Management method and system for intelligently judging illegal behaviors of sales personnel

Abstract

The invention provides a management method and system for intelligently judging illegal behaviors of sales personnel. The management method comprises the following steps: respectively acquiring a sound signal and an image signal; the collected sound signals and the collected image signals are preprocessed respectively; and carrying out intelligent identification on the preprocessed sound signals and image signals through an analysis model to judge illegal behaviors. According to the invention, perception technologies such as voiceprint recognition, image recognition and the like and intelligent recognition are utilized, so that the management level is improved, passive processing after work is carried out, evidence cannot be obtained, timely management and control in the sales process are improved, and sound recording and video recording evidence can be obtained in time.

Description

Technical Field

[0001] The present invention relates to the field of voiceprint recognition and perception technology, and in particular, to a management method and system for intelligently identifying sales personnel's illegal behaviors. Background Art

[0002] In the prior art, back-end management personnel can only review audio and video recordings after a customer complains, resulting in delayed management.

[0003] Patent document CN113852724A (application number: 202111123074.0) discloses an AI voice-based abnormal behavior prevention and control method that is efficient and has intelligent analysis and prompting functions. The AI ​​voice-based abnormal behavior prevention and control method includes the following contents: intelligent call-out and dialogue based on AI voice; intelligent analysis and recording of customer voice information, identification of customers and risk awakening prompts based on stored abnormal behavior customers and analyzed customer voice information; and matching the analyzed customer voice information with the stored risk identification information, generating matching results, and generating corresponding risk levels based on the matching results. Summary of the invention

[0004] In view of the defects in the prior art, the purpose of the present invention is to provide a management method and system for intelligently identifying the illegal behaviors of sales personnel.

[0005] The first aspect of the present invention provides a management method for intelligently identifying sales personnel's illegal behaviors, comprising:

[0006] Collecting sound signals and image signals respectively;

[0007] Preprocessing the collected sound signals and image signals respectively;

[0008] The pre-processed sound and image signals are intelligently identified and judged for violations through the analysis model.

[0009] Optionally, in a first implementation of the first aspect of the present invention, the collecting of sound information and image signals separately includes:

[0010] The sound signal is collected by a sound sensor; wherein the sound sensor includes a pickup and a microphone;

[0011] The image signal is collected by an image sensor; wherein the image sensor includes a camera.

[0012] Optionally, in a second implementation of the first aspect of the present invention, the preprocessing of the collected sound signal and image signal includes:

[0013] The collected sound signal is subjected to denoising, feature extraction and normalization processing to obtain a pre-processed sound signal;

[0014] The collected image signal is subjected to denoising, image scaling and cropping, and grayscale processing to obtain a preprocessed image signal.

[0015] Optionally, in a third implementation of the first aspect of the present invention, the intelligently identifying and distinguishing illegal behaviors on the pre-processed sound signals and image signals through the analysis model includes:

[0016] The analysis model includes a voiceprint recognition model and an image recognition model;

[0017] Constructing a sound training set, and using the sound training set to train the voiceprint recognition model to obtain a trained voiceprint recognition model; using the trained voiceprint recognition model to recognize the collected real-time sound signals and identify illegal behaviors; wherein the sound training set is the collected sound signals and their corresponding annotated sales behaviors; the annotated sales behaviors include: illegal behaviors and non-illegal behaviors;

[0018] An image training set is constructed, and an image recognition model is trained using the image training set to obtain a trained image recognition model; the trained image recognition model is used to recognize the collected real-time image signals to identify illegal behaviors; wherein the image training set includes: collected image signals and their corresponding annotated sales behaviors; the annotated sales behaviors include illegal behaviors and non-illegal behaviors.

[0019] Optionally, in a third implementation of the first aspect of the present invention, the method further includes: transmitting the identified illegal behavior to a monitoring terminal;

[0020] Based on the identified violations, analysis reports are generated regularly and transmitted to the monitoring end.

[0021] A second aspect of the present invention provides a management system for intelligently identifying sales personnel's illegal behaviors, comprising:

[0022] A collection module, used for collecting sound signals and image signals respectively;

[0023] A preprocessing module, used to preprocess the collected sound signals and image signals respectively;

[0024] The intelligent identification module is used to intelligently identify and identify violations of pre-processed sound signals and image signals through analysis models.

[0025] Optionally, in a first implementation of the second aspect of the present invention, the acquisition module includes:

[0026] The sound signal is collected by a sound sensor; wherein the sound sensor includes a pickup and a microphone;

[0027] The image signal is collected by an image sensor; wherein the image sensor includes a camera.

[0028] Optionally, in a second implementation of the second aspect of the present invention, the preprocessing module includes:

[0029] The collected sound signal is subjected to denoising, feature extraction and normalization processing to obtain a pre-processed sound signal;

[0030] The collected image signal is subjected to denoising, image scaling and cropping, and grayscale processing to obtain a preprocessed image signal.

[0031] Optionally, in a third implementation of the second aspect of the present invention, the intelligent identification module includes:

[0032] The analysis model includes a voiceprint recognition model and an image recognition model;

[0033] Constructing a sound training set, and using the sound training set to train the voiceprint recognition model to obtain a trained voiceprint recognition model; using the trained voiceprint recognition model to recognize the collected real-time sound signals and identify illegal behaviors; wherein the sound training set is the collected sound signals and their corresponding annotated sales behaviors; the annotated sales behaviors include: illegal behaviors and non-illegal behaviors;

[0034] An image training set is constructed, and an image recognition model is trained using the image training set to obtain a trained image recognition model; the trained image recognition model is used to recognize the collected real-time image signals to identify illegal behaviors; wherein the image training set includes: collected image signals and their corresponding annotated sales behaviors; the annotated sales behaviors include illegal behaviors and non-illegal behaviors.

[0035] Optionally, in a fourth implementation of the second aspect of the present invention, the system further includes: an analysis module, configured to transmit the identified illegal behavior to a monitoring terminal;

[0036] Based on the identified violations, analysis reports are generated regularly and transmitted to the monitoring end.

[0037] Compared with the prior art, the present invention has the following beneficial effects:

[0038] 1. The present invention utilizes perception technologies such as voiceprint recognition and image recognition, as well as intelligent recognition, to improve management level, from passive processing after the event, which is unable to obtain evidence, to timely control of the sales process, and can obtain audio and video evidence in a timely manner;

[0039] 2. The present invention utilizes perception technologies such as voiceprint recognition and image recognition to identify standard illegal words and behaviors, and combines analysis models through continuous training to improve intelligent identification capabilities and enhance the level of in-process supervision and management of managers. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] Other features, objects and advantages of the present invention will become more apparent from the detailed description of non-limiting embodiments made with reference to the following drawings:

[0041] Figure 1 A first flow chart of a management method for intelligently identifying sales personnel's illegal behaviors provided by an embodiment of the present invention;

[0042] Figure 2 A second flow chart of the management method for intelligently identifying sales personnel's illegal behaviors provided by an embodiment of the present invention;

[0043] Figure 3 A structural schematic diagram of a delivery address modification system for express mail provided in an embodiment of the present invention.

[0044] Figure 4 A schematic diagram of the structure of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0045] The embodiment of the present invention provides a management method and system for intelligently distinguishing the illegal behaviors of sales personnel, respectively collecting sound signals and image signals; preprocessing the collected sound signals and image signals respectively; and intelligently identifying and distinguishing illegal behaviors through an analysis model for the preprocessed sound signals and image signals. The present invention solves the problem of managers' post-event passive handling of misleading sales behaviors.

[0046] The terms "first", "second", "third", "fourth", etc. (if any) in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments described herein can be implemented in an order other than that illustrated or described herein. In addition, the terms "including" or "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0047] For ease of understanding, the specific process of the embodiment of the present invention is described below. Figure 1The first embodiment of the management method for intelligently identifying sales personnel's illegal behaviors in the embodiment of the present invention includes:

[0048] 101. Collecting sound signals and image signals respectively;

[0049] In this embodiment, the sound signal is collected by a sound sensor; wherein the sound sensor includes a pickup and a microphone;

[0050] The image signal is collected by an image sensor; wherein the image sensor includes a camera.

[0051] 102. Preprocess the collected sound signals and image signals respectively;

[0052] In this embodiment, the collected sound signal is subjected to denoising, feature extraction and normalization processing to obtain a pre-processed sound signal;

[0053] The collected image signal is subjected to denoising, image scaling and cropping, and grayscale processing to obtain a preprocessed image signal.

[0054] 103. Through the analysis model, the pre-processed sound signal and image signal are intelligently identified and judged for illegal behaviors.

[0055] In this embodiment, the analysis model includes a voiceprint recognition model and an image recognition model;

[0056] Constructing a sound training set, and using the sound training set to train the voiceprint recognition model to obtain a trained voiceprint recognition model; using the trained voiceprint recognition model to recognize the collected real-time sound signals and identify illegal behaviors; wherein the sound training set is the collected sound signals and their corresponding annotated sales behaviors; the annotated sales behaviors include: illegal behaviors and non-illegal behaviors;

[0057] An image training set is constructed, and an image recognition model is trained using the image training set to obtain a trained image recognition model; the trained image recognition model is used to recognize the collected real-time image signals to identify illegal behaviors; wherein the image training set includes: collected image signals and their corresponding annotated sales behaviors; the annotated sales behaviors include illegal behaviors and non-illegal behaviors.

[0058] 104. Transmitting the identified violations to the monitoring terminal;

[0059] In this embodiment, based on the identified violations, analysis reports are regularly generated and transmitted to the monitoring end.

[0060] This embodiment uses some pre-set illegal words or behaviors, voiceprint recognition, image recognition and other perception technologies, combined with analysis models to timely discover some illegal behaviors of sales personnel, and warn management personnel at the first time, intervene in time, and prevent sales risks. It can enable management personnel to upgrade their post-passive handling of misleading sales behaviors to timely control of the sales process, and obtain audio and video evidence in time.

[0061] See also Figure 2 The second embodiment of the management method for intelligently identifying the illegal behavior of sales personnel in the embodiment of the present invention includes:

[0062] 201. Use the AI ​​analysis model to compare the sound collected by the microphone with the words that are clearly prohibited from use in the pre-collected sales activities to determine whether there is any suspected violation of the regulations;

[0063] 202. The AI ​​analysis model is used to determine the similarity between the body movements and behaviors captured by the camera and the pre-set violations. Behaviors that are similar can be identified as suspicious violations;

[0064] Among them, the AI ​​analysis model can improve its intelligent judgment ability and accuracy through continuous training.

[0065] This embodiment uses an AI analysis model to intelligently identify the collected sounds and images, and immediately sends suspected illegal sales behaviors to the mobile phones of internal management personnel, and provides audio and video files generated during the illegal behavior for internal management personnel to review. Internal management personnel can promptly review and ultimately determine whether the behavior is illegal, and can stop sales personnel in time to prevent the situation from escalating. They can also control the process, reduce complaints, and have a certain deterrent effect on sales personnel, thereby improving the company's management level.

[0066] The above describes the management method for intelligently distinguishing the illegal behaviors of sales personnel in the embodiment of the present invention. The following describes the management system for intelligently distinguishing the illegal behaviors of sales personnel in the embodiment of the present invention. Figure 3 In one embodiment of the present invention, a management system for intelligently identifying sales personnel's illegal behaviors includes:

[0067] The acquisition module 301 is used to respectively acquire sound signals and image signals;

[0068] In this embodiment, the acquisition module 301 includes: collecting sound signals through a sound sensor; wherein the sound sensor includes a pickup and a microphone;

[0069] The image signal is collected by an image sensor; wherein the image sensor includes a camera.

[0070] The preprocessing module 302 is used to preprocess the collected sound signal and image signal respectively;

[0071] In this embodiment, the preprocessing module 302 includes: performing denoising, feature extraction and normalization processing on the collected sound signal to obtain a preprocessed sound signal;

[0072] The collected image signal is subjected to denoising, image scaling and cropping, and grayscale processing to obtain a preprocessed image signal.

[0073] The intelligent identification module 303 is used to intelligently identify and identify illegal behaviors on the pre-processed sound signals and image signals through an analysis model.

[0074] In this embodiment, the analysis model includes a voiceprint recognition model and an image recognition model;

[0075] Constructing a sound training set, and using the sound training set to train the voiceprint recognition model to obtain a trained voiceprint recognition model; using the trained voiceprint recognition model to recognize the collected real-time sound signals and identify illegal behaviors; wherein the sound training set is the collected sound signals and their corresponding annotated sales behaviors; the annotated sales behaviors include: illegal behaviors and non-illegal behaviors;

[0076] An image training set is constructed, and an image recognition model is trained using the image training set to obtain a trained image recognition model; the trained image recognition model is used to recognize the collected real-time image signals to identify illegal behaviors; wherein the image training set includes: collected image signals and their corresponding annotated sales behaviors; the annotated sales behaviors include illegal behaviors and non-illegal behaviors.

[0077] An analysis module 304, for transmitting the identified illegal behavior to a monitoring terminal;

[0078] In this embodiment, based on the identified violations, analysis reports are regularly generated and transmitted to the monitoring end.

[0079] This embodiment uses perception technologies such as voiceprint recognition and image recognition to identify standard illegal words and behaviors, and combines AI decision analysis model algorithms through continuous training to improve intelligent identification capabilities and enhance the level of management personnel's in-process supervision and management.

[0080] above Figure 3 The management system for intelligently identifying sales personnel's illegal behaviors in the embodiment of the present invention is described in detail from the perspective of modular functional entities, and the electronic device in the embodiment of the present invention is described in detail from the perspective of hardware processing.

[0081] Figure 4 7 is a schematic diagram of the structure of an electronic device provided by an embodiment of the present invention. The electronic device 700 may have relatively large differences due to different configurations or performances, and may include one or more processors (central processing unit, CPU) 710 (for example, one or more processors) and a memory 720, and one or more storage media 730 (for example, one or more mass storage devices) storing application programs 733 or data 732. Among them, the memory 720 and the storage medium 730 can be temporary storage or permanent storage. The program stored in the storage medium 730 may include one or more modules (not shown in the figure), and each module may include a series of instruction operations in the electronic device 700. Furthermore, the processor 710 may be configured to communicate with the storage medium 730 to execute a series of instruction operations in the storage medium 730 on the electronic device 700.

[0082] The electronic device 700 may also include one or more power supplies 740, one or more wired or wireless network interfaces 750, one or more input and output interfaces 750, and / or one or more operating systems 731, such as Windows Server, Mac OS X, Unix, Linux, FreeBSD, etc. It will be appreciated by those skilled in the art that Figure 4 The structure of the electronic device shown does not constitute a limitation on the electronic device, and may include more or less components than shown in the figure, or combine some components, or arrange the components differently.

[0083] The present invention also provides a computer-readable storage medium, which may be a non-volatile computer-readable storage medium or a volatile computer-readable storage medium. Instructions are stored in the computer-readable storage medium. When the instructions are executed on a computer, the computer executes the steps of a management method for intelligently identifying violations of sales personnel.

[0084] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working process of the above-described system, device, or unit can refer to the corresponding process in the aforementioned method embodiment and will not be repeated here.

[0085] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM), random access memory (RAM), disk or optical disk, etc., various media that can store program codes.

[0086] As described above, the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features thereof may be replaced by equivalents. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A management method for intelligently identifying sales personnel's illegal behaviors, characterized in that: include: Collecting sound signals and image signals respectively; Preprocessing the collected sound signals and image signals respectively; The pre-processed sound and image signals are intelligently identified and judged for violations through the analysis model.

2. The management method for intelligently identifying sales personnel's illegal behaviors according to claim 1 is characterized in that: The collecting of sound information and image signals respectively includes: The sound signal is collected by a sound sensor; wherein the sound sensor includes a pickup and a microphone; The image signal is collected by an image sensor; wherein the image sensor includes a camera.

3. The management method for intelligently identifying sales personnel's illegal behaviors according to claim 1 is characterized in that: The preprocessing of the collected sound signal and image signal includes: The collected sound signal is subjected to denoising, feature extraction and normalization processing to obtain a pre-processed sound signal; The collected image signal is subjected to denoising, image scaling and cropping, and grayscale processing to obtain a preprocessed image signal.

4. The management method for intelligently identifying sales personnel's illegal behaviors according to claim 1 is characterized in that: The intelligent identification and discrimination of illegal behaviors of the pre-processed sound signal and image signal by the analysis model includes: The analysis model includes a voiceprint recognition model and an image recognition model; Constructing a sound training set, and using the sound training set to train the voiceprint recognition model to obtain a trained voiceprint recognition model; using the trained voiceprint recognition model to recognize the collected real-time sound signals and identify illegal behaviors; wherein the sound training set is the collected sound signals and their corresponding annotated sales behaviors; the annotated sales behaviors include: illegal behaviors and non-illegal behaviors; An image training set is constructed, and an image recognition model is trained using the image training set to obtain a trained image recognition model; the trained image recognition model is used to recognize the collected real-time image signals to identify illegal behaviors; wherein the image training set includes: collected image signals and their corresponding annotated sales behaviors; the annotated sales behaviors include illegal behaviors and non-illegal behaviors.

5. The management method for intelligently identifying sales personnel's illegal behaviors according to claim 1 is characterized in that: The method further includes: transmitting the identified illegal behavior to a monitoring terminal; Based on the identified violations, analysis reports are generated regularly and transmitted to the monitoring end.

6. A management system for intelligently identifying sales personnel's illegal behaviors, characterized in that: include: A collection module, used for collecting sound signals and image signals respectively; A preprocessing module, used to preprocess the collected sound signals and image signals respectively; The intelligent identification module is used to intelligently identify and identify violations of pre-processed sound signals and image signals through analysis models.

7. The management system for intelligently identifying sales personnel's illegal behaviors according to claim 6 is characterized in that: The acquisition module comprises: The sound signal is collected by a sound sensor; wherein the sound sensor includes a pickup and a microphone; The image signal is collected by an image sensor; wherein the image sensor includes a camera.

8. The management system for intelligently identifying sales personnel's illegal behaviors according to claim 6 is characterized in that: The preprocessing module comprises: The collected sound signal is subjected to denoising, feature extraction and normalization processing to obtain a pre-processed sound signal; The collected image signal is subjected to denoising, image scaling and cropping, and grayscale processing to obtain a preprocessed image signal.

9. The management system for intelligently identifying sales personnel's illegal behaviors according to claim 6 is characterized in that: The intelligent recognition module comprises: The analysis model includes a voiceprint recognition model and an image recognition model; Constructing a sound training set, and using the sound training set to train the voiceprint recognition model to obtain a trained voiceprint recognition model; using the trained voiceprint recognition model to recognize the collected real-time sound signals and identify illegal behaviors; wherein the sound training set is the collected sound signals and their corresponding annotated sales behaviors; the annotated sales behaviors include: illegal behaviors and non-illegal behaviors; An image training set is constructed, and an image recognition model is trained using the image training set to obtain a trained image recognition model; the trained image recognition model is used to recognize the collected real-time image signals to identify illegal behaviors; wherein the image training set includes: collected image signals and their corresponding annotated sales behaviors; the annotated sales behaviors include illegal behaviors and non-illegal behaviors.

10. The management system for intelligently identifying sales personnel's illegal behaviors according to claim 6 is characterized in that: The system further comprises: an analysis module for transmitting the identified illegal behavior to a monitoring terminal; Based on the identified violations, analysis reports are generated regularly and transmitted to the monitoring end.

Images