Mobile phone video customer service interaction method and device, electronic equipment and storage medium

Abstract

The invention relates to a mobile phone video customer service interaction method and device, electronic equipment and a storage medium, and the method comprises the steps that a video customer service request is sent to a proxy call session control function network element, and the proxy call session control function network element forwards the video customer service request to a home subscriber server. And when the corresponding user information is queried, sending a session initiation request to the service call session control function network element through an SIP protocol. And performing service logic query in response to the session initiation request through the service call session control function network element, and forwarding the session initiation request to the proxy call session control function network element through the application server after the service logic is queried. And sending the user video stream to a human body action recognition unit for action intention recognition through the proxy call session control function network element. The user intention recognition result is fed back to the application server, and the application server drives the digital customer service to operate based on the user intention recognition result so as to establish an interaction channel between the digital customer service and the user.

Description

Technical Field

[0001] The present invention relates to the technical field of human-computer interaction, and in particular to a method, device, electronic equipment and storage medium for mobile phone video customer service interaction. Background Art

[0002] With the rapid development of science and technology, human-computer interaction technology has penetrated into all aspects of daily life and is also an important development direction for emerging technologies such as wearable devices. At present, in human-computer interaction, users make specific gestures and specific hand shapes, and the human-computer interaction system outputs instructions when it recognizes the specific gestures or specific hand shapes. In human-computer interaction, customer service can improve customer satisfaction and is an indispensable service for enterprise development.

[0003] Traditional customer service is divided into call centers and electronic channels. Call centers rely on voice networks, are highly real-time, and give customers a sense of exclusivity, but rely on customer expressions. It is sometimes difficult to accurately identify user intentions based solely on user expressions. Therefore, a new customer service method, video customer service, is proposed. Existing video customer service mainly relies on application software to process audio and video, and this processing process will cause a certain delay in audio and video. At the same time, due to a large number of concurrent requests, the interaction is blocked, and the interaction quality cannot be well guaranteed, making it difficult to meet users' real-time needs for customer service.

[0004] Therefore, existing video customer service is highly dependent on application software, and it is difficult to conduct real-time video customer service interactions through mobile phone calls while ensuring that video customer service accurately identifies user intentions. Summary of the invention

[0005] Based on this, it is necessary to provide a mobile phone video customer service interaction method, device, electronic device and storage medium that can conduct video customer service interaction through mobile phone calls, has strong real-time performance and can take into account the video customer service to accurately identify user intentions in response to the above technical problems.

[0006] The present invention provides a mobile phone video customer service interaction method, the method comprising: Sending a video customer service request to a proxy call session control function network element, wherein the proxy call session control function network element is used to forward the video customer service request to a home subscriber server; When the home subscriber server queries corresponding user information in response to the video customer service request, sending a session initiation request to the service call session control function network element through the SIP protocol; Performing a service logic query in response to the session initiation request through the service call session control function network element, and forwarding the session initiation request to the proxy call session control function network element through the application server after the corresponding service logic is queried; Sending the user video stream to the human motion recognition unit in response to the session initiation request through the proxy call session control function network element, so as to call a machine learning algorithm to perform motion intention recognition on the user video stream to obtain a user intention recognition result; The user intention recognition result is fed back to the application server, and the application server drives the digital customer service to run based on the user intention recognition result to establish an interactive channel between the digital customer service driving unit and the user terminal.

[0007] In one of the embodiments, the sending of the video customer service request to the proxy call session control function network element, wherein the proxy call session control function network element is used to forward the video customer service request to the home subscriber server, includes: Sending the video customer service request to the proxy call session control function network element in the operator's IMS network through an application or a dial-up interface; forwarding the video customer service request to the home subscriber server through the proxy call session control function network element, so as to call the home subscriber server to query the user information corresponding to the user terminal; The user information includes the user number and subscription information corresponding to the user terminal.

[0008] In one of the embodiments, when the home subscriber server queries the corresponding user information in response to the video customer service request, sending a session initiation request to the service call session control function network element through the SIP protocol includes: In response to the video customer service request and according to the queried user information corresponding to the user terminal, the home subscriber server sends a corresponding session initiation request to the service call session control function network element through the SIP protocol; The session initiation request includes an audio communication request and a video communication request, and the SIP protocol is a protocol for establishing, modifying and terminating a multimedia session.

[0009] In one of the embodiments, the querying of service logic by the service call session control function network element in response to the session initiation request, and forwarding the session initiation request to the proxy call session control function network element through the application server after the corresponding service logic is queried, includes: In response to the session initiation request, calling the service call session control function network element to query the service logic corresponding to the user information, and obtaining the queried service logic; The service logic is sent to the proxy call session control function network element through the SIP protocol, so as to call the proxy call session control function network element to respond to the session initiation request according to the service logic.

[0010] In one of the embodiments, the sending of the user video stream to the human motion recognition unit by the proxy call session control function network element in response to the session initiation request, so as to call a machine learning algorithm to perform motion intention recognition on the user video stream, and obtain a user intention recognition result, includes: In response to the session initiation request, sending the corresponding user video stream to the human motion recognition unit according to the business logic, wherein the human motion recognition unit has a machine learning algorithm for recognizing human motion; The human motion recognition unit is driven to call the machine learning algorithm to recognize the human motion in the user video stream, and the recognized human motion is analyzed to obtain the user intention recognition result.

[0011] In one embodiment, the user intention recognition result is fed back to the application server, and the application server drives the digital customer service to run based on the user intention recognition result to establish an interaction channel between the digital customer service driving unit and the user terminal, including: After receiving the user intention recognition result, the application server determines the action intention corresponding to the human body action in the user video stream through logical processing, and drives the digital customer service driving unit to operate according to the action intention; The digital customer service driving unit drives the digital customer service to respond to the action intention and establish a corresponding interaction channel with the user terminal.

[0012] In one embodiment, the user intention recognition result is fed back to the application server, and the application server drives the digital customer service to run based on the user intention recognition result to establish an interactive channel between the digital customer service driving unit and the user terminal, and then includes: receiving interactive content from the digital customer service through the interactive channel, wherein the interactive content is feedback from the digital customer service to the user terminal based on the action intention; The user video stream obtained by the user terminal after receiving the interactive content is fed back to the digital customer service driving unit through the interactive channel, so that the user terminal and the digital customer service driving unit can have a video conversation through the interactive channel.

[0013] The present invention also provides a mobile phone video customer service interaction device, the device comprising: A video customer service request module, used to send a video customer service request to a proxy call session control function network element, and the proxy call session control function network element is used to forward the video customer service request to a home subscriber server; A session initiation request module, configured to send a session initiation request to a service call session control function network element through a SIP protocol when the home subscriber server queries corresponding user information in response to the video customer service request; a logic query module, configured to perform a service logic query through the service call session control function network element in response to the session initiation request, and forward the session initiation request to the proxy call session control function network element through the application server after the corresponding service logic is queried; A user intention recognition module is used to send the user video stream to the human action recognition unit through the proxy call session control function network element in response to the session initiation request, so as to call the machine learning algorithm to perform action intention recognition on the user video stream to obtain a user intention recognition result; The interactive channel establishment module is used to feed back the user intention recognition result to the application server, and the application server drives the digital customer service to run based on the user intention recognition result to establish an interactive channel between the digital customer service driving unit and the user end.

[0014] The present invention also provides an electronic device, including a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, it implements any of the mobile phone video customer service interaction methods described above.

[0015] The present invention also provides a computer storage medium storing a computer program, wherein when the computer program is executed by a processor, the mobile phone video customer service interaction method as described in any one of the above is implemented.

[0016] The present invention also provides a computer program product, including a computer program, which, when executed by a processor, implements any of the mobile phone video customer service interaction methods described above.

[0017] In the above-mentioned mobile phone video customer service interaction method, device, electronic device and storage medium, the user terminal sends a video customer service request to the proxy call session control function network element, and the proxy call session control function network element is used to forward the video customer service request to the home contract user server. Subsequently, when the home contract user server queries the corresponding user information in response to the video customer service request, it sends a session initiation request to the service call session control function network element through the SIP protocol. Then, the service call session control function network element responds to the session initiation request to query the business logic, and after querying the corresponding business logic, the session initiation request is forwarded to the proxy call session control function network element through the application server. Then, the proxy call session control function network element responds to the session initiation request to send the user video stream to the human motion recognition unit to call the machine learning algorithm to perform motion intent recognition on the user video stream to obtain the user intent recognition result. Finally, the user intent recognition result is fed back to the application server, and the application server drives the digital customer service to run based on the user intent recognition result to establish an interactive channel between the digital customer service driving unit and the user terminal. This method detects user behavior information through action recognition algorithms, determines user behavior intentions, and establishes a link through the operator's IMS network to conduct digital video customer service behavior dialogues. It can conduct video customer service interactions through mobile phone calls, has strong real-time performance, and can also take into account video customer service to accurately identify user intentions, thereby achieving faster and more effective customer service. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0019] Figure 1 This is one of the flow diagrams of the mobile phone video customer service interaction method provided by the present invention; Figure 2 A schematic diagram of the overall architecture of video customer service interaction of a mobile phone video customer service interaction method in a specific embodiment of the present invention; Figure 3 A schematic diagram of the overall process of video customer service interaction of a mobile phone video customer service interaction method in a specific embodiment provided by the present invention; Figure 4 The second flowchart of the mobile phone video customer service interaction method provided by the present invention; Figure 5 The third flowchart of the mobile phone video customer service interaction method provided by the present invention; Figure 6 The fourth flowchart of the mobile phone video customer service interaction method provided by the present invention; Figure 7 This is a fifth flow chart of the mobile phone video customer service interaction method provided by the present invention; Figure 8 The sixth flow chart of the mobile phone video customer service interaction method provided by the present invention; Fig. 9 A schematic diagram of the structure of the mobile phone video customer service interaction device provided by the present invention; Fig.10 This is a diagram of the internal structure of the electronic device provided by the present invention. DETAILED DESCRIPTION

[0020] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0021] Combine the following Figure 1-Figure 10 The present invention describes the mobile phone video customer service interaction method, device, electronic device and storage medium.

[0022] like Figure 1 As shown, in one embodiment, a mobile phone video customer service interaction method includes the following steps: Step S110: sending a video customer service request to a proxy call session control function network element, and the proxy call session control function network element is used to forward the video customer service request to a home subscriber server.

[0023] Specifically, the user terminal sends a video customer service request to the proxy call session control function network element, and the proxy call session control function network element is used to forward the video customer service request to the home subscriber server.

[0024] Step S120: When the home subscriber server queries the corresponding user information in response to the video customer service request, it sends a session initiation request to the service call session control function network element through the SIP protocol.

[0025] Specifically, after receiving the video customer service request, the home subscriber server queries whether there is corresponding user information in response to the video customer service request, and after querying the corresponding user information, sends a session initiation request to the service call session control function network element through the SIP protocol.

[0026] It should be noted that the home subscriber server responds to the video customer service request and sends a corresponding session initiation request to the service call session control function network element through the SIP protocol according to the user information corresponding to the queried user terminal.

[0027] The session initiation request includes an audio communication request and a video communication request, and the SIP protocol is a protocol used to establish, modify and terminate multimedia sessions.

[0028] Step S130: the service call session control function network element performs a service logic query in response to the session initiation request, and after the corresponding service logic is queried, the session initiation request is forwarded to the proxy call session control function network element through the application server.

[0029] Specifically, after receiving the session initiation request sent by the home subscriber server, the service call session control function network element performs a service logic query in response to the session initiation request, and after querying the corresponding service logic, forwards the session initiation request to the proxy call session control function network element through the application server according to the service logic.

[0030] Step S140, in response to the session initiation request, the proxy call session control function network element sends the user video stream to the human action recognition unit to call a machine learning algorithm to perform action intention recognition on the user video stream to obtain a user intention recognition result.

[0031] Specifically, the proxy call session control function network element receives the session initiation request forwarded by the service call session control function network element and sends the corresponding user video stream to the human motion recognition unit to call the machine learning algorithm in the human motion recognition unit to perform motion intention recognition on the user video stream to obtain the user intention recognition result.

[0032] Step S150, feeding back the user intention recognition result to the application server, and the application server drives the digital customer service to run based on the user intention recognition result to establish an interactive channel between the digital customer service driving unit and the user end.

[0033] Specifically, the user intention recognition result obtained in step S140 is fed back to the application server, and the application server drives the digital customer service to run according to the received user intention recognition result, thereby establishing an interactive channel between the digital customer service driving unit and the user end.

[0034] In the above-mentioned mobile phone video customer service interaction method, the user terminal sends a video customer service request to the proxy call session control function network element, and the proxy call session control function network element is used to forward the video customer service request to the home subscriber server. Subsequently, when the home subscriber server queries the corresponding user information in response to the video customer service request, it sends a session initiation request to the service call session control function network element through the SIP protocol. Then, the service call session control function network element responds to the session initiation request to query the business logic, and after querying the corresponding business logic, the session initiation request is forwarded to the proxy call session control function network element through the application server. Then, the proxy call session control function network element responds to the session initiation request to send the user video stream to the human motion recognition unit to call the machine learning algorithm to perform motion intent recognition on the user video stream to obtain the user intent recognition result. Finally, the user intent recognition result is fed back to the application server, and the application server drives the digital customer service to run based on the user intent recognition result to establish an interactive channel between the digital customer service driving unit and the user terminal. This method detects user behavior information through action recognition algorithms, determines user behavior intentions, and establishes a link through the operator's IMS network to conduct digital video customer service behavior dialogues. It can conduct video customer service interactions through mobile phone calls, has strong real-time performance, and can also take into account video customer service to accurately identify user intentions, thereby achieving faster and more effective customer service.

[0035] See also Figure 2 As shown, in a specific embodiment, the mobile phone video customer service interaction method provided by the present invention is that the user transmits the video to the designated Volte video capability platform through the operator's network and the Volte video capability gateway. On the Volte video capability platform, the action recognition algorithm is used to identify the user's behavior, identify the user's behavior intention, and feedback drive the AI ​​digital human, and then establish a connection with the video customer service seat to realize the user's dialogue with the customer service system.

[0036] In this embodiment, the motion recognition algorithm mainly includes two parts. One part is the motion capture unit. The motion capture unit uses image processing or deep learning algorithms to capture the user's body language and behavior in real time and convert it into analyzable data. The other part is the behavior analysis unit. The behavior analysis unit analyzes the data of the motion capture module through the motion recognition algorithm to determine the user's intention. Machine learning algorithms such as support vector machines (SVM) and random forests can be used to classify and identify the user's actions and behaviors.

[0037] Combination Figure 3As shown, in this embodiment, the network elements in the figure are as follows: P-CSCF (Proxy-Call Session Control Function) proxy call session control function, S-CSCF (Service Call Session Control Function) service call session control function, HSS (Home Subscriber Server) home subscriber server, AS (Application Server) application server.

[0038] The mobile phone user initiates a video customer service request to the P-CSCF network element in the operator's IMS network. The request can be initiated in a variety of ways, such as from a mobile phone application, dial-up interface, etc. The P-CSCF network element forwards the request to the HSS (HomeSubscriber Server), which queries the user information, including the user number, subscription information, etc. Subsequently, signaling is transmitted between various network elements through the SIP (Session Initiation Protocol), where SIP is a protocol used to establish, modify, and terminate multimedia sessions, such as audio and video communications. Business logic queries are performed on the application server (Application Server, AS), which is a server used to process business logic. It can process the user's video customer service request and perform logical processing based on the user information and action recognition results. After logical processing, the user's video stream is input into the human action recognition system for action intention recognition. The system uses deep learning or machine learning algorithms to judge the user's intention by analyzing the user's behavior and actions.

[0039] After motion recognition, AS processes the motion intent logically and drives the digital customer service to establish a link with the user for a video conversation. The digital customer service can be a pre-set customer service robot or manual customer service, which automatically replies or provides manual service based on the user's intent. The motion recognition algorithm detects user behavior information, determines the user's behavioral intent, and establishes a link through the operator's IMS network to conduct a digital video customer service behavior conversation. The motion recognition algorithm analyzes the user's intent and automatically establishes a link with the digital video customer service to achieve fast and effective customer service. Thresholds can also be set to better meet user needs and improve service quality.

[0040] In this embodiment, an action recognition algorithm is used to detect user behavior information and determine the user's behavioral intention. The user's actions and behaviors can be analyzed through deep learning or machine learning algorithms to determine the user's needs and intentions. In addition, a threshold can be set as needed. Only when the user's behavior exceeds the preset threshold will the establishment of a link be triggered, thereby better meeting user needs and improving service quality. In addition, by utilizing the operator's IMS network, fast and efficient video call link establishment can be achieved, providing more convenient customer service.

[0041] like Figure 4 As shown, in one embodiment, the mobile phone video customer service interaction method provided by the present invention sends a video customer service request to the proxy call session control function network element, and the proxy call session control function network element is used to forward the video customer service request to the home subscriber server, specifically including the following steps: Step S112: sending a video customer service request to a proxy call session control function network element in the operator's IMS network through an application or a dial-up interface.

[0042] Step S114: forwarding the video customer service request to the home subscriber server through the proxy call session control function network element, so as to call the home subscriber server to query the user information corresponding to the user terminal.

[0043] The user information includes the user number and subscription information corresponding to the user terminal.

[0044] like Figure 5 As shown, in one embodiment, the mobile phone video customer service interaction method provided by the present invention performs a business logic query in response to a session initiation request through a service call session control function network element, and forwards the session initiation request to the proxy call session control function network element through an application server after the corresponding business logic is queried, specifically including the following steps: Step S132: In response to the session initiation request, the service call session control function network element is called to query the service logic corresponding to the user information, and the queried service logic is obtained.

[0045] Step S134: Send the service logic to the proxy call session control function network element through the SIP protocol, so as to call the proxy call session control function network element to respond to the session initiation request according to the service logic.

[0046] like Figure 6 As shown, in one embodiment, the mobile phone video customer service interaction method provided by the present invention sends the user video stream to the human motion recognition unit in response to the session initiation request through the proxy call session control function network element, so as to call the machine learning algorithm to perform motion intention recognition on the user video stream to obtain the user intention recognition result, which specifically includes the following steps: Step S142, in response to the session initiation request, the corresponding user video stream is sent to the human motion recognition unit according to the business logic, and the human motion recognition unit has a machine learning algorithm for recognizing human motion.

[0047] Step S144, driving the human motion recognition unit to call a machine learning algorithm to recognize human motions in the user video stream, and analyzing the recognized human motions to obtain a user intention recognition result.

[0048] like Figure 7 As shown, in one embodiment, the mobile phone video customer service interaction method provided by the present invention feeds back the user intention recognition result to the application server, and the application server drives the digital customer service to run based on the user intention recognition result to establish an interaction channel between the digital customer service driving unit and the user end, specifically including the following steps: Step S152, after receiving the user intention recognition result, the application server determines the action intention corresponding to the human body action in the user video stream through logical processing, and drives the digital customer service driving unit to run according to the action intention.

[0049] Step S154: The digital customer service driving unit drives the digital customer service to respond to the action intention and establish a corresponding interaction channel with the user terminal.

[0050] like Figure 8 As shown, in one embodiment, the mobile phone video customer service interaction method provided by the present invention feeds back the user intention recognition result to the application server, and the application server drives the digital customer service to run based on the user intention recognition result to establish an interaction channel between the digital customer service driving unit and the user end, and then includes the following steps: Step S810: receiving interactive content from the digital customer service through the interactive channel. The interactive content is feedback from the digital customer service to the user end based on the action intention.

[0051] Step S820: Feedback the user video stream obtained by the user terminal after receiving the interactive content to the digital customer service driving unit through the interactive channel, so that the user terminal and the digital customer service driving unit can have a video conversation through the interactive channel.

[0052] The mobile phone video customer service interaction device provided by the present invention is described below. The mobile phone video customer service interaction device described below and the mobile phone video customer service interaction method described above can be referenced to each other.

[0053] like Fig. 9 As shown, in one embodiment, a mobile phone video customer service interaction device includes a video customer service request module 910, a session initiation request module 920, a logic query module 930, a user intention recognition module 940 and an interaction channel establishment module 950.

[0054] The video customer service request module 910 is used to send a video customer service request to the proxy call session control function network element, and the proxy call session control function network element is used to forward the video customer service request to the home subscriber server.

[0055] The session initiation request module 920 is used to send a session initiation request to the service call session control function network element through the SIP protocol when the home subscriber server queries the corresponding user information in response to the video customer service request.

[0056] The logic query module 930 is used to perform a service logic query in response to the session initiation request through the service call session control function network element, and forward the session initiation request to the proxy call session control function network element through the application server after the corresponding service logic is queried.

[0057] The user intention recognition module 940 is used to send the user video stream to the human motion recognition unit in response to the session initiation request through the proxy call session control function network element, so as to call the machine learning algorithm to perform motion intention recognition on the user video stream and obtain the user intention recognition result.

[0058] The interactive channel establishment module 950 is used to feed back the user intention recognition result to the application server, and the application server drives the digital customer service to run based on the user intention recognition result to establish an interactive channel between the digital customer service driving unit and the user end.

[0059] In this embodiment, the mobile phone video customer service interactive device provided by the present invention, the video customer service request module 910 is specifically used for: Send a video customer service request to the proxy call session control function network element in the operator's IMS network through an application or dial-up interface.

[0060] The video customer service request is forwarded to the home subscriber server through the proxy call session control function network element, so as to call the home subscriber server to query the user information corresponding to the user terminal.

[0061] The user information includes the user number and subscription information corresponding to the user terminal.

[0062] In this embodiment, the mobile video customer service interaction device provided by the present invention, the session initiation request module 920 is specifically used for: The home subscriber server responds to the video customer service request and sends a corresponding session initiation request to the service call session control function network element through the SIP protocol according to the user information corresponding to the queried user terminal.

[0063] The session initiation request includes an audio communication request and a video communication request, and the SIP protocol is a protocol used to establish, modify and terminate multimedia sessions.

[0064] In this embodiment, the mobile phone video customer service interaction device provided by the present invention, the logic query module 930 is specifically used for: In response to the session initiation request, the service call session control function network element is called to query the service logic corresponding to the user information to obtain the queried service logic.

[0065] The service logic is sent to the proxy call session control function network element through the SIP protocol, so as to call the proxy call session control function network element to respond to the session initiation request according to the service logic.

[0066] In this embodiment, in the mobile phone video customer service interaction device provided by the present invention, the user intention recognition module 940 is specifically used for: In response to the session initiation request, the corresponding user video stream is sent to the human motion recognition unit according to the business logic. The human motion recognition unit has a machine learning algorithm for recognizing human motion.

[0067] The human action recognition unit is driven to call the machine learning algorithm to recognize the human actions in the user video stream, and the recognized human actions are analyzed to obtain the user intention recognition result.

[0068] In this embodiment, the mobile phone video customer service interactive device provided by the present invention, the interactive channel establishment module 950 is specifically used for: After receiving the user intention recognition result, the application server determines the action intention corresponding to the human body movement in the user video stream through logical processing, and drives the digital customer service drive unit to run according to the action intention.

[0069] The digital customer service driving unit drives the digital customer service to respond to the action intention and establish a corresponding interaction channel with the user end.

[0070] In this embodiment, the mobile phone video customer service interaction device provided by the present invention further includes a video customer service interaction module for: The interactive content is received from the digital customer service through the interactive channel. The interactive content is the feedback from the digital customer service to the user end based on the action intention.

[0071] The user video stream obtained after the user terminal receives the interactive content is fed back to the digital customer service driving unit through the interactive channel, so that the user terminal and the digital customer service driving unit can have a video conversation through the interactive channel.

[0072] Fig.10 An example of a physical structure diagram of an electronic device is shown. The electronic device may be a smart terminal, and its internal structure diagram may be as follows: Fig.10As shown. The electronic device includes a processor, an internal memory and a network interface connected via a system bus. The processor of the electronic device is used to provide computing and control capabilities. The memory of the electronic device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The network interface of the electronic device is used to communicate with an external terminal via a network connection. When the computer program is executed by the processor, a mobile phone video customer service interaction method is implemented, and the method includes: Sending a video customer service request to a proxy call session control function network element, where the proxy call session control function network element is used to forward the video customer service request to a home subscriber server; When the home subscriber server queries the corresponding user information in response to the video customer service request, it sends a session initiation request to the service call session control function network element through the SIP protocol; Performing a service logic query in response to the session initiation request through the service call session control function network element, and forwarding the session initiation request to the proxy call session control function network element through the application server after the corresponding service logic is queried; The proxy call session control function network element sends the user video stream to the human action recognition unit in response to the session initiation request, so as to call the machine learning algorithm to perform action intention recognition on the user video stream and obtain the user intention recognition result; The user intention recognition result is fed back to the application server, and the application server drives the digital customer service operation based on the user intention recognition result to establish an interaction channel between the digital customer service driving unit and the user end.

[0073] Those skilled in the art will understand that Fig.10 The structure shown in the figure is only a block diagram of a part of the structure related to the scheme of the present invention, and does not constitute a limitation on the electronic device to which the scheme of the present invention is applied. The specific electronic device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0074] On the other hand, the present invention further provides a computer storage medium storing a computer program, which implements a mobile phone video customer service interaction method when the computer program is executed by a processor, the method comprising: Sending a video customer service request to a proxy call session control function network element, where the proxy call session control function network element is used to forward the video customer service request to a home subscriber server; When the home subscriber server queries the corresponding user information in response to the video customer service request, it sends a session initiation request to the service call session control function network element through the SIP protocol; Performing a service logic query in response to the session initiation request through the service call session control function network element, and forwarding the session initiation request to the proxy call session control function network element through the application server after the corresponding service logic is queried; The proxy call session control function network element sends the user video stream to the human action recognition unit in response to the session initiation request, so as to call the machine learning algorithm to perform action intention recognition on the user video stream and obtain the user intention recognition result; The user intention recognition result is fed back to the application server, and the application server drives the digital customer service operation based on the user intention recognition result to establish an interaction channel between the digital customer service driving unit and the user end.

[0075] In another aspect, a computer program product or a computer program is provided, the computer program product or the computer program comprising computer instructions, the computer instructions being stored in a computer-readable storage medium. A processor of an electronic device reads the computer instructions from the computer-readable storage medium, and when the processor executes the computer instructions, a method for mobile phone video customer service interaction is implemented, the method comprising: Sending a video customer service request to a proxy call session control function network element, where the proxy call session control function network element is used to forward the video customer service request to a home subscriber server; When the home subscriber server queries the corresponding user information in response to the video customer service request, it sends a session initiation request to the service call session control function network element through the SIP protocol; Performing a service logic query in response to the session initiation request through the service call session control function network element, and forwarding the session initiation request to the proxy call session control function network element through the application server after the corresponding service logic is queried; The proxy call session control function network element sends the user video stream to the human action recognition unit in response to the session initiation request, so as to call the machine learning algorithm to perform action intention recognition on the user video stream and obtain the user intention recognition result; The user intention recognition result is fed back to the application server, and the application server drives the digital customer service operation based on the user intention recognition result to establish an interaction channel between the digital customer service driving unit and the user end.

[0076] Those of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be implemented by instructing related hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer 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 by the present invention may 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.

[0077] By way of 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), etc.

[0078] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0079] 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. A mobile phone video customer service interaction method, characterized in that: The method comprises: Sending a video customer service request to a proxy call session control function network element, wherein the proxy call session control function network element is used to forward the video customer service request to a home subscriber server; When the home subscriber server queries corresponding user information in response to the video customer service request, sending a session initiation request to the service call session control function network element through the SIP protocol; Performing a service logic query in response to the session initiation request through the service call session control function network element, and forwarding the session initiation request to the proxy call session control function network element through the application server after the corresponding service logic is queried; Sending the user video stream to the human motion recognition unit in response to the session initiation request through the proxy call session control function network element, so as to call a machine learning algorithm to perform motion intention recognition on the user video stream to obtain a user intention recognition result; The user intention recognition result is fed back to the application server, and the application server drives the digital customer service to run based on the user intention recognition result to establish an interactive channel between the digital customer service driving unit and the user terminal.

2. The mobile phone video customer service interaction method according to claim 1, characterized in that: The sending of the video customer service request to the proxy call session control function network element, wherein the proxy call session control function network element is used to forward the video customer service request to the home subscriber server, includes: Sending the video customer service request to the proxy call session control function network element in the operator's IMS network through an application or a dial-up interface; forwarding the video customer service request to the home subscriber server through the proxy call session control function network element, so as to call the home subscriber server to query the user information corresponding to the user terminal; The user information includes the user number and subscription information corresponding to the user terminal.

3. The mobile phone video customer service interaction method according to claim 2, characterized in that: When the home subscriber server queries corresponding user information in response to the video customer service request, sending a session initiation request to a service call session control function network element through the SIP protocol includes: In response to the video customer service request and according to the queried user information corresponding to the user terminal, the home subscriber server sends a corresponding session initiation request to the service call session control function network element through the SIP protocol; The session initiation request includes an audio communication request and a video communication request, and the SIP protocol is a protocol for establishing, modifying and terminating a multimedia session.

4. The mobile phone video customer service interaction method according to claim 3, characterized in that: The performing a service logic query in response to the session initiation request through the service call session control function network element, and forwarding the session initiation request to the proxy call session control function network element through the application server after the corresponding service logic is queried, includes: In response to the session initiation request, calling the service call session control function network element to query the service logic corresponding to the user information, and obtaining the queried service logic; The service logic is sent to the proxy call session control function network element through the SIP protocol, so as to call the proxy call session control function network element to respond to the session initiation request according to the service logic.

5. The mobile phone video customer service interaction method according to claim 4, characterized in that: The sending of the user video stream to the human motion recognition unit by the proxy call session control function network element in response to the session initiation request, so as to call a machine learning algorithm to perform motion intention recognition on the user video stream, and obtain a user intention recognition result, including: In response to the session initiation request, sending the corresponding user video stream to the human motion recognition unit according to the business logic, wherein the human motion recognition unit has a machine learning algorithm for recognizing human motion; The human motion recognition unit is driven to call the machine learning algorithm to recognize the human motion in the user video stream, and the recognized human motion is analyzed to obtain the user intention recognition result.

6. The mobile phone video customer service interaction method according to claim 5, characterized in that: Feeding back the user intention recognition result to the application server, and the application server driving the digital customer service to run based on the user intention recognition result to establish an interactive channel between the digital customer service driving unit and the user terminal, includes: After receiving the user intention recognition result, the application server determines the action intention corresponding to the human body action in the user video stream through logical processing, and drives the digital customer service driving unit to operate according to the action intention; The digital customer service driving unit drives the digital customer service to respond to the action intention and establish a corresponding interaction channel with the user terminal.

7. The mobile phone video customer service interaction method according to claim 6, characterized in that: The method feeds back the user intention recognition result to the application server, and the application server drives the digital customer service to run based on the user intention recognition result to establish an interactive channel between the digital customer service driving unit and the user terminal, and then includes: receiving interactive content from the digital customer service through the interactive channel, wherein the interactive content is feedback from the digital customer service to the user terminal based on the action intention; The user video stream obtained by the user terminal after receiving the interactive content is fed back to the digital customer service driving unit through the interactive channel, so that the user terminal and the digital customer service driving unit can have a video conversation through the interactive channel.

8. A mobile phone video customer service interactive device, characterized in that: The device comprises: A video customer service request module, used to send a video customer service request to a proxy call session control function network element, and the proxy call session control function network element is used to forward the video customer service request to a home subscriber server; A session initiation request module, configured to send a session initiation request to a service call session control function network element through a SIP protocol when the home subscriber server queries corresponding user information in response to the video customer service request; a logic query module, configured to perform a service logic query through the service call session control function network element in response to the session initiation request, and forward the session initiation request to the proxy call session control function network element through the application server after the corresponding service logic is queried; A user intention recognition module is used to send the user video stream to the human action recognition unit through the proxy call session control function network element in response to the session initiation request, so as to call the machine learning algorithm to perform action intention recognition on the user video stream to obtain a user intention recognition result; The interactive channel establishment module is used to feed back the user intention recognition result to the application server, and the application server drives the digital customer service to run based on the user intention recognition result to establish an interactive channel between the digital customer service driving unit and the user end.

9. An electronic device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 7 are implemented.

10. A computer storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

Images