Cigarette retail space-time data cloud edge collaborative determination system, method, device and medium

Abstract

The application discloses a cigarette retail space-time data cloud edge collaborative determination system, method, equipment and medium, and relates to the technical field of artificial intelligence. The system comprises an edge acquisition module, an analysis module, a voice recognition module, a price extraction module and a cloud analysis module. The acquisition module can acquire video data and audio data of the settlement area where the cigarette is retailed at the time, and the video data and the audio data correspond to each other through a timestamp. The analysis module can analyze frame images in the video data and obtain category information of each cigarette. The voice recognition module can extract a voice segment from the audio data according to the category information of the cigarette and the timestamp, and perform text recognition on the voice segment to obtain text information of the voice segment. The price extraction module can extract a retail price of the cigarette in the text information. The cloud analysis module can fuse the cigarette retail price containing space-time information. The system can quickly obtain the cigarette retail space-time data and improve the accuracy.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of artificial intelligence, in particular to a cigarette retail space-time data cloud edge collaborative determination system, method, device and medium. BACKGROUND

[0002] It is difficult to obtain cigarette retail market data, which is a great challenge for the high-quality development of the tobacco industry. The retail guide price of cigarettes has a planning nature, while the actual price of cigarettes contains market demand information, and the degree of coincidence between the two is not high, which will lead to the difficulty of the existing cigarette retail market analysis model to adapt to the actual development of the cigarette industry in the new era. The difficulties of current cigarette retail market data collection include at least the following aspects: first, the informationization level of retail terminals is not high, and the cost of collecting market information such as retail price by traditional market research methods is too high; second, the lack of key market factors such as the profit situation of cigarette retailers, cigarette brands and cigarette price points makes the means of analyzing and regulating the market limited; third, the existing data collection lacks time series and spatial elements, and cannot better reflect the time and space dynamic information of the market, which is not conducive to more effective resource allocation. SUMMARY

[0003] In view of the above defects or shortcomings in the related art, it is desirable to provide a cigarette retail space-time data cloud edge collaborative determination system, method, device and medium, which can quickly obtain cigarette retail prices containing space-time information to obtain accurate cigarette retail space-time data.

[0004] In a first aspect, the present application provides a cigarette retail space-time data cloud edge collaborative determination system, which comprises:

[0005] An edge acquisition module configured to acquire video data and audio data of a terminal settlement area where the cigarette retail is located, wherein the video data and the audio data correspond to time stamp and spatial information;

[0006] An edge analysis module electrically connected to the edge acquisition module, configured to analyze frame images in the video data, obtain category information of each cigarette, and record space-time information; wherein the video data is Each represents a video frame at time t i , and the category data of the cigarette is obtained by frame-by-frame analysis Wherein represents the cigarette category information corresponding to the video frame at time t i ;

[0007] An edge-end speech recognition module electrically connected to the edge-end analysis module is configured to adaptively extract speech segments from the audio data based on the cigarette category information and the timestamp and spatial information; wherein the speech segment data is... Each Indicates t i The audio frames at specific timestamps are used to align the video data from the edge acquisition module with the audio data from the speech recognition module. This can be represented as follows:

[0008] Cigarette category data:

[0009] Voice segment data:

[0010] Timestamp: T = {t1, t2, t3, ..., t} n}

[0011] Data fusion: here This represents the combination of category data for the i-th video frame and audio segment data for the audio frame;

[0012] The edge-side speech recognition module compresses bimodal data (W,A) containing category data W (including spatiotemporal information of cigarettes) and speech segment data A into (R). Then, R is uploaded to the cloud deployed in the information center. In the cloud, (R)→(W,A) is decompressed, and text recognition is performed on speech segment data A to obtain its text information, i.e., (A)→(P), where (P) is the price text data extracted after speech recognition, P={p1,p2,p3,…,p… n}, p i This represents the i-th retail price among multiple price groups;

[0013] The final cigarette category was determined to be C. z =max{h(W)}, where h(W) refers to the frequency of cigarette categories in the category data. max{h(W)} represents the cigarette category with the highest frequency.

[0014] The edge-end price extraction module, electrically connected to the edge-end speech recognition module, is configured to extract prices via p i The index P i_ind The price text data extracted after speech recognition is P = {p1, p2, p3, ..., p...} n The final price P is determined in} z The calculation formula is as follows:

[0015]

[0016] In the above formula, K fa price weight representing a voice-recognized retail price, p0 represents a guide price of a cigarette category C z obtained by the user; a time weight representing a voice-recognized retail price, Δt i representing a difference between a time of audio extraction and a time of cigarette category recognition,

[0017] P z = {max(p i_ind )→p i}

[0018] In the above formula, max(p i_ind )→p i represents a price corresponding to the maximum value;

[0019] a cloud analysis module configured to fuse the category information of the cigarette and the text information of the voice segment to obtain a cigarette retail price containing the spatiotemporal information, and write the cigarette retail price into an information management system to obtain cigarette retail spatiotemporal data.

[0020] Optionally, in some embodiments of the present application, the edge analysis module comprises a positioning unit and an output unit connected to each other;

[0021] The positioning unit is configured to sequentially locate positions of the cigarettes in the frame images in the order of the timestamps using a target detection neural network model, and generate a full-range moving track of the cigarettes; and

[0022] The output unit is configured to output the category information of the cigarettes if the end point of the full-range moving track of the cigarettes is a customer.

[0023] Optionally, in some embodiments of the present application, the edge analysis module further comprises a framing unit and a preprocessing unit connected to each other;

[0024] The framing unit is configured to perform a framing operation on the video data; and the preprocessing unit is configured to extract the frame images from the framing result according to a first preset time interval and perform a noise reduction operation.

[0025] Optionally, in some embodiments of the present application, the edge voice recognition module comprises a first determination unit and a first splicing unit connected to each other;

[0026] The first determination unit is configured to determine a first time at which the category information is recognized, and the timestamp comprises the first time; and

[0027] The first splicing unit is configured to acquire voice data in a second preset time interval before the first time point based on the first time point, splice the voice data with recording data in a third preset time interval after the first time point, and obtain the voice segment.

[0028] Optionally, in some embodiments of the present application, the edge price extraction module comprises a matching unit configured to traverse each character of the text information, and sequentially match each character with a preset regular expression to obtain the retail price of the cigarette.

[0029] Optionally, in some embodiments of the present application, the edge price extraction module further comprises a second determination unit and a correction unit connected to each other.

[0030] The second determination unit is configured to reversely determine a second time point corresponding to the retail price in the audio data, and the timestamp comprises the second time point; and

[0031] The correction unit is configured to correct the retail price according to a guide price corresponding to the category information, a first time point at which the category information is identified, and the second time point, to obtain a final retail price of the cigarette.

[0032] Optionally, in some embodiments of the present application, the edge collection module comprises a detection unit, a recording unit and a second splicing unit connected to each other.

[0033] The detection unit is configured to detect a frame image in the video data to determine whether there is a cigarette sales behavior in the settlement area.

[0034] The recording unit is configured to save historical recording data and start recording for a preset time period again to obtain current recording data if there is a cigarette sales behavior in the settlement area; and

[0035] The second splicing unit is configured to splice the historical recording data and the current recording data, and perform decomposition and overlay operations on the current recording data in the spliced recording data to obtain the audio data.

[0036] In a second aspect, the present application provides a cigarette retail space-time data cloud edge collaborative determination method, which comprises:

[0037] Collecting video data and audio data of a terminal settlement area where a cigarette is sold, the video data and the audio data being corresponding to time stamp and space information;

[0038] analyze frame images in the video data to obtain category information of each cigarette, and record space-time information;

[0039] adaptively intercept a voice segment from the audio data according to the category information of the cigarette and the timestamp and space information, and perform text recognition on the voice segment to obtain text information of the voice segment;

[0040] extract a retail price of the cigarette in the text information;

[0041] fuse the category information of the cigarette and the text information of the voice segment to obtain a cigarette retail price containing the space-time information, and write the cigarette retail price into an information management system to obtain cigarette retail space-time data.

[0042] In a third aspect, the present application provides an electronic device, which comprises a processor and a memory, and the memory stores at least one instruction, at least one program, a code set or an instruction set, which are loaded and executed by the processor to implement the steps of the cigarette retail space-time data cloud-edge collaborative method in the second aspect.

[0043] In a fourth aspect, the present application provides a computer-readable storage medium, which stores one or more programs, and the one or more programs can be executed by one or more processors to implement the steps of the cigarette retail space-time data cloud-edge collaborative method in the second aspect.

[0044] As can be seen from the above technical solutions, the embodiments of the present application have the following advantages:

[0045] The embodiments of the present application provide a cigarette retail space-time data cloud-edge collaborative determination system, method, device and medium. The original video data and audio data in the terminal settlement area are directly collected when the cigarette is retailed, that is, the data is real-time and reliable. Then, the category information of each cigarette is obtained by analyzing frame images in the video data. The text information is obtained by intercepting a voice segment from the audio data and performing recognition based on the category information of the cigarette and the timestamp. The retail price of the cigarette in the text information is extracted. Then, the category information of the cigarette and the text information of the voice segment are fused to obtain a cigarette retail price containing space-time information, which is written into an information management system. Therefore, the cigarette retail space-time data can be quickly obtained, and the accuracy is improved. BRIEF DESCRIPTION OF DRAWINGS

[0046] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the accompanying drawings needed in the embodiments will be briefly introduced as follows. Obviously, the drawings in the following description are only some embodiments of the present application, and for those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0047] Figure 1 A structural block diagram of a cigarette retail space-time data cloud edge collaborative determination system provided by an embodiment of the present application is shown in the figure.

[0048] Figure 2 A structural block diagram of another cigarette retail space-time data cloud edge collaborative determination system provided by an embodiment of the present application is shown in the figure.

[0049] Figure 3 A recording data processing process schematic diagram provided by an embodiment of the present application is shown in the figure.

[0050] Figure 4 Another recording data processing process schematic diagram provided by an embodiment of the present application is shown in the figure.

[0051] Figure 5 A structural block diagram of another cigarette retail space-time data cloud edge collaborative determination system provided by an embodiment of the present application is shown in the figure.

[0052] Figure 6 A scene schematic diagram of a customer taking cigarettes first and paying later provided by an embodiment of the present application is shown in the figure, in which Figure 6 (a) represents a customer taking cigarettes, Figure 6 (b) represents a customer paying;

[0053] Figure 7 A scene schematic diagram of a customer paying first and taking cigarettes later provided by an embodiment of the present application is shown in the figure, in which Figure 7 (a) represents a customer paying, Figure 7 (b) represents a customer taking cigarettes;

[0054] Figure 8 A structural block diagram of another cigarette retail space-time data cloud edge collaborative determination system provided by an embodiment of the present application is shown in the figure.

[0055] Figure 9 A structural block diagram of a cigarette retail space-time data cloud edge collaborative determination system provided by another embodiment of the present application is shown in the figure.

[0056] Figure 10 A structural block diagram of another cigarette retail space-time data cloud edge collaborative determination system provided by another embodiment of the present application is shown in the figure.

[0057] Figure 11 A scene schematic diagram of two or more customers buying cigarettes provided by an embodiment of the present application is shown in the figure.

[0058] Figure 12 A voice recognition process schematic diagram provided for the embodiment of the present application;

[0059] Figure 13 A basic flow schematic diagram of a cigarette retail space-time data cloud edge collaborative determination method provided for the embodiment of the present application;

[0060] Figure 14 A structural block diagram of an electronic device provided for the embodiment of the present application. DETAILED DESCRIPTION

[0061] The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative work fall within the scope of protection of the present application.

[0062] In order to make the above-mentioned purposes, features and advantages of the present application more obvious and easy to understand, the present application will be further described in detail below with reference to the drawings and specific embodiments.

[0063] It should be noted that the embodiments in the present application and the features in the embodiments can be combined with each other without conflict, and the following embodiments will be described in detail. Figures 1 to 14 The cigarette retail space-time data cloud edge collaborative determination system, method, device and medium provided by the embodiments of the present application are described in detail.

[0064] Please refer to Figure 1As shown in FIG. 1, it is a structural block diagram of a cigarette retail space-time data cloud edge collaborative determination system provided by an embodiment of the present application. The cigarette retail space-time data cloud edge collaborative determination system 100 comprises an edge end acquisition module 101, an edge end analysis module 102 electrically connected with the edge end acquisition module 101, an edge end voice recognition module 103 electrically connected with the edge end analysis module 102, an edge end price extraction module 104 electrically connected with the edge end voice recognition module 103, and a cloud end analysis module 105, and the electrical connection can include any one of wired physical connection and wireless communication connection. Among them, the edge end acquisition module 101 can acquire video data and audio data of a terminal settlement area where the cigarette is sold at the time, and the video data and the audio data correspond to the time stamp and the space information; the edge end analysis module 102 can analyze the frame image in the video data, obtain the category information of each cigarette, and record the space-time information; the edge end voice recognition module 103 can adaptively intercept the voice segment from the audio data according to the category information of the cigarette and the time stamp and the space information, and perform text recognition on the voice segment to obtain the text information of the voice segment; the edge end price extraction module 104 can extract the retail price of the cigarette in the text information; and the cloud end analysis module 105 can fuse the category information of the cigarette and the text information of the voice segment to obtain a cigarette retail price containing space-time information, and write into an information management system to obtain the cigarette retail space-time data.

[0065] Exemplarily, the following will be combined with Figures 2 to 12 to make a detailed description of part of the composition modules of the cigarette retail space-time data cloud edge collaborative determination system 100 in the embodiment of the present application. For example Figure 2 As shown in FIG. 1, the edge end acquisition module 101 comprises but is not limited to a detection unit 1011, a recording unit 1012 and a second splicing unit 1013 connected with each other. Among them, the detection unit 1011 can continuously detect the frame image in the video data to determine whether there is a cigarette sales behavior in the settlement area, for example, the video data is collected by a camera, and when the frame image shows that a person moves outside the counter, it can be determined that there is a cigarette sales behavior in the settlement area. If there is a cigarette sales behavior in the settlement area, the recording unit 1012 can save the historical recording data and start recording again for a preset time to obtain the current recording data, for example, the recording data is collected by a sound pickup device, and the historical recording data is saved as wav_1, the preset time is 1 minute and 30 seconds, and the current recording data is wav_2. For another example, when a new cigarette sales behavior occurs in the settlement area during the recording of wav_2, the wav_2 recording is stopped and the data is saved, and the recording of 1 minute and 30 seconds is started again, named as wav_3. For another example, when a new cigarette sales behavior occurs in the settlement area during the recording of wav_3, the wav_3 recording is stopped and the data is saved, and the recording of 1 minute and 30 seconds is started again, named as wav_4, and so on, until the complete wav_n is recorded, that is, the recording is ended.

[0066] Further, as shown in Figure 3 , the second splicing unit 1013 can splice the historical recording data and the current recording data, and perform decomposition and covering operation on the current recording data in the spliced recording data, to obtain the audio data, for example Figure 4 , divide the 1 minute and 30 seconds into 9 time periods t1, t2,..., t9, each of which is 10 seconds, and the corresponding current recording data is decomposed into segments f1, f2,..., f9, and then the 10th recording is obtained as segment f 10 , that is, the length of the 10th recording is also 10 seconds, and then segment f2 covers segment f1, segment f3 covers segment f2,..., segment f9 covers segment f8, and segment f 10 covers segment f9, and so on. The advantage of this setting is to reduce the calculation amount and only retain the recording before and after the transaction time node, while protecting the privacy of the merchant. In addition, after obtaining the complete wav_n data, the embodiment of the present application can extract the last 20 seconds of the current recording data as a memory voice, and then record 1 minute and 10 seconds from the starting point of the memory voice, and continue to perform decomposition and covering operation, which will not be described here.

[0067] Further, as shown in Figure 5 , the edge analysis module 102 includes but is not limited to a positioning unit 1021 and an output unit 1022 connected to each other, etc. Among them, the positioning unit 1021 can sequentially locate the positions of each cigarette in the frame image according to the chronological order of the time stamp, and generate the full movement trajectory of the cigarette by using a target detection neural network model, for example, the target detection neural network model can be a YOLO model, which can locate and frame the positions of each cigarette in the frame image, and give the category information of the cigarette around the frame. Further, for example, the full movement trajectory of the cigarette can be the placement and recovery of the cigarette by the merchant, or the taking and returning of the cigarette by the customer, etc. In addition, if the end point of the full movement trajectory of the cigarette is the customer, it means that the cigarette is in the settlement state, at this time the output unit 1022 can output the category information of the cigarette, for example Figure 6 , which is a schematic diagram of the scene that the customer takes the cigarette first and then pays, wherein Figure 6 (a) represents the customer taking the cigarette, Figure 6 (b) represents the customer paying, while 1 represents the camera, 2 represents the server, 3 represents the sound pickup device, 4 represents the cigarette, 5 represents the table, and 6 represents the payment device, and further, for example Figure 7 , which is a schematic diagram of the scene that the customer pays first and then takes the cigarette, wherein Figure 7 (a) represents the customer paying, Figure 7 (b) represents the customer taking the cigarette.

[0068] Further, as shown in Figure 8As shown, the edge-end analysis module 102 in the embodiment of the present application can also include a framing unit 1023 and a preprocessing unit 1024 connected with each other. Among them, the framing unit 1023 can perform framing operation on the video data, and the preprocessing unit 1024 can extract frame images from the framing result and perform noise reduction operation according to a first preset time interval, for example, the first preset time interval is 2 seconds, and the noise reduction method includes but is not limited to median filtering method, thereby improving the detection accuracy of the subsequent target detection neural network model.

[0069] For example Figure 9 As shown, the edge-end speech recognition module 103 includes but is not limited to a first determination unit 1031 and a first splicing unit 1032 connected with each other. Among them, the first determination unit 1031 can determine a first time point for recognizing product category information, and the timestamp includes the first time point, so that the first splicing unit 1032 can take the first time point as a reference to obtain speech data within a second preset time interval before the first time point, and splice the speech data with recording data within a third preset time interval after the first time point to obtain a speech segment, and the second preset time interval and the third preset time interval can be equal or not equal. Further, the edge-end speech recognition module 103 can also include a text conversion unit 1033, which can use a speech recognition model to perform text recognition on the speech segment to obtain standardized text information of the speech segment, for example, the speech recognition model is a fine-tuned whisper model, and the sampling frequency is 16000Hz. Optionally, before text conversion, the text conversion unit 1033 of the embodiment of the present application can also perform noise reduction operation on the speech segment, thereby reducing noise interference and improving the recognition accuracy of the speech recognition model.

[0070] For example Figure 10 As shown, the edge-end price extraction module 104 can include a matching unit 1041, which can traverse each character of the text information and match each character with a preset regular expression in turn to obtain the retail price of the cigarette, for example, the preset regular expression can be "PayPal account *** yuan". In addition, after obtaining the retail price of the cigarette, the embodiment of the present application can obtain the retail quantity of the cigarette by counting the number of retail prices. Further, the edge-end price extraction module 104 can also include a second determination unit 1042 and a correction unit 1043 connected with each other. As Figure 11 As shown, when more than two customers (for example, customer A and customer B) purchase cigarettes within a certain time, the matching unit 1041 will extract multiple groups of prices, and since the speech segment is associated with the timestamp, at this time Figure 12As shown, the second determination unit 1042 can reversely determine the second moment corresponding to the retail price in the audio data, and the timestamp includes the second moment. Further, the correction unit 1043 can correct the retail price according to the guide price corresponding to the category information, the first moment at which the category information is identified, and the second moment, to obtain the final retail price of the cigarette, for example, the final retail price of the cigarette can be calculated by the following formula, that is,

[0071]

[0072] In formula (1), K f represents the price weight of the voice-recognized retail price, p0represents the guide price of the obtained cigarette category C z ; represents the time weight of the voice-recognized retail price, Δt i represents the difference between the moment at which the audio extraction price is extracted and the moment at which the cigarette category is identified,

[0073] P z ={max(p i_ind )→p i} (2)

[0074] In formula (2), max(p i_ind )→p i represents the price corresponding to the maximum value.

[0075] The cigarette retail space-time data cloud edge collaborative determination system provided by the embodiment of the application directly collects the original video data and audio data in the terminal settlement area when the cigarette is retailed, that is, the data has real-time and is real and reliable, then the frame image in the video data is analyzed to obtain the category information of each cigarette, the voice segment is intercepted from the audio data based on the category information and the timestamp of the cigarette, and the text information is recognized to obtain the retail price of the cigarette in the text information, and then the category information of the cigarette and the text information of the voice segment are fused to obtain a cigarette retail price containing space-time information, and written into an information management system, so that the cigarette retail space-time data can be quickly obtained, and the accuracy is improved.

[0076] Based on the foregoing embodiment, the embodiment of the application provides a cigarette retail space-time data cloud edge collaborative determination method. Please refer to Figure 13 , which is a basic flowchart of a cigarette retail space-time data cloud edge collaborative determination method provided by the embodiment of the application, and the method specifically includes the following steps:

[0077] S101, collect the video data and audio data in the terminal settlement area where the cigarette is retailed, and the video data and audio data correspond to the time stamp and the space information.

[0078] Exemplarily, the video data can be collected by a camera, and the audio data can be collected by a sound collector. Further, when collecting the video data and the audio data, the embodiment of the present application can continuously detect the frame images in the video data to determine whether there is a cigarette sales behavior in the settlement area; then, if there is a cigarette sales behavior in the settlement area, the historical recording data is saved, and the recording of the preset time length is restarted to obtain the current recording data; further, the historical recording data and the current recording data are spliced, and the current recording data in the spliced recording data is decomposed and overlaid to obtain the audio data.

[0079] S102, analyze the frame images in the video data to obtain the category information of each cigarette and record the space-time information.

[0080] Exemplarily, the embodiment of the present application can sequentially locate the positions of each cigarette in the frame images according to the chronological order of the time stamps, using the target detection neural network model, and generate the full movement trajectory of the cigarette. If the end point of the full movement trajectory of the cigarette is a customer, the category information of the cigarette is output. Optionally, before analyzing the frame images in the video data, the embodiment of the present application can also perform a frame dividing operation on the video data, and extract frame images from the frame dividing result according to a first preset time interval and perform a noise reduction operation.

[0081] S103, adaptively intercept a voice segment from the audio data according to the category information of the cigarette and the time stamp and space information, and perform text recognition on the voice segment to obtain text information of the voice segment.

[0082] Exemplarily, the embodiment of the present application first determines a first moment of recognizing the category information, and the time stamp includes the first moment. Then, taking the first moment as a reference, voice data within a second preset time interval before the first moment is obtained, and the voice data is spliced with recording data within a third preset time interval after the first moment to obtain a voice segment. Further, the embodiment of the present application can use a speech recognition model to perform text recognition on the voice segment to obtain standardized text information of the voice segment, for example, the speech recognition model is a fine-tuned whisper model, and the sampling frequency is 16000Hz. Optionally, before text conversion, the embodiment of the present application can also perform a noise reduction operation on the voice segment to reduce noise interference and improve model recognition accuracy.

[0083] S104, extract the retail price of the cigarette in the text information.

[0084] Exemplarily, the embodiment of the present application can traverse each character of the text information, and sequentially match each character with a preset regular expression to obtain the retail price of the cigarette. Further, if the retail prices of two or more cigarettes are extracted, the embodiment of the present application can also reversely determine the second moment corresponding to the retail price in the audio data, the timestamp includes the second moment, and correct the retail price according to the guide price corresponding to the category information, the first moment at which the category information is identified, and the second moment, to obtain the final retail price of the cigarette.

[0085] S105, fusing the category information of the cigarette with the text information of the voice segment to obtain a cigarette retail price containing space-time information, and writing into an information management system to obtain cigarette retail space-time data.

[0086] It should be noted that the same steps and the same content in the embodiment and other embodiments are described with reference to the description of other embodiments, and will not be repeated here.

[0087] The cigarette retail space-time data cloud edge collaborative determination method provided by the embodiment of the present application directly collects the original video data and audio data of the terminal settlement area when the cigarette is retailed, that is, the data has real-time and is real and reliable. Then, the category information of each cigarette is obtained by analyzing the frame image in the video data, the text information is obtained by intercepting the voice segment from the audio data and identifying based on the category information of the cigarette and the timestamp, and the retail price of the cigarette in the text information is extracted. Further, the category information of the cigarette is fused with the text information of the voice segment to obtain a cigarette retail price containing space-time information, and written into an information management system, so that the cigarette retail space-time data can be quickly obtained, and the accuracy is improved.

[0088] Based on the foregoing embodiment, the embodiment of the present application provides an electronic device. Please refer to Figure 14 The electronic device 200 can include a processor 201 and a memory 202. The memory 202 stores at least one instruction, at least one program, a code set or an instruction set. The instruction, program, code set or instruction set is loaded and executed by the processor 201 to realize Figure 13 The steps of the cigarette retail space-time data cloud edge collaborative determination method corresponding to the embodiment.

[0089] As another aspect, the embodiment of the present application provides a computer readable storage medium for storing program code, the program code being used to execute any one of the foregoing Figure 13 The cigarette retail space-time data cloud edge collaborative determination method corresponding to the embodiment.

[0090] Those skilled in the art can clearly understand that, for the convenience and brevity of the description, the specific working processes of the above-described system, device and module can refer to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0091] In several embodiments provided in the present application, it should be understood that the disclosed system, device and method can be implemented in other ways. For example, the above-described device embodiments are only schematic, for example, the division of the modules is only a logical function division, and actual implementation can have another division manner, for example, a plurality of modules or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the coupling or direct coupling or communication connection between the shown or discussed mutual ones can be indirect coupling or communication connection through some interfaces, devices or modules, and can be electrical, mechanical or other forms. The modules described as separate components can be or can not be physically separated, and the components shown as modules can be or can not be physical units, that is, can be located in one place, or can be distributed on a plurality of network units. Some or all of the modules can be selected according to actual needs to achieve the purpose of the embodiment scheme.

[0092] In addition, each functional module in each embodiment of the present application can be integrated in one processing unit, or each module can be physically present alone, or two or more units can be integrated in one module. The integrated unit can be realized in the form of hardware or in the form of a software functional unit. If the integrated unit is realized 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.

[0093] Based on such understanding, the technical solutions of the present application essentially or say the part that makes a contribution to the prior art or the whole or part of the technical solutions can be embodied in the form of a software product, which is stored in a storage medium and includes a plurality of instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the cigarette retail space-time data cloud edge collaboration determination method of each embodiment of the present application. The foregoing storage medium includes: a U disk, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, and various media that can store program codes.

[0094] Any technical features in the above embodiments can be combined, and for the sake of brevity, not all possible combinations are described above, however, it should be understood that the application encompasses all possible combinations of the technical features unless such a combination is not technically possible.

[0095] The principles and implementation manners of the present application are described herein by using specific examples, and the above embodiments are only used to help understand the method of the present application and its core idea; meanwhile, according to the idea of the present application, the specific implementation manners and application scopes will be changed by those skilled in the art. In conclusion, the content of the present specification should not be understood as a limitation of the present application.

Claims

1. A cigarette retail space-time data cloud edge collaborative determination system, characterized in that, The cigarette retail space-time data cloud edge collaborative determination system comprises: An edge terminal acquisition module configured to acquire video data and audio data of a terminal settlement area where cigarettes are retailed, the video data and the audio data corresponding to time stamps and space information; An edge terminal analysis module electrically connected to the edge terminal acquisition module and configured to analyze frame images in the video data, obtain category information of each cigarette, and record space-time information; An edge terminal voice recognition module electrically connected to the edge terminal analysis module and configured to adaptively intercept a voice segment from the audio data according to the category information of the cigarette and the time stamps and space information, and perform text recognition on the voice segment to obtain text information of the voice segment; An edge terminal price extraction module electrically connected to the edge terminal voice recognition module and configured to extract a retail price of the cigarette in the text information; A cloud end analysis module configured to fuse the category information of the cigarette and the text information of the voice segment to obtain a cigarette retail price containing the space-time information, and write the cigarette retail price into an information management system to obtain cigarette retail space-time data; The edge terminal price extraction module comprises a matching unit, a second determination unit and a correction unit connected to each other; the matching unit is configured to traverse each character in the text information, and sequentially match the each character with a preset regular expression to obtain the retail price of the cigarette; the second determination unit is configured to reversely determine a second time corresponding to the retail price in the audio data, the time stamp comprising the second time; and the correction unit is configured to correct the retail price according to a guide price corresponding to the category information, a first time at which the category information is recognized, and the second time to obtain a final retail price of the cigarette.

2. The cigarette retail space-time data cloud edge collaboration determination system according to claim 1, characterized in that, The edge terminal analysis module comprises a positioning unit and an output unit connected to each other; The positioning unit is configured to sequentially locate positions of each cigarette in the frame images in the order of the time stamps using a target detection neural network model, and generate a full-range moving track of the cigarette; and The output unit is configured to output the category information of the cigarette if the full-range moving track of the cigarette ends at a customer.

3. The cigarette retail space-time data cloud edge collaboration determination system according to claim 2, characterized in that, The edge terminal analysis module further comprises a framing unit and a preprocessing unit connected to each other; The framing unit is configured to perform a framing operation on the video data; and the preprocessing unit is configured to extract the frame images from a framing result according to a first preset time interval and perform a noise reduction operation.

4. The cigarette retail space-time data cloud edge collaboration determination system according to claim 1, characterized in that, The edge terminal voice recognition module comprises a first determination unit and a first splicing unit connected to each other; The first determination unit is configured to determine a first time at which the category information is recognized, the time stamp comprising the first time; and The first splicing unit is configured to take the first time as a reference, obtain voice data within a second preset time interval before the first time, and splice the voice data with recording data within a third preset time interval after the first time to obtain the voice segment.

5. The cigarette retail space-time data cloud edge collaboration determination system according to any one of claims 1 to 4, characterized in that, The edge terminal acquisition module comprises a detection unit, a recording unit and a second splicing unit connected with each other. The detection unit is configured to detect frame images in the video data to determine whether there is a cigarette sales behavior in the settlement area. The recording unit is configured to save historical recording data and restart recording for a preset time period to obtain current recording data if there is a cigarette sales behavior in the settlement area. Furthermore, The second splicing unit is configured to splice the historical recording data and the current recording data, decompose and cover the current recording data in the spliced recording data, and obtain the audio data.

6. A method for cloud edge collaborative determination of cigarette retail space-time data, characterized in that, The cigarette retail space-time data cloud edge collaborative determination method comprises: Acquiring video data and audio data of a terminal settlement area where cigarettes are retailed at a time, wherein the video data and the audio data correspond to time stamps and space information; Analyzing frame images in the video data to obtain category information of each cigarette and record space-time information; According to the category information of the cigarette and the time stamp and space information, adaptively intercepting a voice segment from the audio data, and performing text recognition on the voice segment to obtain text information of the voice segment; Extracting a retail price of the cigarette in the text information; Fusing the category information of the cigarette and the text information of the voice segment to obtain a cigarette retail price containing the space-time information, and writing into an information management system to obtain cigarette retail space-time data; Wherein, the extraction of the retail price of the cigarette in the text information further comprises: traversing each character of the text information, and sequentially matching each character with a preset regular expression to obtain the retail price of the cigarette; reversely determining a second time corresponding to the retail price in the audio data, wherein the time stamp comprises the second time; and correcting the retail price according to a guide price corresponding to the category information, a first time when the category information is recognized, and the second time, to obtain a final retail price of the cigarette.

7. An electronic device, comprising: The electronic device comprises a processor and a memory, wherein the memory stores at least one instruction, at least one program, a code set or an instruction set, and the instruction, the program, the code set or the instruction set is loaded and executed by the processor to realize the steps of the cigarette retail space-time data cloud edge collaborative determination method of claim 6.

8. A computer-readable storage medium, characterized in that, The computer readable storage medium stores one or more programs which can be executed by one or more processors to realize the steps of the cigarette retail space-time data cloud edge collaborative determination method of claim 6.

Images