserting the demand standard segment video into the virtual customer service live broadcast at the demand insertion time specifically include the following steps:

[0147] Step S1051: Based on the customer service live broadcast sequence, perform sequence positioning to determine the current live broadcast sequence.

[0148] Step S1052: plan the required insertion time according to the current live broadcast sequence.

[0149] Step S1053: Create a demand insertion task according to the demand insertion time.

[0150] Step S1054: insert the task according to the requirement, and insert the required standard segment video to conduct virtual customer service live broadcast.

[0151] Furthermore, Fig. 9 The application architecture diagram of the artificial intelligence customer service management system based on the enterprise knowledge base provided by an embodiment of the present invention is shown.

[0152] Among them, in another preferred embodiment provided by the present invention, an artificial intelligence customer service management system based on an enterprise knowledge base includes:

[0153] The actual live broadcast processing module 101 is used to periodically update and obtain the actual live broadcast customer service video, perform entry recognition, exit recognition and time period judgment, and intercept multiple live broadcast standard segment videos from the actual live broadcast customer service video.

[0154] In an embodiment of the present invention, live broadcast recording is performed during the actual live broadcast process. The actual live broadcast processing module 101 periodically obtains the recorded actual live broadcast customer service video according to a preset live broadcast update cycle, and then extracts the initialization segment video from the actual live broadcast customer service video according to a preset initialization period. By dynamically identifying the initialization segment video, the live broadcast customer service for the actual live broadcast is determined, and the model model, poster model, etc. in the initialization segment video are eliminated. Then, the customer service facial recognition is performed on the live broadcast customer service of the actual live broadcast to obtain the customer service facial feature data, and then the initialization segment video is processed frame by frame to obtain multiple initialization frame images. According to the multiple customer service facial feature data, the initialization frame image with the live broadcast customer service is identified and eliminated from the multiple initialization frame images, and then the initialization frame image with the live broadcast customer service is eliminated from the initialization frame images. Among the remaining multiple initialization frame images, the clearest initialization frame image is selected and marked as the actual live broadcast background image. With the actual live broadcast background image as a reference, entry and exit identification is performed on the actual live customer service video, and multiple customer service entry times and multiple customer service exit times of the live customer service in the actual live customer service video are recorded. According to the multiple customer service entry times and the multiple corresponding customer service exit times, multiple corresponding customer service presence time periods are determined, and then the multiple customer service presence time periods are compared with the preset standard presence time periods, and the customer service presence time periods that are shorter than the standard presence time periods are marked as qualified presence time periods, thereby screening and obtaining multiple qualified presence time periods, and then according to the multiple qualified presence time periods, multiple corresponding live standard segment videos are intercepted from the actual live customer service video.

[0155] Specifically, Fig.10 The application architecture diagram of the actual live broadcast processing module 101 in the system provided by an embodiment of the present invention is shown.

[0156] Among them, in the preferred implementation mode provided by the present invention, the actual live broadcast processing module 101 specifically includes:

[0157] The video acquisition unit 1011 is used to periodically acquire the actual live customer service video according to a preset live update cycle.

[0158] The segment video extraction unit 1012 is used to extract the initialization segment video from the actual live customer service video.

[0159] The facial recognition unit 1013 is used to perform customer service facial recognition on the initialization video segment to obtain customer service facial feature data.

[0160] The frame-by-frame processing unit 1014 is used to process the initialization segment video frame by frame to obtain multiple initialization frame images.

[0161] The background acquisition unit 1015 is used to perform feature matching and image elimination on the multiple initialization frame images according to the customer service facial feature data to obtain the actual live broadcast background image.

[0162] The video segment capture unit 1016 is used to perform entry recognition, exit recognition and time period judgment on the actual live customer service video according to the actual live background image, and capture multiple live standard video segments.

[0163] Furthermore, the artificial intelligence customer service management system based on the enterprise knowledge base also includes:

[0164] The live video recognition module 102 is used to perform product recognition and voice recognition on the multiple live standard segment videos, record multiple corresponding standard segment annotation information, and update and construct the enterprise knowledge base.

[0165] In an embodiment of the present invention, the live video recognition module 102 performs commodity recognition on multiple live standard segment videos according to a preset commodity database, records multiple corresponding commodity segment annotation information, then performs voice recognition of live customer service on multiple live standard segment videos, records multiple corresponding voice segment annotation information, and comprehensively organizes multiple commodity segment annotation information and multiple corresponding voice segment annotation information according to a preset annotation information organization format to generate multiple comprehensive segment annotation information, then performs key recognition on the multiple comprehensive segment annotation information, removes non-critical information irrelevant to the commodity, and generates multiple standard segment annotation information from the multiple comprehensive segment annotation information, performs correlation matching on the multiple standard segment annotation information based on the enterprise knowledge base before updating, and according to the results of the correlation matching, Classify and mark multiple standard segment annotation information into multiple existing segment annotation information and multiple non-segment annotation information, mark the live standard segment videos corresponding to the multiple existing segment annotation information as existing standard segment videos, and mark the live standard segment videos corresponding to the multiple non-segment annotation information as non-standard segment videos, so as to classify the multiple live standard segment videos into multiple existing standard segment videos and multiple non-standard segment videos, and then replace the corresponding segment videos and annotation information in the enterprise knowledge base according to the multiple existing standard segment videos and the multiple existing segment annotation information, so as to realize the upgrade and update of the enterprise knowledge base. At the same time, according to the multiple non-standard segment videos and the multiple non-segment annotation information, supplement the segment videos and annotation information to the enterprise knowledge base, so as to realize the supplement and update of the enterprise knowledge base.

[0166] The sequential virtual live broadcast module 103 is used to receive virtual customer service tasks, filter multiple relevant standard segment videos and corresponding relevant annotation information from the enterprise knowledge base, and perform sequential virtual customer service live broadcasts on the multiple relevant standard segment videos.

[0167] In an embodiment of the present invention, when a virtual customer service application for artificial intelligence customer service is required, the sequential virtual live broadcast module 103 receives the virtual customer service task, then identifies the virtual customer service task, determines multiple customer service display products and multiple customer service display projects that need to be displayed for customer service in the virtual customer service task, and selects multiple relevant standard segment videos and corresponding relevant annotation information from the enterprise knowledge base according to the multiple customer service display products, and then selects multiple project standard segment videos from the multiple relevant standard segment videos according to the multiple customer service display projects, and plans the customer service live broadcast sequence of the multiple project standard segment videos, and then performs virtual customer service live broadcast for the multiple project standard segment videos according to the customer service live broadcast sequence.

[0168] The demand video matching module 104 is used to guide live broadcast interaction based on artificial intelligence technology, obtain user interaction information, match demand videos based on multiple related annotation information, and select demand standard segment videos.

[0169] In an embodiment of the present invention, during the live broadcast of virtual customer service, the demand video matching module 104, based on artificial intelligence technology, guides the users of the virtual live broadcast room to interact with each other, obtains user interaction information in real time, performs key identification on the user interaction information, extracts the interaction key information, and then matches the corresponding target annotation information from multiple related annotation information based on the interaction key information, and then selects the corresponding demand standard segment video from multiple related standard segment videos based on the target annotation information.

[0170] The virtual live broadcast inserting module 105 is used to plan the demand insertion time, and insert the demand standard segment video into the virtual customer service live broadcast at the demand insertion time.

[0171] In an embodiment of the present invention, the virtual live broadcast module 105 inserts a sequence positioning of the virtual customer service live broadcast based on the customer service live broadcast sequence, determines the current live broadcast sequence of the virtual customer service live broadcast, and then plans the demand insertion time according to the current live broadcast sequence, creates the demand insertion task according to the demand insertion time, and then inserts the demand standard segment video according to the demand insertion task to perform virtual customer service live broadcast, so as to realize the changes of the live broadcast in accordance with the needs of users of the virtual live broadcast room during the virtual customer service live broadcast, thereby making the virtual live broadcast more user-friendly. For example: when the virtual customer service live broadcast is performing a clothing product matching display, if a user needs to know about the delivery, exchange, etc., the user can choose to insert the demand standard segment video corresponding to the after-sales introduction of the corresponding product for display.

[0172] It should be understood that, although each step in the flow chart of each embodiment of the present invention is shown in sequence according to the indication of the arrow, these steps are not necessarily performed in sequence according to the order indicated by the arrow. Unless there is a clear explanation in this article, the execution of these steps does not have a strict order restriction, and these steps can be performed in other orders. Moreover, at least a portion of the steps in each embodiment may include a plurality of sub-steps or a plurality of stages, and these sub-steps or stages are not necessarily performed at the same time, but can be performed at different times, and the execution order of these sub-steps or stages is not necessarily performed in sequence, but can be performed in turn or alternately with at least a portion of other steps or sub-steps or stages of other steps.

[0173] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the program can be stored in a non-volatile computer-readable storage medium. When the program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

[0174] The above-mentioned embodiments only express several implementation methods of the present invention, and the description thereof is relatively specific and detailed, but it cannot be understood as limiting the scope of the patent of the present invention. It should be pointed out that, for ordinary technicians in this field, several variations and improvements can be made without departing from the concept of the present invention, which all belong to the protection scope of the present invention. Therefore, the protection scope of the patent of the present invention shall be subject to the attached claims.

Claims

1. An artificial intelligence customer service management method based on an enterprise knowledge base, characterized in that: The method specifically comprises the following steps: Periodically update and obtain the actual live customer service video, perform entry identification, exit identification and time period judgment, and intercept multiple live standard segment videos from the actual live customer service video; Perform product recognition and voice recognition on a plurality of live standard segment videos, record a plurality of corresponding standard segment annotation information, and update and construct an enterprise knowledge base; receiving a virtual customer service task, selecting a plurality of relevant standard segment videos and corresponding relevant annotation information from the enterprise knowledge base, and sequentially performing virtual customer service live broadcasts on the plurality of relevant standard segment videos; Based on artificial intelligence technology, live broadcast interaction guidance is carried out to obtain user interaction information, and based on multiple related annotation information, required video matching is carried out to select required standard segment videos; Plan the demand insertion time, and insert the demand standard segment video into the virtual customer service live broadcast at the demand insertion time.

2. The artificial intelligence customer service management method based on enterprise knowledge base according to claim 1 is characterized in that: The periodic updating and obtaining of the actual live customer service video, performing entry identification, exit identification and time period determination, and intercepting a plurality of live standard segment videos from the actual live customer service video specifically comprises the following steps: According to the preset live broadcast update cycle, the actual live customer service video is periodically obtained; Extracting an initialization segment video from the actual live customer service video; Perform customer service facial recognition on the initialization video segment to obtain customer service facial feature data; Processing the initialization segment video frame by frame to obtain multiple initialization frame images; According to the customer service facial feature data, feature matching and image elimination are performed on the multiple initialization frame images to obtain an actual live broadcast background image; According to the actual live broadcast background image, entry recognition, exit recognition and time period judgment are performed on the actual live broadcast customer service video, and multiple live broadcast standard segment videos are intercepted.

3. The artificial intelligence customer service management method based on enterprise knowledge base according to claim 2 is characterized in that: The step of performing entry recognition, exit recognition and time period judgment on the actual live customer service video according to the actual live background image, and intercepting multiple live standard segment videos specifically comprises the following steps: According to the actual live broadcast background image, the actual live broadcast customer service video is identified for entry and exit, and multiple customer service entry times and multiple customer service exit times are recorded; Determine a plurality of corresponding customer service presence time periods according to the plurality of customer service entry times and the plurality of customer service exit times; comparing the plurality of customer service presence periods with a preset standard presence period; Selecting a plurality of qualified presence time periods from the plurality of customer service presence time periods; According to the multiple qualified presence time periods, multiple live standard segment videos are captured from the actual live customer service video.

4. The artificial intelligence customer service management method based on enterprise knowledge base according to claim 1 is characterized in that: The performing of commodity recognition and voice recognition on the plurality of live standard segment videos, recording a plurality of corresponding standard segment annotation information, and updating and constructing the enterprise knowledge base specifically comprises the following steps: According to a preset commodity database, commodity identification is performed on the plurality of live standard segment videos, and a plurality of corresponding commodity segment annotation information is recorded; Performing voice recognition on a plurality of live standard segment videos, and recording a plurality of corresponding voice segment annotation information; Comprehensively sorting out the plurality of commodity segment annotation information and the plurality of voice segment annotation information to generate a plurality of comprehensive segment annotation information; Performing key identification and information screening on the plurality of comprehensive segment annotation information to generate a plurality of standard segment annotation information; According to the plurality of live standard segment videos and corresponding standard segment annotation information, the enterprise knowledge base is updated and constructed.

5. The artificial intelligence customer service management method based on enterprise knowledge base according to claim 4 is characterized in that: The updating and constructing of the enterprise knowledge base according to the plurality of live standard segment videos and the corresponding standard segment annotation information specifically comprises the following steps: Based on the enterprise knowledge base before updating, the plurality of standard segment annotation information are classified and identified to divide the plurality of existing segment annotation information into a plurality of existing segment annotation information and a plurality of unavailable segment annotation information; According to the plurality of existing segment annotation information and the plurality of non-existing segment annotation information, the plurality of live standard segment videos are classified into a plurality of existing standard segment videos and a plurality of non-existing standard segment videos; Updating the enterprise knowledge base according to the plurality of existing standard segment videos; The enterprise knowledge base is supplemented and updated based on the plurality of non-standard segment videos.

6. The artificial intelligence customer service management method based on enterprise knowledge base according to claim 1 is characterized in that: The receiving of the virtual customer service task, selecting a plurality of relevant standard segment videos and corresponding relevant annotation information from the enterprise knowledge base, and sequentially performing virtual customer service live broadcasts on the plurality of relevant standard segment videos specifically comprises the following steps: Receive virtual customer service tasks; Identify the virtual customer service task, and determine a plurality of customer service display commodities and a plurality of customer service display items; According to the plurality of customer service products displayed, a plurality of relevant standard segment videos and corresponding relevant annotation information are selected from the enterprise knowledge base; According to the plurality of customer service display projects, screening a plurality of project standard segment videos from the plurality of related standard segment videos; Plan the customer service live broadcast sequence of multiple standard segment videos of the project; According to the customer service live broadcast sequence, a virtual customer service live broadcast is performed on a plurality of the project standard segment videos.

7. The artificial intelligence customer service management method based on enterprise knowledge base according to claim 1 is characterized in that: The method of guiding live interactive broadcast based on artificial intelligence technology, obtaining user interactive information, matching required videos based on a plurality of related annotation information, and selecting required standard segment videos specifically includes the following steps: Based on artificial intelligence technology, conduct interactive guidance for live broadcasts; Get user interaction information in real time; Performing key identification on the user interaction information and extracting key interaction information; According to the interactive key information, matching target annotation information from a plurality of related annotation information; According to the target annotation information, a corresponding required standard segment video is selected from a plurality of related standard segment videos.

8. The artificial intelligence customer service management method based on enterprise knowledge base according to claim 6 is characterized in that: The planning of the demand insertion time and inserting the demand standard segment video into the virtual customer service live broadcast at the demand insertion time specifically include the following steps: Based on the customer service live broadcast sequence, perform sequence positioning to determine the current live broadcast sequence; According to the current live broadcast sequence, plan the required insertion time; Creating a demand insertion task according to the demand insertion time; Insert tasks according to the requirements and insert the required standard segment video to conduct virtual customer service live broadcast.

9. An artificial intelligence customer service management system based on an enterprise knowledge base, characterized in that: The system includes an actual live broadcast processing module, a live broadcast video recognition module, a sequential virtual live broadcast module, a demand video matching module and an insertion virtual live broadcast module, wherein: The actual live broadcast processing module is used to periodically update and obtain the actual live broadcast customer service video, perform entry recognition, exit recognition and time period judgment, and intercept multiple live broadcast standard segment videos from the actual live broadcast customer service video; A live video recognition module, used to perform commodity recognition and voice recognition on a plurality of live standard segment videos, record a plurality of corresponding standard segment annotation information, and update and construct an enterprise knowledge base; A sequential virtual live broadcast module is used to receive a virtual customer service task, select a plurality of relevant standard segment videos and corresponding relevant annotation information from the enterprise knowledge base, and perform sequential virtual customer service live broadcast on the plurality of relevant standard segment videos; A demand video matching module is used to guide live broadcast interaction based on artificial intelligence technology, obtain user interaction information, match demand videos based on multiple related annotation information, and select demand standard segment videos; The virtual live broadcast module is inserted to plan the demand insertion time, and at the demand insertion time, the demand standard segment video is inserted into the virtual customer service live broadcast.

10. The artificial intelligence customer service management system based on enterprise knowledge base according to claim 9 is characterized in that: The actual live broadcast processing module specifically includes: A video acquisition unit, used to periodically acquire actual live customer service videos according to a preset live update cycle; A segment video extraction unit, used to extract an initialization segment video from the actual live customer service video; A facial recognition unit, used to perform customer service facial recognition on the initialization video segment to obtain customer service facial feature data; A frame-by-frame processing unit, used to process the initialization segment video frame by frame to obtain a plurality of initialization frame images; A background acquisition unit, configured to perform feature matching and image elimination on the plurality of initialization frame images according to the customer service facial feature data, to acquire an actual live broadcast background image; The video segment capture unit is used to perform entry recognition, exit recognition and time period judgment on the actual live customer service video according to the actual live background image, and capture multiple live standard video segments.

Images