A method and device for analyzing customer purchase intention

Abstract

The present application provides a method and device for analyzing customer purchase intention. After acquiring multimedia video data containing shopping guide audio data and customer image data; parsing the multimedia video data to obtain corresponding shopping guide audio data and customer image data; extracting customer key point information from the customer image data, performing action recognition through a key point timing network, and generating a first recognition result; converting the shopping guide audio data into text information, analyzing the text information through a preset knowledge graph with time, and generating a second recognition result; inputting the first recognition result and the second recognition result into a preset fusion network to generate a prediction result corresponding to the multimedia video data; determining the customer purchase probability based on the prediction result to realize customer purchase intention analysis. The present application realizes customer purchase intention analysis by integrating customer key points with sound knowledge graphs, and further promotes store product sales.

Description

Technical Field

[0001] The present application relates to the field of motion recognition technology, and in particular, to a method and device for analyzing customer purchase intention. Background Art

[0002] At present, the main method for analyzing customer purchase intention is to use deep learning methods to obtain the movements of people in the video; or to convert the sound into text through voice recognition technology, and then obtain the theme of the voice through knowledge graph. However, if only one method is used to analyze customer purchase intention, the analysis result is not accurate enough and cannot maximize the promotion of store product sales. Summary of the invention

[0003] In view of the problems in the above content, the present application provides a customer purchase intention analysis method and device, which realizes customer purchase intention analysis by integrating customer key points with sound knowledge graph, and further promotes store product sales.

[0004] In order to achieve the above objectives, this application provides the following technical solutions:

[0005] A method for analyzing customer purchase intention, comprising:

[0006] Acquire multimedia video data including shopping guide audio data and customer image data;

[0007] Parsing the multimedia video data to obtain corresponding shopping guide audio data and customer image data;

[0008] Extracting customer key point information from the customer image data, performing action recognition through a key point sequential network, and generating a first recognition result, wherein the key point sequential network is an action recognition network based on the customer key point information;

[0009] Convert the shopping guide audio data into text information, analyze the text information through a preset knowledge graph with time, and generate a second recognition result, wherein the preset knowledge graph with time is a knowledge graph with keywords as nodes;

[0010] Inputting the first recognition result and the second recognition result into a preset fusion network to generate a prediction result corresponding to the multimedia video data;

[0011] The customer purchase probability is determined based on the prediction results to achieve customer purchase intention analysis.

[0012] Furthermore, the multimedia video data is parsed to obtain corresponding shopping guide audio data and customer image data, including:

[0013] Performing sound separation processing on the multimedia video data to obtain corresponding sound files and generate the shopping guide audio data;

[0014] The multimedia video data is subjected to image separation processing to obtain corresponding customer action videos and generate the customer image data.

[0015] Furthermore, the method for constructing the key point timing network includes:

[0016] Obtain action videos containing key points of the customer and use them as sample data;

[0017] Customer key point information is extracted from the action video, and the customer key point information is used as a training set of a time-based graph neural network. The time-based graph neural network is trained to obtain the key point timing network.

[0018] Furthermore, the method for generating the preset knowledge graph with time includes:

[0019] Obtain text information containing keywords and use it as sample data;

[0020] Keywords are extracted from the text information, and the keywords are used as entities in the knowledge graph to construct the preset knowledge graph with time.

[0021] A customer purchase intention analysis device, comprising:

[0022] A first processing unit, used to obtain multimedia video data including shopping guide audio data and customer image data;

[0023] A second processing unit is used to parse the multimedia video data to obtain corresponding shopping guide audio data and customer image data;

[0024] A third processing unit is used to extract customer key point information from the customer image data, perform action recognition through a key point sequential network, and generate a first recognition result, wherein the key point sequential network is an action recognition network based on the customer key point information;

[0025] a fourth processing unit, configured to convert the shopping guide audio data into text information, analyze the text information through a preset knowledge graph with time, and generate a second recognition result, wherein the preset knowledge graph with time is a knowledge graph with keywords as nodes;

[0026] a fifth processing unit, configured to input the first recognition result and the second recognition result into a preset fusion network to generate a prediction result corresponding to the multimedia video data;

[0027] The sixth processing unit is used to determine the customer purchase probability according to the prediction result to realize the customer purchase intention analysis.

[0028] Furthermore, the second processing unit is specifically configured to:

[0029] Performing sound separation processing on the multimedia video data to obtain corresponding sound files and generate the shopping guide audio data;

[0030] The multimedia video data is subjected to image separation processing to obtain corresponding customer action videos and generate the customer image data.

[0031] Furthermore, the third processing unit is further configured to:

[0032] Obtain action videos containing key points of the customer and use them as sample data;

[0033] Customer key point information is extracted from the action video, and the customer key point information is used as a training set of a time-based graph neural network. The time-based graph neural network is trained to obtain the key point timing network.

[0034] Furthermore, the fourth processing unit is further configured to:

[0035] Obtain text information containing keywords and use it as sample data;

[0036] Keywords are extracted from the text information, and the keywords are used as entities in the knowledge graph to construct the preset knowledge graph with time.

[0037] A storage medium includes a stored program, wherein when the program is executed, the device where the storage medium is located is controlled to execute the customer purchase intention analysis method as described above.

[0038] An electronic device comprises at least one processor, and at least one memory and a bus connected to the processor; wherein the processor and the memory communicate with each other via the bus; and the processor is used to call program instructions in the memory to execute the customer purchase intention analysis method as described above.

[0039] The customer purchase intention analysis method and device described in the present application, after obtaining multimedia video data containing shopping guide audio data and customer image data; parsing the multimedia video data to obtain corresponding shopping guide audio data and customer image data; extracting customer key point information from the customer image data, performing action recognition through a key point timing network, and generating a first recognition result; converting the shopping guide audio data into text information, analyzing the text information through a preset knowledge graph with time, and generating a second recognition result; inputting the first recognition result and the second recognition result into a preset fusion network to generate a prediction result corresponding to the multimedia video data; determining the customer purchase probability based on the prediction result to achieve customer purchase intention analysis. The present application achieves customer purchase intention analysis by integrating customer key points with sound knowledge graphs, and further promotes store product sales. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0041] Figure 1 A flowchart of a method for analyzing customer purchase intention disclosed in an embodiment of the present application;

[0042] Figure 2 A schematic diagram of a method for analyzing customer purchase intention disclosed in an embodiment of the present application;

[0043] Figure 3 A schematic diagram of the structure of a device for analyzing customer purchase intention disclosed in an embodiment of the present application;

[0044] Figure 4 A schematic diagram of the structure of an electronic device disclosed in an embodiment of the present application. DETAILED DESCRIPTION

[0045] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0046] Please see attached Figure 1 , is a flow chart of a method for analyzing customer purchase intention provided in an embodiment of the present application. Figure 1As shown, the embodiment of the present application provides a method for analyzing customer purchase intention, which includes the following steps:

[0047] S101: Acquire multimedia video data including shopping guide audio data and customer image data;

[0048] In this step, multimedia video data is obtained through on-site multimedia equipment, which can be a video camera or other audio and video equipment. It should be noted that multimedia video data includes shopping guide audio data and customer image data, so the corresponding multimedia equipment requires specific audio collection and image collection functions. It should be noted that multimedia video data is collected through multimedia equipment on the store site. The customer's position can be located by looking at the image video to see whether the customer is wearing work clothes in the store.

[0049] It should be further explained that the embodiment of the present application only uses the customer's body key point information, and does not use the customer's private information (such as gender, face), so as to ensure the customer's privacy.

[0050] S102: parsing the multimedia video data to obtain corresponding shopping guide audio data and customer image data;

[0051] In this step, the multimedia video data is parsed to obtain corresponding shopping guide audio data and customer image data, including: performing sound separation processing on the multimedia video data to obtain corresponding sound files and generate the shopping guide audio data; performing image separation processing on the multimedia video data to obtain corresponding customer action videos and generate the customer image data.

[0052] It should be noted that the sound file and the action video need to be separated from the multimedia video data in order to obtain the corresponding shopping guide audio data and customer image data.

[0053] S103: extracting customer key point information from the customer image data, performing action recognition through a key point sequential network, and generating a first recognition result, wherein the key point sequential network is an action recognition network based on the customer key point information;

[0054] In this step, it is necessary to first extract the customer's key point information from the customer image data, perform action recognition through the key point temporal network, and generate the first recognition result, such as Figure 2 As shown, specifically, the preset action recognition network is an action recognition network based on customer key point information.

[0055] It should be noted that the method for constructing the key point timing network includes: obtaining an action video containing customer key points and using it as sample data; extracting customer key point information from the action video, using the customer key point information as a training set for a time-based graph neural network, training the time-based graph neural network, and obtaining the key point timing network.

[0056] S104: converting the shopping guide audio data into text information, analyzing the text information through a preset knowledge graph with time, and generating a second recognition result, wherein the preset knowledge graph with time is a knowledge graph with keywords as nodes;

[0057] In this step, the shopping guide audio data needs to be converted into text information through a voice conversion method, and the text information is analyzed through a preset knowledge graph to generate a second recognition result, such as Figure 2 As shown, the preset time-based knowledge graph is a knowledge graph with keywords as nodes.

[0058] It should be noted that the method for generating the preset knowledge graph includes: obtaining text information containing keywords and using it as sample data; extracting keywords from the text information, using the keywords as entities in the knowledge graph, and constructing the preset knowledge graph with time.

[0059] S105: Inputting the first recognition result and the second recognition result into a preset fusion network to generate a prediction result corresponding to the multimedia video data.

[0060] S106: Determine the customer purchase probability according to the prediction result to analyze the customer's purchase intention.

[0061] The embodiment of the present application provides a method for analyzing customer purchase intention. After acquiring multimedia video data containing shopping guide audio data and customer image data; parsing the multimedia video data to obtain corresponding shopping guide audio data and customer image data; extracting customer key point information from the customer image data, performing action recognition through a key point timing network, and generating a first recognition result; converting the shopping guide audio data into text information, analyzing the text information through a preset knowledge graph with time, and generating a second recognition result; inputting the first recognition result and the second recognition result into a preset fusion network to generate a prediction result corresponding to the multimedia video data; determining the customer purchase probability based on the prediction result to achieve customer purchase intention analysis. The embodiment of the present application achieves customer purchase intention analysis by integrating customer key points with the sound knowledge graph, thereby further promoting store product sales.

[0062] See also Figure 3Based on the customer purchase intention analysis method disclosed in the above embodiment, this embodiment correspondingly discloses a customer purchase intention analysis device, which includes:

[0063] The first processing unit 301 is used to obtain multimedia video data including shopping guide audio data and customer image data;

[0064] The second processing unit 302 is used to parse the multimedia video data to obtain corresponding shopping guide audio data and customer image data;

[0065] The third processing unit 303 is used to extract customer key point information from the customer image data, perform action recognition through a key point sequential network, and generate a first recognition result, wherein the key point sequential network is an action recognition network based on customer key point information;

[0066] The fourth processing unit 304 is used to convert the shopping guide audio data into text information, analyze the text information through a preset knowledge graph with time, and generate a second recognition result, wherein the preset knowledge graph with time is a knowledge graph with keywords as nodes;

[0067] A fifth processing unit 305, configured to input the first recognition result and the second recognition result into a preset fusion network to generate a prediction result corresponding to the multimedia video data;

[0068] The sixth processing unit 306 is used to determine the customer purchase probability according to the prediction result to implement the customer purchase intention analysis.

[0069] Furthermore, the second processing unit 302 is specifically configured to:

[0070] Performing sound separation processing on the multimedia video data to obtain corresponding sound files and generate the shopping guide audio data;

[0071] The multimedia video data is subjected to image separation processing to obtain corresponding customer action videos and generate the customer image data.

[0072] Furthermore, the third processing unit 303 is further configured to:

[0073] Obtain action videos containing key points of the customer and use them as sample data;

[0074] Customer key point information is extracted from the action video, and the customer key point information is used as a training set of a time-based graph neural network. The time-based graph neural network is trained to obtain the key point timing network.

[0075] Furthermore, the fourth processing unit 304 is further configured to:

[0076] Obtain text information containing keywords and use it as sample data;

[0077] Keywords are extracted from the text information, and the keywords are used as entities in the knowledge graph to construct the preset knowledge graph with time.

[0078] The customer purchase intention analysis device includes a processor and a memory. The first processing unit, the second processing unit, the third processing unit, the fourth processing unit, the fifth processing unit and the sixth processing unit are all stored in the memory as program units, and the processor executes the program units stored in the memory to realize corresponding functions.

[0079] The processor contains a kernel, which retrieves the corresponding program unit from the memory. One or more kernels can be set, and the kernel parameters can be adjusted to achieve the fusion of customer key points and sound knowledge graphs to achieve customer purchase intention analysis and further promote the purpose of store product sales.

[0080] An embodiment of the present application provides a storage medium on which a program is stored. When the program is executed by a processor, the customer purchase intention analysis method is implemented.

[0081] An embodiment of the present application provides a processor, which is used to run a program, wherein the customer purchase intention analysis method is executed when the program is running.

[0082] The present application embodiment provides an electronic device, such as Figure 4 As shown, the electronic device 40 includes at least one processor 401, and at least one memory 402 and a bus 403 connected to the processor; wherein the processor 401 and the memory 402 communicate with each other through the bus 403; the processor 401 is used to call the program instructions in the memory 402 to execute the above-mentioned customer purchase intention analysis method.

[0083] The electronic devices in this article can be servers, PCs, PADs, mobile phones, etc.

[0084] The present application also provides a computer program product, which, when executed on a data processing device, is suitable for executing a program for initializing the following method steps:

[0085] Acquire multimedia video data including shopping guide audio data and customer image data;

[0086] Parsing the multimedia video data to obtain corresponding shopping guide audio data and customer image data;

[0087] Extracting customer key point information from the customer image data, performing action recognition through a key point sequential network, and generating a first recognition result, wherein the key point sequential network is an action recognition network based on the customer key point information;

[0088] Convert the shopping guide audio data into text information, analyze the text information through a preset knowledge graph with time, and generate a second recognition result, wherein the preset knowledge graph with time is a knowledge graph with keywords as nodes;

[0089] Inputting the first recognition result and the second recognition result into a preset fusion network to generate a prediction result corresponding to the multimedia video data;

[0090] The customer purchase probability is determined based on the prediction results to achieve customer purchase intention analysis.

[0091] Furthermore, the multimedia video data is parsed to obtain corresponding shopping guide audio data and customer image data, including:

[0092] Performing sound separation processing on the multimedia video data to obtain corresponding sound files and generate the shopping guide audio data;

[0093] The multimedia video data is subjected to image separation processing to obtain corresponding customer action videos and generate the customer image data.

[0094] Furthermore, the method for constructing the key point timing network includes:

[0095] Obtain action videos containing key points of the customer and use them as sample data;

[0096] Customer key point information is extracted from the action video, and the customer key point information is used as a training set of a time-based graph neural network. The time-based graph neural network is trained to obtain the key point timing network.

[0097] Furthermore, the method for generating the preset knowledge graph with time includes:

[0098] Obtain text information containing keywords and use it as sample data;

[0099] Keywords are extracted from the text information, and the keywords are used as entities in the knowledge graph to construct the preset knowledge graph with time.

[0100] The present application is described by flowcharts and / or block diagrams of the methods, devices (systems), and computer program products of the embodiments of the present application. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of the processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0101] In a typical configuration, the device includes one or more processors (CPU), memory and bus. The device may also include input / output interface, network interface and the like.

[0102] The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM, and the memory includes at least one memory chip. The memory is an example of a computer-readable medium.

[0103] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0104] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0105] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code.

[0106] The above are only embodiments of the present application and are not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included within the scope of the claims of the present application.

Claims

1. A method for analyzing customer purchase intention, characterized in that: include: Acquire multimedia video data including shopping guide audio data and customer image data; wherein the customer image data locates the customer by whether the customer is wearing work clothes in the store; Parsing the multimedia video data to obtain corresponding shopping guide audio data and customer image data; Extracting customer key point information from the customer image data, performing action recognition through a key point sequential network, and generating a first recognition result, wherein the key point sequential network is an action recognition network based on the customer key point information; Convert the shopping guide audio data into text information, analyze the text information through a preset knowledge graph with time, and generate a second recognition result, wherein the preset knowledge graph with time is a knowledge graph with keywords as nodes; Inputting the first recognition result and the second recognition result into a preset fusion network to generate a prediction result corresponding to the multimedia video data; The customer purchase probability is determined based on the prediction results to achieve customer purchase intention analysis.

2. The method according to claim 1, characterized in that The step of parsing the multimedia video data to obtain corresponding shopping guide audio data and customer image data includes: Performing sound separation processing on the multimedia video data to obtain corresponding sound files and generate the shopping guide audio data; The multimedia video data is subjected to image separation processing to obtain corresponding customer action videos and generate the customer image data.

3. The method according to claim 1, characterized in that The method for constructing the key point timing network comprises: Obtain action videos containing key points of the customer and use them as sample data; Customer key point information is extracted from the action video, and the customer key point information is used as a training set of a time-based graph neural network. The time-based graph neural network is trained to obtain the key point timing network.

4. The method according to claim 1, characterized in that: The method for generating the preset knowledge graph with time includes: Obtain text information containing keywords and use it as sample data; Keywords are extracted from the text information, and the keywords are used as entities in the knowledge graph to construct the preset knowledge graph with time.

5. A customer purchase intention analysis device, characterized in that: include: The first processing unit is used to obtain multimedia video data including shopping guide audio data and customer image data; wherein the customer image data locates the customer's position according to whether the customer is wearing work clothes in the store; A second processing unit is used to parse the multimedia video data to obtain corresponding shopping guide audio data and customer image data; A third processing unit is used to extract customer key point information from the customer image data, perform action recognition through a key point sequential network, and generate a first recognition result, wherein the key point sequential network is an action recognition network based on the customer key point information; a fourth processing unit, configured to convert the shopping guide audio data into text information, analyze the text information through a preset knowledge graph with time, and generate a second recognition result, wherein the preset knowledge graph with time is a knowledge graph with keywords as nodes; a fifth processing unit, configured to input the first recognition result and the second recognition result into a preset fusion network to generate a prediction result corresponding to the multimedia video data; The sixth processing unit is used to determine the customer purchase probability according to the prediction result to realize the customer purchase intention analysis.

6. The device according to claim 5, characterized in that The second processing unit is specifically used for: Performing sound separation processing on the multimedia video data to obtain corresponding sound files and generate the shopping guide audio data; The multimedia video data is subjected to image separation processing to obtain a corresponding customer action video and generate the customer image data.

7. The device according to claim 5, characterized in that The third processing unit is further specifically configured to: Obtain action videos containing key points of the customer and use them as sample data; Customer key point information is extracted from the action video, and the customer key point information is used as a training set of a time-based graph neural network. The time-based graph neural network is trained to obtain the key point timing network.

8. The device according to claim 5, characterized in that The fourth processing unit is further specifically configured to: Obtain text information containing keywords and use it as sample data; Keywords are extracted from the text information, and the keywords are used as entities in the knowledge graph to construct the preset knowledge graph with time.

9. A storage medium, characterized in that: The storage medium includes a stored program, wherein when the program is executed, the device where the storage medium is located is controlled to execute the customer purchase intention analysis method according to any one of claims 1 to 4.

10. An electronic device, characterized in that: The electronic device includes at least one processor, and at least one memory and a bus connected to the processor; wherein the processor and the memory communicate with each other via the bus; the processor is used to call program instructions in the memory to execute the customer purchase intention analysis method as described in any one of claims 1 to 4.

Images