Electronic commerce live broadcast processing method and live broadcast platform based on big data

Abstract

The invention relates to the technical field of image communication, in particular to an electronic commerce live broadcast processing method based on big data and a live broadcast platform, which are used for solving the problems that the existing electronic commerce video live broadcast platform cannot intelligently analyze the optimal broadcast time and cannot intelligently and automatically sort commodities in a live broadcast room, so that the live broadcast effect is poor, and the live broadcast efficiency is poor. And the sales effect is not good. The e-commerce live broadcast platform comprises a live broadcast processing module, a live broadcast reminding unit, a real-time monitoring unit, a real-time analysis unit and a commodity sorting unit. According to the e-commerce live broadcast platform, the sales effect of the live broadcast room can be effectively improved by obtaining the optimal live broadcast time period and intelligently displaying the commodities, so that the development of the e-commerce live broadcast industry is promoted.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of image communication, in particular to an e-commerce live broadcast processing method and a live broadcast platform based on big data. BACKGROUND

[0002] E-commerce live broadcast refers to that an offline entity seller sells products through a network live broadcast platform to expand the products and enable customers to purchase the products while learning about the performance of the products. E-commerce live broadcast has the advantages of directness, rapidness, strong interactivity, rich content and the like.

[0003] At present, the existing e-commerce video live broadcast platform still has many problems. In the existing shop live broadcast video, the recommended goods are generally fixedly pushed and played, and the push order of the recommended goods video cannot be adjusted in real time according to the goods link accessed by the user, thereby wasting a lot of viewing time of the user, reducing the interest and expectation of the user, and affecting the live shopping experience of the user. Meanwhile, the existing e-commerce video live broadcast platform cannot push other goods associated in the shop according to the goods link accessed by the user, so that the user cannot quickly learn about the information of other goods associated in the shop, thereby reducing the consumption desire of the user and the sales economy of the shop, and affecting the development and progress of the e-commerce video live broadcast platform. In order to solve the above problems, the patent with the application number CN202011355558.3 discloses an e-commerce video live broadcast platform based on big data analysis. The present application divides the shop live broadcast video into several recommended video segments, records the goods corresponding to the recommended video segment link accessed by the user, counts the attributes of the goods corresponding to the recommended video segment link accessed by the user, analyzes the ratio of the attribute quantitative data of the goods corresponding to the recommended video segment link accessed by the user to the attribute quantitative data of other recommended goods of the shop, calculates the correlation degree coefficient of the goods corresponding to the recommended video segment link accessed by the user and other goods, and sorts and plays the video according to the size order of the correlation degree coefficient, thereby improving the consumption desire of the user and increasing the live shopping experience of the user. However, the e-commerce video live broadcast platform still has the following deficiencies: the e-commerce video live broadcast platform cannot intelligently analyze the best broadcast time, and cannot intelligently and automatically sort the goods in the live broadcast room, thereby resulting in poor live broadcast effect and poor sales effect. SUMMARY

[0004] In order to overcome the above technical problems, the purpose of the present application is to provide a big data-based e-commerce live broadcast processing method and a live broadcast platform: the live broadcast processing module obtains the heat parameter of the live broadcast process in the historical data, the live broadcast reminding unit obtains the heat value according to the heat parameter, the real-time monitoring unit obtains the priority parameter of the analysis object in real time, the real-time analysis unit obtains the priority coefficient according to the priority parameter, and the commodity sorting unit sorts and displays the analysis object in the live broadcast room according to the priority coefficient, solves the problem that the existing e-commerce video live broadcast platform cannot intelligently analyze the best broadcast time and cannot intelligently and automatically sort the goods in the live broadcast room, resulting in poor live broadcast effect and poor sales effect.

[0005] The purpose of the present application can be realized by the following technical solutions:

[0006] The big data-based e-commerce live broadcast platform comprises:

[0007] The live broadcast processing module is used for obtaining the heat parameter of the live broadcast process in the historical data and sending the heat parameter to the live broadcast reminding unit, wherein the heat parameter comprises a popularity value RQ and a commodity value SP.

[0008] The live broadcast reminding unit is used for obtaining a heat value RD according to the heat parameter and obtaining a reminding time according to the heat value RD to remind the live broadcast host.

[0009] The real-time monitoring unit is used for obtaining the priority parameter of the analysis object i in real time and sending the priority parameter to the real-time analysis unit, wherein the priority parameter comprises a total ratio YZ, a sales value XS and a sales time value SS.

[0010] The real-time analysis unit is used for obtaining a priority coefficient YX according to the priority parameter and sending the priority coefficient YX to the commodity sorting unit.

[0011] The commodity sorting unit is used for sorting and displaying the analysis object i in the live broadcast room according to the priority coefficient YX.

[0012] The further scheme of the present application is that the live broadcast processing module obtains the heat parameter in the following specific process:

[0013] All live broadcast processes in the historical data are obtained.

[0014] Obtaining total person times of watching, total number of comments and total number of likes in a preset time period during each live broadcast process, and marking them as total observation value ZG, comment value PL and like value DZ respectively, and substituting total observation value ZG, comment value PL and like value DZ into formula RQ=s1*ZG+s2*PL+s3*DL to obtain popularity value RQ, wherein s1, s2 and s3 are preset proportion coefficients of total observation value ZG, comment value PL and like value DZ respectively, and s1+s2+s3=1, 1>s1>s3>s2>0;

[0015] Obtaining the total number of goods sold and the total sales amount and the total number of goods added to the shopping cart in a preset time period during each live broadcast process, and marking them as sales value XL, sales value XE and add value JG, and substituting sales value XL, sales value XE and add value JG into formula SP=q1*XL+q2*XE+q3*JG to obtain goods value SP, wherein q1, q2 and q3 are preset weight coefficients of sales value XL, sales value XE and add value JG respectively, and q1>q2>q3>2.36;

[0016] The popularity value RQ and the goods value SP are sent to the live broadcast reminding unit.

[0017] Further scheme of the application: the specific process that the live broadcast reminding unit obtains the heat value RD is as follows:

[0018] Ellipse graph is drawn with the popularity value RQ and the goods value SP as the long semi-axis and the short semi-axis of the ellipse respectively, the area of the ellipse graph is obtained and marked as the heat value RD;

[0019] The heat values RD are sorted in descending order, the preset time period corresponding to the heat value RD at the first position is marked as the selected time period, the middle time of the selected time period is obtained and marked as the selected time, and the time of the preset reminding time period before the selected time is marked as the reminding time;

[0020] The current time is obtained, if the current time=the reminding time, a prompt short line is generated to the mobile terminal of the live broadcast host.

[0021] Further scheme of the application: the specific process that the real-time monitoring unit obtains the priority parameter is as follows:

[0022] Each product uploaded in the real-time live broadcast process is marked as analysis object i, i, …, n, n is a natural number;

[0023] The total number and the remaining number of the analysis object i are obtained and marked as total value and remaining value, the ratio between the remaining value and the total value is obtained and marked as the ratio YZ;

[0024] Obtain the total number of items sold, the number of people who purchased the items, and the number of times orders were cancelled for analysis object i. Label these as Total Sales Value SZ, Purchase Value GS, and Cancellation Value QD, respectively. Substitute the Total Sales Value SZ, Purchase Value GS, and Cancellation Value QD into the formula. The sales value XS is obtained, where o1, o2, and o3 are the preset proportional coefficients of the total sales value SZ, the purchase value GS, and the order value QD, respectively, and o1+o2+o3=1, 0<o2<o1<o3<1;

[0025] Get the time when analysis object i was sold, get the time difference between two consecutive sales and mark it as the time difference value, get the average of all time differences and mark it as the sales time value SS;

[0026] The total surplus ratio YZ, sales value XS, and sales time value SS are sent to the real-time analysis unit.

[0027] A further aspect of the present invention: The specific process by which the real-time analysis unit obtains the priority coefficient YX is as follows:

[0028] Substitute the total surplus ratio YZ, sales value XS, and sales value SS into the formula. The priority coefficient YX is obtained, where h1, h2, and h3 are the preset ratio coefficients of the total surplus ratio YZ, sales value XS, and sales time value SS, respectively, and h1+h2+h3=1, 1>h2>h1>h3>0, γ is the error factor, and γ=1.013 is taken.

[0029] Send the priority coefficient YX to the product sorting unit.

[0030] A further aspect of this invention: a big data-based e-commerce live streaming processing method, comprising the following steps:

[0031] Step 1: The live streaming processing module retrieves all live streaming processes from historical data;

[0032] Step 2: The live streaming processing module obtains the total number of viewers, comments, and likes within a preset time period for each live stream, and marks them as the total view value ZG, comment value PL, and like value DZ, respectively. Substituting the total view value ZG, comment value PL, and like value DZ into the formula RQ = s1 × ZG + s2 × PL + s3 × DL, the popularity value RQ is obtained, where s1, s2, and s3 are the preset proportional coefficients of the total view value ZG, comment value PL, and like value DZ, respectively, and s1 + s2 + s3 = 1, 1 > s1 > s3 > s2 > 0;

[0033] Step three: the live processing module acquires the number of sales and the total sales of the commodity in the preset time period of each live process, and marks them as the sales value XL and the sales value XE respectively, and marks the total number of times the commodity is added to the shopping cart as the add value JG, and substitutes the sales value XL, the sales value XE and the add value JG into the formula SP=q1*XL+q2*XE+q3*JG to obtain the commodity value SP, wherein q1, q2 and q3 are preset weight coefficients of the sales value XL, the sales value XE and the add value JG respectively, and q1>q2>q3>2.36;

[0034] Step four: the live processing module sends the popularity value RQ and the commodity value SP to the live reminding unit;

[0035] Step five: the live reminding unit draws an elliptical graph with the popularity value RQ and the commodity value SP as the long semi-axis and the short semi-axis respectively, obtains the area of the elliptical graph and marks it as the heat value RD;

[0036] Step six: the live reminding unit sorts the heat values RD in descending order, marks the preset time period corresponding to the heat value RD at the first place as the selected time period, obtains the middle time of the selected time period and marks it as the selected time, and obtains the time of the preset reminding time period before the selected time and marks it as the reminding time;

[0037] Step seven: the live reminding unit obtains the current time, and if the current time=the reminding time, generates a prompt short line to the mobile terminal of the live host;

[0038] Step eight: the real-time monitoring unit marks each product uploaded in the real-time live process as an analysis object i, i, …, n, n is a natural number;

[0039] Step nine: the real-time monitoring unit obtains the total number and the remaining number of the analysis object i, and marks them as the total value and the remaining value, obtains the ratio between the remaining value and the total value and marks it as the ratio YZ;

[0040] Step ten: the real-time monitoring unit obtains the total number of sold, the number of people who buy the commodity and the number of times of canceling the order after purchase of the analysis object i, and marks them as the total value SZ, the number of purchases GS and the order value QD, and substitutes the total value SZ, the number of purchases GS and the order value QD into the formula to obtain the sales value XS, wherein o1, o2 and o3 are preset proportion coefficients of the total value SZ, the number of purchases GS and the order value QD respectively, and o1+o2+o3=1, 0

[0041] Step eleven: the real-time monitoring unit obtains the time when the analysis object i is sold, obtains the time difference between two adjacent times and marks it as a time difference value, obtains the average value of all time difference values and marks it as a sales time value SS;

[0042] Step twelve: the real-time monitoring unit sends the total remaining ratio YZ, the sales value XS and the sales time value SS to the real-time analysis unit;

[0043] Step thirteen: the real-time analysis unit substitutes the total remaining ratio YZ, the sales value XS and the sales time value SS into the formula to obtain a priority coefficient YX, wherein h1, h2 and h3 are respectively preset proportional coefficients of the total remaining ratio YZ, the sales value XS and the sales time value SS, and h1+h2+h3=1, 1>h2>h1>h3>0, and γ is an error factor, and γ=1.013 is taken;

[0044] Step fourteen: the real-time analysis unit sends the priority coefficient YX to the commodity sorting unit;

[0045] Step fifteen: the commodity sorting unit sorts the analysis object i according to the priority coefficient YX from large to small and displays it in the live room.

[0046] The beneficial effects of the present application are as follows:

[0047] The e-commerce live broadcast processing method and live broadcast platform based on big data of the present application obtain the heat parameter of the live broadcast process in the historical data through the live broadcast processing module, obtain the heat value according to the heat parameter through the live broadcast reminding unit, obtain the priority parameter of the analysis object in real time through the real-time monitoring unit, obtain the priority coefficient according to the priority parameter through the real-time analysis unit, and sort the analysis object according to the priority coefficient and display it in the live room through the commodity sorting unit; the live broadcast processing method first analyzes the live broadcast process of the historical data, obtains the popularity value and the commodity value, the popularity value is used to reflect the popularity degree of the live broadcast process in a preset time period, the commodity value is used to reflect the commodity sales situation of the live broadcast process in a preset time period, the heat value obtained by analyzing the two is used to comprehensively measure the heat situation of the live broadcast process in a preset time period, and the greater the heat value is, the higher the heat is, so that the selected time period is a time period with good heat in a comprehensive situation, and it is easy to obtain the effect in this time period, then the real-time live broadcast process is analyzed, the total remaining ratio, the sales value and the sales time value are obtained, and the three can measure the commodity sales quantity and rate, therefore, the priority coefficient obtained by analyzing the three can comprehensively measure the sales effect of the commodity, and the greater the priority coefficient is, the better the sales effect is, so that the corresponding commodity is preferentially displayed, which can further improve the sales effect of the live room; the live broadcast platform can effectively improve the sales effect of the live room by obtaining the best live broadcast time period and the intelligent display of the commodity, thereby promoting the development of the e-commerce live broadcast industry. BRIEF DESCRIPTION OF DRAWINGS

[0048] The application will be further described below with reference to the drawings.

[0049] Figure 1 is the principle diagram of the e-commerce live broadcast platform based on big data in the application. DETAILED DESCRIPTION

[0050] The technical solutions in the embodiments of the application will be clearly and completely described below with reference to the embodiments of the application. Obviously, the described embodiments are only a part of the embodiments of the application, but not all the embodiments of the application. Based on the embodiments of the application, all other embodiments obtained by those skilled in the art without creative work fall within the protection scope of the application.

[0051] Embodiment 1

[0052] Please refer to Figure 1 The embodiment is an e-commerce live broadcast platform based on big data, which comprises the following modules: a live broadcast processing module, a live broadcast reminding unit, a real-time monitoring unit, a real-time analysis unit and a commodity sorting unit.

[0053] The live broadcast processing module is configured to obtain a heat parameter of a live broadcast process in historical data and send the heat parameter to the live broadcast reminding unit, wherein the heat parameter comprises a popularity value RQ and a commodity value SP.

[0054] The live broadcast reminding unit is configured to obtain a heat value RD according to the heat parameter and obtain a reminding time according to the heat value RD to remind a live broadcast host.

[0055] The real-time monitoring unit is configured to obtain a priority parameter of an analysis object i in real time and send the priority parameter to the real-time analysis unit, wherein the priority parameter comprises a total remaining ratio YZ, a sales value XS and a sales time value SS.

[0056] The real-time analysis unit is configured to obtain a priority coefficient YX according to the priority parameter and send the priority coefficient YX to the commodity sorting unit.

[0057] The commodity sorting unit is configured to sort the analysis object i according to the priority coefficient YX and display the analysis object i in a live broadcast room.

[0058] Embodiment 2

[0059] Please refer to Figure 1 The embodiment is an e-commerce live broadcast processing method based on big data, which is characterized by comprising the following steps.

[0060] Step 1: The live broadcast processing module obtains all live broadcast processes in historical data.

[0061] Step two: the live broadcast processing module obtains the total number of views, the total number of comments and the total number of likes in the preset time period of each live broadcast process, and marks them as total view value ZG, comment value PL and like value DZ respectively. The total view value ZG, comment value PL and like value DZ are substituted into the formula RQ = s1 x ZG + s2 x PL + s3 x DL to obtain the popularity value RQ, wherein s1, s2 and s3 are preset proportion coefficients of the total view value ZG, the comment value PL and the like value DZ respectively, and s1 + s2 + s3 = 1, 1 > s1 > s3 > s2 > 0;

[0062] Step three: the live broadcast processing module obtains the number of sales, the sales amount and the total number of times of adding to the shopping cart of the product in the preset time period of each live broadcast process, and marks them as sales value XL, sales amount value XE and add purchase value JG respectively. The sales value XL, sales amount value XE and add purchase value JG are substituted into the formula SP = q1 x XL + q2 x XE + q3 x JG to obtain the product value SP, wherein q1, q2 and q3 are preset weight coefficients of the sales value XL, the sales amount value XE and the add purchase value JG respectively, and q1 > q2 > q3 > 2.36;

[0063] Step four: the live broadcast processing module sends the popularity value RQ and the product value SP to the live broadcast reminding unit;

[0064] Step five: the live broadcast reminding unit draws an elliptical graph with the popularity value RQ and the product value SP as the long semi-axis and the short semi-axis respectively, obtains the area of the elliptical graph and marks it as the heat value RD;

[0065] Step six: the live broadcast reminding unit sorts the heat values RD in descending order, marks the preset time period corresponding to the heat value RD at the first place as the selected time period, obtains the middle time of the selected time period and marks it as the selected time, and obtains the time of the preset reminding time period before the selected time as the reminding time;

[0066] Step seven: the live broadcast reminding unit obtains the current time, and if the current time = the reminding time, generates a prompt short line to the mobile terminal of the live broadcast host;

[0067] Step eight: the real-time monitoring unit marks each product uploaded in the real-time live broadcast process as an analysis object i, i, …, n, n is a natural number;

[0068] Step nine: the real-time monitoring unit obtains the total number and the remaining number of the analysis object i, and marks them as the total value and the remaining value. The ratio between the remaining value and the total value is obtained and marked as the ratio YZ;

[0069] Step ten: the real-time monitoring unit obtains the total number of the analysis object i that has been sold, the number of people who buy the goods, and the number of times of canceling the order after purchase, and marks them as sold total value SZ, purchase number value GS, and order cancellation value QD, respectively, and substitutes the sold total value SZ, the purchase number value GS, and the order cancellation value QD into the formula to obtain the sales value XS, wherein o1, o2, and o3 are preset proportion coefficients of the sold total value SZ, the purchase number value GS, and the order cancellation value QD, respectively, and o1+o2+o3=1, 0

[0070] Step eleven: the real-time monitoring unit obtains the time when the analysis object i is sold, obtains the time difference between the adjacent two times when it is sold and marks it as the time difference value, and obtains the average value of all the time difference values and marks it as the sold time value SS.

[0071] Step twelve: the real-time monitoring unit sends the remaining total ratio YZ, the sales value XS, and the sold time value SS to the real-time analysis unit.

[0072] Step thirteen: the real-time analysis unit substitutes the remaining total ratio YZ, the sales value XS, and the sold time value SS into the formula to obtain the priority coefficient YX, wherein h1, h2, and h3 are preset proportion coefficients of the remaining total ratio YZ, the sales value XS, and the sold time value SS, respectively, and h1+h2+h3=1, 1>h2>h1>h3>0, and γ is an error factor, and γ=1.013.

[0073] Step fourteen: the real-time analysis unit sends the priority coefficient YX to the goods sorting unit.

[0074] Step fifteen: the goods sorting unit sorts the analysis object i according to the priority coefficient YX from large to small and displays it in the live room.

[0075] In the description of the present specification, the description of the terms "one embodiment", "example", "specific example", and the like means that the specific features, structures, materials, or characteristics described in connection with the embodiment or example are included in at least one embodiment or example of the present application. In the present specification, the illustrative description of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials, or characteristics described can be combined in any one or more embodiments or examples in a suitable manner.

[0076] The above is only an example and description of the present application, and those skilled in the art can make various modifications or supplements to the described specific embodiments or adopt similar ways to replace them, as long as they do not deviate from the scope of the present application or exceed the scope defined by the present claims.

Claims

1. A big data-based e-commerce live streaming platform, characterized in that: include: The live streaming processing module is used to obtain the popularity parameters of the live streaming process from historical data and send the popularity parameters to the live streaming reminder unit. The popularity parameters include popularity value and product value. The live broadcast reminder unit is used to obtain a popularity value based on the popularity parameter, and then determine the reminder time based on the popularity value to remind the live broadcast host. The real-time monitoring unit is used to acquire the priority parameters of the analysis object in real time and send the priority parameters to the real-time analysis unit; among them, the priority parameters include the total surplus ratio, sales value, and sales time value; The real-time analysis unit is used to obtain priority coefficients based on priority parameters and send the priority coefficients to the product sorting unit; The product sorting unit is used to sort the analyzed objects according to priority coefficients and display them in the live broadcast room.

2. The big data-based e-commerce live streaming platform according to claim 1, characterized in that, The specific process by which the live streaming processing module obtains popularity parameters is as follows: Retrieve all live streams from historical data; The system obtains the total number of viewers, comments, and likes within a preset time period for each live stream, and labels them as total view value, comment value, and like value, respectively. The system then analyzes the total view value, comment value, and like value to obtain the popularity value. Get the number of products sold, the sales amount, and the total number of times products were added to the shopping cart within a preset time period during each live broadcast. Mark these as sales value, sales amount, and add-to-cart value, respectively. Analyze the sales value, sales amount, and add-to-cart value to obtain the product value. Send popularity and product value to the live stream notification unit.

3. The big data-based e-commerce live streaming platform according to claim 1, characterized in that, The specific process by which the live stream notification unit obtains the popularity value is as follows: Draw an ellipse with popularity value and product value as the major and minor axes, respectively, obtain the area of ​​the ellipse and mark it as the popularity value; Sort the popularity values ​​in descending order, mark the preset time period corresponding to the first popularity value as the selected time period, obtain the middle time of the selected time period and mark it as the selected time, obtain the time of the preset reminder time period before the selected time and mark it as the reminder time. Get the current time. If the current time equals the reminder time, generate a notification and send it to the live broadcast host's mobile device.

4. The big data-based e-commerce live streaming platform according to claim 1, characterized in that, The specific process by which the real-time monitoring unit obtains priority parameters is as follows: Each product listed during the live stream is marked as an analysis object; Obtain the total number and remaining number of the analyzed objects, and label them as total value and remaining value. Obtain the ratio between the remaining value and the total value and label it as the ratio of remaining to total. Obtain the total number of items sold, the number of people who purchased the items, and the number of times orders were canceled after purchase for the analyzed object. Mark these as total sales value, purchase value, and order cancellation value, respectively. Analyze the total sales value, purchase value, and order cancellation value to obtain the sales value. Get the time when the object being analyzed was sold, get the time difference between two consecutive sales and mark it as the time difference value, get the average of all time differences and mark it as the sales time value; The total surplus ratio, sales value, and sales time value are sent to the real-time analysis unit.

5. The big data-based e-commerce live streaming platform according to claim 1, characterized in that, The specific process by which the real-time analysis unit obtains the priority coefficient is as follows: The priority coefficient is obtained by analyzing the total surplus ratio, sales value, and sales time value. Send the priority coefficient to the product sorting unit.

6. A big data-based e-commerce live streaming processing method, characterized in that: Includes the following steps: Step 1: The live streaming processing module retrieves all live streaming processes from historical data; Step 2: The live streaming processing module obtains the total number of viewers, comments, and likes within a preset time period for each live stream, and marks them as total view value, comment value, and like value, respectively. The total view value, comment value, and like value are then analyzed to obtain the popularity value. Step 3: The live streaming processing module obtains the number of products sold, the sales amount, and the total number of times products are added to the shopping cart within a preset time period during each live stream. These are then marked as sales volume value, sales amount value, and add-to-cart value, respectively. The sales volume value, sales amount value, and add-to-cart value are analyzed to obtain the product value. Step 4: The live streaming processing module sends the popularity score and product score to the live streaming notification unit; Step 5: The live broadcast reminder unit draws an ellipse with the popularity value and product value as the major and minor axes of the ellipse, respectively, obtains the area of ​​the ellipse, and marks it as the popularity value; Step Six: The live broadcast reminder unit sorts the popularity values ​​in descending order, marks the preset time period corresponding to the first popularity value as the selected time period, obtains the middle time of the selected time period and marks it as the selected time, and obtains the time of the preset reminder time period before the selected time and marks it as the reminder time. Step 7: The live broadcast reminder unit obtains the current time. If the current time equals the reminder time, a notification is generated and sent to the live broadcast host's mobile terminal. Step 8: The real-time monitoring unit marks each product listed during the live broadcast as an analysis object; Step 9: The real-time monitoring unit obtains the total number and remaining number of the analyzed objects, and marks them as the total value and the remaining value. It also obtains the ratio between the remaining value and the total value and marks it as the remaining-total ratio. Step 10: The real-time monitoring unit obtains the total number of items sold, the number of people who purchased the items, and the number of times orders were canceled after purchase. These are then marked as total sales value, purchase value, and order cancellation value, respectively. The total sales value, purchase value, and order cancellation value are analyzed to obtain the sales value. Step 11: The real-time monitoring unit obtains the time when the analyzed object is sold, obtains the time difference between two adjacent sales and marks it as the time difference value, obtains the average of all time difference values ​​and marks it as the sales time value; Step 12: The real-time monitoring unit sends the total surplus ratio, sales value, and sales time value to the real-time analysis unit; Step 13: The real-time analysis unit analyzes the total surplus ratio, sales value, and sales time value to obtain the priority coefficient; Step Fourteen: The real-time analysis unit sends the priority coefficient to the product sorting unit; Step 15: The product sorting unit sorts the analyzed objects in descending order of priority coefficient and displays them in the live broadcast room.

Images