Preheating point location determination method, device and equipment

Abstract

The invention relates to the technical field of intelligent analysis, and discloses a preheating point location determination method, device and equipment, and the method comprises the steps: determining the playing frequency corresponding to each playing point location and the first screen playing time consumption according to historical playing behavior data; selecting candidate preheating point locations from the playing point locations based on the playing frequency and the first screen playing time consumption; based on the popularity parameters, determining popularity corresponding to each candidate preheating point location; and selecting a preheating point position from the candidate preheating point positions based on the heat degree of each candidate preheating point position. As the candidate preheating point locations which are accessed at high frequency and have relatively long first screen playing time can be quickly determined according to historical playing behavior data analysis, and further selection is performed according to the popularity of each candidate preheating point location in combination with related settings, the candidate preheating point locations can be reasonably selected as the preheating point locations, and the accuracy of the candidate preheating point locations is improved. Automatic selection of the preheating point positions is achieved, and the labor burden is reduced.

Description

Technical Field

[0001] The present application relates to the field of intelligent analysis technology, and in particular to a method, device and equipment for determining a preheating point. Background Art

[0002] In a multi-level networking scenario, if a user wants to view the video data of a certain point, the user needs to initiate an image acquisition request. After receiving the image acquisition request, the platform will retrieve the video data through multiple service media network nodes. The video data will then be transmitted through multiple service media network nodes to reach the platform, and then sent to the user's device by the platform. The overall streaming process takes a long time, affecting the user's viewing experience, especially the first screen loading speed, and the problem of inconsistent playback experience at high-frequency, high-quality points.

[0003] To address this issue, the relevant technology is to use manual experience to set pre-hot spots and pre-fetch streams for the pre-hot spots. That is, the platform retrieves video data from the playback point through the service media network node in advance for caching, to ensure that when the user initiates an image acquisition request, the platform can use the data cached during the pre-fetching of the stream to provide display first, thereby increasing the first-screen loading speed of the pre-hot spots and reducing the first-screen loading time.

[0004] However, the manual setting of preheating points is labor-intensive and inefficient, and the points that actually need to be preheated will change with the user's usage habits, and the manual setting cannot be adjusted in time. In addition, the manual setting is prone to too many or too few preheating points, which does not meet the actual preheating needs. Summary of the invention

[0005] The main purpose of the present application is to provide a method, device and equipment for determining a preheating point, aiming to solve the technical problems that the related technology manually sets the preheating point, which is costly, inefficient and cannot be flexibly adjusted, resulting in poor actual effects.

[0006] To achieve the above object, the present application proposes a method for determining a preheating point, the method comprising:

[0007] Determine the playback frequency and first screen playback time corresponding to each playback point according to the historical playback behavior data, wherein the first screen playback time is the interval between the time when the user requests to retrieve the image and the time when the image corresponding to the playback point is first displayed on the user's device, and the playback point is a device or apparatus for capturing images at a preset point;

[0008] Selecting a candidate preheating point from the playback points based on the playback frequency and the first screen playback time;

[0009] Based on the heat parameter, determine the heat corresponding to each candidate preheating point;

[0010] A preheating point is selected from the candidate preheating points based on the heat levels of the candidate preheating points.

[0011] In a possible implementation of the present application, the popularity parameters include playback frequency and first screen playback time;

[0012] The step of determining the heat corresponding to each candidate preheating point based on the heat parameter includes:

[0013] Determine the playback frequency score corresponding to each candidate preheating spot based on the playback frequency corresponding to the candidate preheating spot, and determine the first screen playback time score corresponding to each candidate preheating spot based on the first screen playback time corresponding to the candidate preheating spot;

[0014] A heat score result corresponding to each candidate preheating hotspot is generated according to the playback frequency score and the first screen time consumption score, and the heat score result is used to characterize the heat level of the candidate preheating hotspot.

[0015] In a possible implementation of the present application, determining the playback frequency score corresponding to each candidate pre-hot spot based on the playback frequency corresponding to the candidate pre-hot spot, and determining the first screen time consumption score corresponding to each candidate pre-hot spot based on the first screen playback time consumption corresponding to the candidate pre-hot spot, includes:

[0016] Calculate the difference between the playback frequency of each candidate preheating point and the frequency threshold, and determine the frequency threshold difference corresponding to each candidate preheating point;

[0017] Determine the target difference interval to which the frequency threshold difference of each candidate preheating point belongs;

[0018] Determine the target time interval to which the first screen playback time corresponding to each candidate preheating spot belongs;

[0019] The interval score corresponding to the target time-consuming interval is found to obtain the first screen time-consuming score corresponding to each candidate preheating hotspot, and the interval score corresponding to the target difference interval is found to obtain the playback frequency score corresponding to each candidate preheating hotspot.

[0020] In a possible implementation of the present application, the heat parameters include playback frequency, first screen playback time, and preheating improvement ratio;

[0021] The step of determining the heat corresponding to each candidate preheating point based on the heat parameter includes:

[0022] Estimate the time required to preheat the first screen for each candidate preheating hotspot;

[0023] Determine the preheating improvement ratio corresponding to each candidate preheating hot spot according to the preheating first screen time consumption and the first screen playback time consumption;

[0024] The heat corresponding to each candidate preheating hot spot is determined according to the preheating improvement ratio, the playing frequency and the first screen time consumption.

[0025] In a possible implementation of the present application, the heat parameters include playback frequency, first screen playback time, and historical preheating tags;

[0026] The step of determining the heat corresponding to each candidate preheating point based on the heat parameter includes:

[0027] Determine the historical preheating label corresponding to each candidate preheating point according to the historical preheating record, wherein the historical preheating label is used to indicate whether the candidate preheating point has been selected as the preheating point;

[0028] The heat corresponding to each candidate preheating hot spot is determined according to the historical preheating label, the playback frequency, and the first screen time consumption.

[0029] In a possible implementation of the present application, determining the heat corresponding to each candidate preheating point based on the heat parameter includes:

[0030] Determine the importance of each candidate preheating spot;

[0031] Determine a correction coefficient corresponding to the importance of the preheating point;

[0032] Determine a heat parameter score for each candidate preheating point, and correct each heat parameter score based on the correction coefficient;

[0033] Based on the corrected scores of the heat parameters, the heat corresponding to each candidate preheating point is determined.

[0034] In a possible implementation of the present application, determining the importance of each candidate preheating point includes:

[0035] Obtain the point location, point setting time and point-related services corresponding to each candidate preheating point;

[0036] Determining the importance level of the location according to the location of the point;

[0037] Determine the importance level of the moment according to the point setting moment;

[0038] Obtaining the business importance level corresponding to the business associated with the point;

[0039] The importance level corresponding to each candidate preheating spot is determined according to the location importance level, the time importance level and the service importance level, and the importance level is used to characterize the importance of the preheating spot.

[0040] In a possible implementation of the present application, selecting a preheating point from the candidate preheating points according to the heat score result includes:

[0041] Estimate the single-point preheating resource demand according to the preheating resource demand corresponding to each candidate preheating hot spot, where the single-point preheating resource demand is the bandwidth resource required for prefetching a flow for a single preheating hot spot;

[0042] Determine the preheating bandwidth resources based on the total platform resources and the preheating allocation ratio;

[0043] Determine the total number of preheating spots according to the preheating bandwidth resources and the single-point preheating resource requirements;

[0044] A preheating spot is selected from the candidate preheating spots based on the total number of preheating spots and the heat levels of the candidate preheating spots.

[0045] In addition, to achieve the above-mentioned purpose, the present application also proposes a preheating point determination device, the device comprising:

[0046] A determination module, used to determine the playback frequency and first screen playback time corresponding to each playback point according to the historical playback behavior data, wherein the first screen playback time is the interval between the time when the user requests to retrieve the image and the time when the image corresponding to the playback point is first displayed in the user device, and the playback point is a device or apparatus for capturing images at a preset point;

[0047] A screening module, configured to select candidate preheating spots from the playback spots based on the playback frequency and the first screen playback time;

[0048] A heat module is used to determine the heat corresponding to each candidate preheating point based on the heat parameter;

[0049] The selection module is used to select a preheating point from the candidate preheating points based on the heat levels of the candidate preheating points.

[0050] In addition, to achieve the above-mentioned purpose, the present application also proposes a preheating point determination device, which includes: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the computer program is configured to implement the steps of the preheating point determination method as described above.

[0051] In addition, to achieve the above-mentioned purpose, the present application also proposes a storage medium, which is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by a processor, the steps of the preheating point determination method as described above are implemented.

[0052] In addition, to achieve the above-mentioned purpose, the present application also proposes a computer program product, which includes a computer program. When the computer program is executed by a processor, the steps of the preheating point determination method as described in any one of the above items are implemented.

[0053] One or more technical solutions proposed in this application have at least the following technical effects:

[0054] Since the candidate pre-hotspot locations with high frequency of access and long first-screen playback time can be quickly determined based on historical playback behavior data analysis, and further selection can be made based on the popularity of each candidate pre-hotspot location in combination with relevant settings, it is ensured that the candidate pre-hotspot locations can be reasonably selected as pre-hotspot locations, thus realizing the automatic selection of pre-hotspot locations and reducing the manpower burden. BRIEF DESCRIPTION OF THE DRAWINGS

[0055] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0056] 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, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0057] Figure 1 A schematic diagram of a flow chart provided for the first embodiment of the method for determining the preheating point of the present application;

[0058] Figure 2 A schematic diagram of a flow chart provided for Embodiment 2 of the method for determining the preheating point of the present application;

[0059] Figure 3 A schematic diagram of a flow chart provided for Embodiment 3 of the method for determining the preheating point of the present application;

[0060] Figure 4 This is a schematic diagram of the overall process of determining the preheating point in one embodiment of the present application;

[0061] Figure 5 This is a schematic diagram of the module structure of the preheating point determination device according to an embodiment of the present application;

[0062] Figure 6 Schematic diagram of the device structure of the hardware operating environment involved in the preheating point determination method in the embodiment of the present application.

[0063] The purpose, features and advantages of this application will be further described in conjunction with the embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0064] It should be understood that the specific embodiments described herein are only used to explain the technical solutions of the present application and are not used to limit the present application.

[0065] In order to better understand the technical solution of the present application, a detailed description will be given below in conjunction with the accompanying drawings and specific implementation methods.

[0066] Based on this, the present application embodiment provides a method for determining a preheating point, referring to Figure 1 , Figure 1 This is a flow chart of the first embodiment of the preheating point determination method of the present application.

[0067] In this embodiment, the preheating point determination method includes steps S10 to S40:

[0068] Step S10: Determine the playback frequency and first screen playback time corresponding to each playback point according to the historical playback behavior data.

[0069] It should be noted that the executor of this embodiment can be a video playback platform that manages multiple playback points, or a pre-hot spot position determination device set in the video playback platform, or a pre-hot spot position determination device that is independent of the video playback platform but can manage and control the video playback platform. The pre-hot spot position determination device can be an electronic device such as a personal computer or a server, or other devices that can achieve the same or similar functions. This embodiment does not limit this. In this embodiment and the following embodiments, the pre-hot spot position determination method of this application is explained by taking the pre-hot spot position determination device as an example.

[0070] It should be noted that the first screen playback time can be the interval between the moment when the user requests to retrieve the image and the moment when the image corresponding to the playback point is first displayed on the user's device. The playback point can be a device or apparatus that captures images at a preset point, such as a camera, or other similar devices.

[0071] In actual use, the historical playback behavior data can be analyzed and processed to count the number of playbacks at each playback point and the first-screen playback duration of each playback. Then, the playback frequency of the playback point can be obtained by dividing the playback duration by the statistical duration, and the average, maximum, minimum or median of the first-screen playback duration of multiple playbacks can be used as the first-screen playback time of the playback point.

[0072] Among them, the historical playback behavior data may be user playback behavior data collected previously, for example: the user playback behavior data may be "the user requests to schedule the image of playback point B during time period A, the total playback time is 10 seconds, and the first screen loading time is 1 second."

[0073] Of course, this is only an illustrative explanation for ease of understanding, and the specific format of the user playback behavior data is not specifically limited. According to actual needs, the user playback behavior data can be recorded in a more concise format, such as "Time: A, add: B, Atime: 10, ft_time: 1". This embodiment does not limit this.

[0074] Step S20: selecting candidate preheating points from the playback points based on the playback frequency and the first screen playback time.

[0075] It should be noted that the higher the playback frequency, the more times the playback point is played by users. If the loading is slow, the playback point with high playback frequency will have a greater impact than the playback point with low playback frequency. The longer the first screen playback time is, the slower the first screen loading speed is when the video of the playback point is played. The selection of preheating points is actually to eliminate this impact. Based on this, some points with high playback frequency and long first screen playback time can be selected as candidate preheating points.

[0076] In a specific implementation, the administrator of the preheating spot determination device can set the preheating screening rules in advance, and then select candidate preheating spots from the playback points based on the playback frequency and the first-screen playback time. For example: the preheating screening rules are set to the playback frequency being greater than a preset frequency threshold, or the first-screen playback time being greater than a preset duration threshold, then the playback point is selected as a candidate preheating spot; or, the preheating screening rules are set to the playback frequency being greater than a preset frequency threshold, and the first-screen playback time being greater than a preset duration threshold, then the playback point is selected as a candidate preheating spot.

[0077] Step S30: determining the heat corresponding to each candidate preheating point based on the heat parameter;

[0078] Step S40: selecting a preheating point from the candidate preheating points based on the heat levels of the candidate preheating points.

[0079] It should be noted that the heat parameter may be a parameter used when calculating the heat, and the specific heat parameter used may be pre-set by a manager of the preheating point determination device.

[0080] In actual use, when pre-fetching streams for pre-hot spots, the bandwidth resources of the video platform will be occupied, and the processing and caching of video streams will further occupy the memory resources and computing resources of the video platform. The number of pre-hot spots set determines the number of playback spots required for pre-fetching streams. If too many pre-hot spots are set, a large amount of resources of the video platform may be occupied, and the pre-fetched streams are generally continuous, which will continue to occupy a large amount of bandwidth resources, memory resources and computing resources of the video platform, and may even last for a long time, which may cause the video platform to be unable to respond to other normal media stream requests in a timely manner, which will directly affect the platform's services. Quality and user experience, therefore, after determining the candidate preheating spots, further selection is required. Under the premise that the video platform is not affected, the part that most needs preheating is selected as the preheating spot. The heat of the playback point is actually used to characterize the impact of the playback point on the platform when it is played slowly. Therefore, the heat corresponding to each candidate preheating spot can be determined based on the heat parameter, and then the preheating spot can be selected from the candidate preheating spots according to the heat of the candidate preheating spots, so as to ensure that when the number of selectable preheating spots is limited, the candidate preheating spots with higher heat are selected as the preheating spots.

[0081] In a possible implementation of this embodiment, in order to prevent the setting of the preheating point from occupying too many resources, step S40 shown in this embodiment may include:

[0082] Estimate the single-point preheating resource demand according to the preheating resource demand corresponding to each candidate preheating hot spot, where the single-point preheating resource demand is the bandwidth resource required for prefetching a flow for a single preheating hot spot;

[0083] Determine the preheating bandwidth resources based on the total platform resources and the preheating allocation ratio;

[0084] Determine the total number of preheating spots according to the preheating bandwidth resources and the single-point preheating resource requirements;

[0085] A preheating spot is selected from the candidate preheating spots based on the total number of preheating spots and the heat levels of the candidate preheating spots.

[0086] It should be noted that the single-point preheating resource requirement refers to the bandwidth resources required for prefetching a flow for a single preheating hot spot.

[0087] It is understandable that if some candidate preheating spots whose scores in the heat scoring results are greater than the score threshold are selected as preheating spots, then due to the uncertainty of the number of candidate preheating spots whose scores are greater than the score threshold, too many playback spots may be selected as preheating spots. In order to determine the number of selectable preheating spots, it is necessary to first determine the bandwidth resources required for preheating a single preheating spot. Therefore, the single-point preheating resource requirements can be first estimated based on the preheating resource requirements corresponding to each candidate preheating spot.

[0088] In actual use, the maximum value, minimum value, average value or median of the preheating resource requirements corresponding to each candidate preheating hot spot can be obtained, and the calculated result is used as the single-point preheating resource requirement.

[0089] Among them, the specific requirements for using the value can be determined according to actual needs. For example, if it is strictly forbidden for the bandwidth resources occupied by the preheating spot to exceed the preset resources, the calculated maximum value can be used as the single-point preheating resource demand; if the bandwidth resources occupied by the preheating spot are allowed to exceed the preset resources, and the amount of excess resources allowed is large, the calculated minimum value can be used as the single-point preheating resource demand; if the bandwidth resources occupied by the preheating spot are expected to be close to the preset resources, the calculated average or median can be used as the single-point preheating resource demand.

[0090] It should be noted that the total platform resources may be the total amount of bandwidth resources available on the video platform, and the preheating allocation ratio may be the ratio of bandwidth resources that can be occupied by preheating hot spots. The preheating bandwidth resources may be determined by multiplying the total platform resources by the preheating allocation ratio.

[0091] In actual use, the preheating bandwidth resources can be divided by the single-point preheating resource requirements to obtain the total number of preheating hot spots. Since the divisor may not be an integer, the divisor can be rounded up or down, and the rounded value is used as the total number of preheating hot spots.

[0092] In actual use, after determining the total number N of pre-hotspot positions, the candidate pre-hotspot positions can be sorted from high to low based on their popularity, and then the top N candidate pre-hotspot positions in the sorting result can be selected as pre-hotspot positions to strictly control the number of pre-hotspot positions, avoid the pre-fetched streams of the pre-hotspot positions occupying too many resources, and at the same time ensure that the playback points with higher popularity are preferentially selected as pre-hotspot positions.

[0093] This embodiment provides a method for determining a pre-hotspot position. Since the candidate pre-hotspot positions that are frequently accessed and take a long time to play on the first screen can be quickly determined based on historical playback behavior data analysis, further selection is performed based on the popularity of each candidate pre-hotspot position in combination with relevant settings, ensuring that the candidate pre-hotspot positions can be reasonably selected as pre-hotspot positions, realizing automatic selection of pre-hotspot positions and reducing the manpower burden.

[0094] Based on the first embodiment of the present application, in the second embodiment of the present application, the same or similar contents as those in the above-mentioned embodiment 1 can be referred to the above introduction and will not be repeated later.

[0095] In this embodiment, the popularity parameters may include playback frequency and first screen playback time;

[0096] On this basis, please refer to Figure 2 , step S30 may include steps S301 to S302:

[0097] Step S301: determining a playback frequency score corresponding to each candidate preheating spot based on the playback frequency corresponding to the candidate preheating spot, and determining a first screen playback time score corresponding to each candidate preheating spot based on the first screen playback time corresponding to the candidate preheating spot.

[0098] It should be noted that the playback frequency score is a quantitative score of the popularity of the candidate pre-hot spot calculated from the perspective of playback frequency. Similarly, the first screen time score is a quantitative score of the popularity of the candidate pre-hot spot calculated from the perspective of first screen playback time.

[0099] In a possible implementation of this embodiment, in order to ensure the rationality of the heat rating result, step S301 in this embodiment may include steps S3011 to S3014:

[0100] Step S3011: Calculate the difference between the playback frequency of each candidate preheating point and the frequency threshold, and determine the frequency threshold difference corresponding to each candidate preheating point.

[0101] It should be noted that the frequency threshold may be an average or median of the frequencies at which each playback point is visited, and is used to characterize the frequency at which a playback point of average popularity is visited.

[0102] The difference between the playback frequency of the candidate preheating point and the frequency threshold, that is, the frequency threshold difference corresponding to the candidate preheating point, can be used to characterize the difference between the candidate preheating point and the playback point of average popularity in terms of playback frequency.

[0103] Step S3012: Determine the target difference interval to which the frequency threshold difference of each candidate preheating point belongs.

[0104] In actual use, the administrator of the preheating point determination device can set multiple numerical intervals for the frequency threshold difference in advance. After obtaining the frequency threshold difference of each candidate preheating point, the numerical interval to which the frequency threshold difference belongs can be determined, and the numerical interval can be used as the target difference interval.

[0105] For example: assuming that the preset numerical intervals include 1-10, 11-100, 100-1000, 1000-10000, 10000 and above, if the frequency threshold difference of candidate preheating spot A is 500, then the interval 100-1000 is the target difference interval corresponding to the candidate preheating spot A.

[0106] Step S3013: determining the target time-consuming interval to which the first screen playback time corresponding to each candidate preheating point belongs.

[0107] It should be noted that the administrator of the preheating point determination device can set multiple numerical intervals for the first-screen playback time in advance. After obtaining the first-screen playback time corresponding to the candidate preheating point, the first-screen playback time corresponding to the candidate preheating point can be compared with each numerical interval to determine the numerical interval to which the first-screen playback time corresponding to the candidate preheating point belongs, and use the numerical interval as the target time interval.

[0108] Of course, when determining the target time interval to which the first-screen playback time corresponding to the candidate preheating point belongs, the first-screen playback time corresponding to the candidate preheating point can still be calculated by first calculating the difference between the first-screen playback time corresponding to the candidate preheating point and the time threshold (the time threshold can also be the first-screen playback time of a playback point with average popularity, and the time threshold can also be determined by the average value or median), and then determining the target time interval corresponding to the difference. This embodiment does not impose any restrictions on this.

[0109] Step S3014: Find the interval score corresponding to the target time-consuming interval to obtain the first screen time-consuming score corresponding to each candidate preheating hotspot, and find the interval score corresponding to the target difference interval to obtain the playback frequency score corresponding to each candidate preheating hotspot.

[0110] It should be noted that the administrator of the preheating point determination device can set corresponding interval scores for each numerical interval. The later the numerical interval is, that is, the larger the interval start value and / or interval end value of the numerical interval is, the larger the corresponding interval score is.

[0111] In actual use, the interval score of the target time consumption interval corresponding to the candidate prehot spot can be used as the first screen time consumption score corresponding to the candidate prehot spot, thereby obtaining the first screen time consumption score corresponding to each candidate prehot spot; similarly, the interval score corresponding to the target difference interval corresponding to the candidate prehot spot can be used as the playback frequency score corresponding to the candidate prehot spot, thereby obtaining the playback frequency score corresponding to each candidate prehot spot.

[0112] Step S302: Generate a heat score result corresponding to each candidate preheating spot according to the playback frequency score and the first screen time consumption score, wherein the heat score result is used to represent the heat level of the candidate preheating spot.

[0113] It should be noted that, in order to make a reasonable selection, it is necessary to score each candidate preheating spot and generate a heat score result corresponding to each candidate preheating spot.

[0114] Among them, the heat score result is used to characterize the heat of the candidate preheating point. The heat of the candidate preheating point refers to the impact of the long loading time of the candidate preheating point on the video platform, which can be regarded as the demand for pre-fetching the stream at this point. The higher the heat, the more it is necessary to pre-fetch the stream for this playback point to increase the first screen loading speed. Conversely, the lower the heat, the less it is necessary to pre-fetch the stream for this playback point.

[0115] In actual use, in order to comprehensively score each candidate preheating spot in terms of playback frequency and first-screen playback time, the playback frequency score and first-screen playback time score corresponding to the candidate preheating spot can be added respectively, and the obtained sum can be used as the heat score result corresponding to the candidate preheating spot.

[0116] Of course, other methods can also be used for calculation, such as weighted summing of the playback frequency score and the first screen time score corresponding to the candidate preheating spot, and using the obtained result as the heat score result corresponding to the candidate preheating spot, wherein the weighted coefficient in the weighted summing can be pre-set by the administrator of the preheating spot determination device. Of course, multiplication can also be used, for example: the product of the playback frequency score and the first screen time score is used as the heat score result corresponding to the candidate preheating spot.

[0117] In actual use, the heat score result is used to characterize the heat of the candidate preheating spot. Therefore, the preheating spot can be selected from the candidate preheating spot based on the heat score result. In order to facilitate the selection, the heat score result can be characterized in the form of a score, such as: the higher the score, the higher the heat of the candidate preheating spot; the lower the score, the lower the heat of the candidate preheating spot.

[0118] Based on this, when actually selecting the preheating spot, a corresponding score threshold may be set for the heat scoring result, and some candidate preheating spots with scores greater than the score threshold in the corresponding heat scoring result may be selected as the preheating spot.

[0119] In a possible implementation of this embodiment, the heat score result can also be generated in combination with the preheating effect (such as the preheating improvement ratio, which can also be called the preheating improvement amplitude) to ensure that the heat score result is more reasonable. In this case, the heat parameters may include the playback frequency, the first screen playback time and the preheating improvement ratio;

[0120] The step S30 in this embodiment may include:

[0121] Estimate the time required to preheat the first screen for each candidate preheating hotspot;

[0122] Determine the preheating improvement ratio corresponding to each candidate preheating hot spot according to the preheating first screen time consumption and the first screen playback time consumption;

[0123] The heat corresponding to each candidate preheating hot spot is determined according to the preheating improvement ratio, the playing frequency and the first screen time consumption.

[0124] It should be noted that the preheating first screen time consumption may be the first screen playback time consumption of the candidate preheating hotspot after preheating the candidate preheating hotspot. The preheating improvement ratio may be the reduction ratio of the first screen playback time before and after preheating.

[0125] In actual use, the time consumption for preheating the first screen corresponding to the candidate preheating hotspot can be estimated according to the device information, network status, etc. of the candidate preheating hotspot by pre-setting an algorithm or an intelligent model.

[0126] Of course, you can also use tracking points to record the time it takes for the video platform to call the video data of the candidate preheating hotspots, and estimate the preheating first screen time corresponding to the candidate preheating hotspots based on the average time consumed.

[0127] In actual application, the difference between the first screen preheating time and the first screen playback time can be calculated, and the ratio of the difference to the first screen playback time can be used as the preheating improvement ratio corresponding to the candidate preheating hot spot.

[0128] In actual use, after determining the preheating boost ratio, the preheating boost ratio can be combined with the playback frequency and the first screen playback time as preheating parameters, so as to calculate the popularity corresponding to each candidate preheating hotspot. For example, the ratio interval of the preheating boost ratio can be determined, and the score value corresponding to the ratio interval can be used as the boost ratio score corresponding to the candidate preheating hotspot, or the preheating boost ratio can be multiplied by a preset constant, and the obtained product can be used as the boost ratio score corresponding to the candidate preheating hotspot.

[0129] After determining the improvement ratio score, the playback frequency score can be determined according to the playback frequency, and the first screen time score can be determined according to the first screen playback time. Then, the improvement ratio score, the playback frequency score and the first screen time score are comprehensively considered to construct the heat score results corresponding to each candidate preheating spot. The heat score results are used to represent the heat corresponding to each candidate preheating spot.

[0130] Among them, determining the playback frequency score according to the playback frequency and determining the first screen time consumption score according to the first screen playback time consumption are consistent with the above implementation method, and the calculation method of the combination of the improvement ratio score, the playback frequency score and the first screen time consumption score can also be summed or weighted summed, which is similar to constructing the heat score results corresponding to each candidate preheating spot according to the playback frequency score and the first screen time consumption score, and will not be repeated here.

[0131] In a possible implementation of this embodiment, the popularity score result can also be generated in combination with whether the video has been preheated before, so as to ensure that the popularity score result is more reasonable. In this case, the preheating parameters may include the playback frequency, the first screen playback time, and the historical preheating label;

[0132] Step S30 in this embodiment may include:

[0133] Determine the historical preheating label corresponding to each candidate preheating point according to the historical preheating record;

[0134] The heat corresponding to each candidate preheating hot spot is determined according to the historical preheating label, the playback frequency, and the first screen time consumption.

[0135] It should be noted that the historical preheating record may be a record of previously selected preheating hot spots. The historical preheating tag is used to indicate whether the candidate preheating hot spot was previously selected as the preheating hot spot.

[0136] In actual use, it can be determined whether the candidate preheating point has been selected as the preheating point according to the historical preheating records, so as to set the corresponding historical preheating label.

[0137] In actual use, the preheating record score can be constructed based on the historical preheating tags, the playback frequency score can be determined based on the playback frequency, and the first screen time score can be determined based on the first screen playback time. After that, the preheating record score, playback frequency score and first screen time score are combined to construct the heat score results corresponding to each candidate preheating hot spot, and the heat score results are used to represent the heat corresponding to each candidate preheating hot spot.

[0138] Among them, determining the playback frequency score according to the playback frequency and determining the first screen time consumption score according to the first screen playback time consumption are consistent with the above implementation method, and the calculation method of the combination of the preheating record score, the playback frequency score and the first screen time consumption score can also be summed or weighted summed, which is similar to constructing the heat score results corresponding to each candidate preheating hot spot according to the playback frequency score and the first screen time consumption score, and will not be repeated here.

[0139] The implementation method of constructing the warm-up record score based on the historical warm-up tags can be adjusted according to actual needs, for example:

[0140] If the actual demand is that the candidate preheating spot that has not been selected as the preheating hotspot is selected first, then if the historical preheating tag is that the candidate preheating hotspot has not been selected as the preheating hotspot, the preheating record score can be set to a higher level, such as 1; conversely, if the historical preheating tag is that the candidate preheating hotspot has been selected as the preheating hotspot, the preheating record score can be set to a lower level, such as 0;

[0141] If the actual demand is to give priority to being selected as the preheating spot, then if the historical preheating label is that the candidate preheating spot was not selected as the preheating spot, the preheating record score can be set to a lower level, such as set to 0; conversely, if the historical preheating label is that the candidate preheating spot was selected as the preheating spot, the preheating record score can be set to a higher level, such as set to 1.

[0142] In a possible implementation of this embodiment, in order to ensure that when selecting the preheating point, the importance of each playback point can be comprehensively considered for selection, step S30 in this embodiment may include:

[0143] Determine the importance of each candidate preheating spot;

[0144] Determine a correction coefficient corresponding to the importance of the preheating point;

[0145] Determine a heat parameter score for each candidate preheating point, and correct each heat parameter score based on the correction coefficient;

[0146] Based on the corrected scores of the heat parameters, the heat corresponding to each candidate preheating point is determined.

[0147] It should be noted that the importance of the playback point is the degree of importance of the playback point, and the correction coefficient can be a positive number. The higher the importance of the playback point, the larger the corresponding correction coefficient. Conversely, the lower the importance of the playback point, the smaller the corresponding correction coefficient.

[0148] In actual use, the heat parameter score of each candidate preheating point can be calculated based on the heat parameter, and then the heat parameter score is multiplied by the correction coefficient, and the product obtained is used as the heat scoring result to characterize the heat corresponding to each candidate preheating point.

[0149] Among them, the method for determining the heat parameter score is consistent with the method of generating the heat score results corresponding to each candidate preheating spot according to the playback frequency score and the first screen time consumption score corresponding to each candidate preheating spot, and will not be repeated here.

[0150] It is understandable that when generating the heat rating results, multiple factors such as playback frequency and first screen playback time are taken into consideration, which can ensure the rationality of the heat rating results, thereby ensuring that the preheating spots can be reasonably selected.

[0151] In a possible implementation of this embodiment, in order to ensure that the importance of each candidate preheating point can be reasonably determined, the step of determining the importance of each candidate preheating point in this embodiment may include:

[0152] Obtain the point location, point setting time and point-related services corresponding to each candidate preheating point;

[0153] Determining the importance level of the location according to the location of the point;

[0154] Determine the importance level of the moment according to the point setting moment;

[0155] Obtaining the business importance level corresponding to the business associated with the point;

[0156] The importance level identifier corresponding to each candidate preheating spot is determined according to the location importance level, the time importance level and the service importance level, and the importance level is used to characterize the importance of the preheating spot.

[0157] It should be noted that the point location may be the location where the candidate preheat point captures the image, the point setting time may be the time when the candidate preheat point is set, and the point-associated service may be a service associated with the candidate preheat point, such as: intelligent recognition, intelligent detection, etc.

[0158] In actual use, the area to which the point location belongs can be detected to determine whether the area is a specific important area, such as a crossroads. If it belongs to a specific important area, the importance level of the important area can be used as the location importance level; if it does not belong to a specific important area, the location importance level can be set to the default value.

[0159] When determining the moment importance level, the difference between the point setting time and the current time can be calculated, and then the moment importance level is generated based on the difference. For example, if according to actual needs, the earlier the playback point is set, the higher the importance, then the larger the difference is, the higher the moment importance level, and the smaller the difference is, the lower the moment importance level; if according to actual needs, the later the playback point is set, the higher the importance, then the smaller the difference is, the higher the moment importance level, and the larger the difference is, the lower the moment importance level.

[0160] In actual application, the importance level of the point-associated business corresponding to the candidate preheating spot may be used as the importance level of the business corresponding to the candidate preheating spot.

[0161] In a specific implementation, the maximum, minimum or average value among the location importance level, the time importance level and the service importance level may be used as the importance level corresponding to the candidate preheating spot, and the importance level is used to characterize the importance of the preheating spot.

[0162] It should be noted that the above-mentioned methods of determining the heat score results (i.e., methods of determining the heat of candidate preheating hot spots) can be combined in any way to construct a new method of generating heat score results, for example: generating the heat score results corresponding to each candidate preheating hot spot according to the improvement ratio score, preheating record score, playback frequency score and first screen time score; if necessary, the heat score results corresponding to each candidate preheating hot spot can also be generated based on the improvement ratio score, preheating record score, playback frequency score and first screen time score in combination with the correction coefficient.

[0163] This embodiment provides a method for determining a preheating spot. Since a heat score result can be generated in a variety of different ways, it is ensured that the generated heat score result can correctly characterize the heat of each candidate preheating spot, and the preheating spot can be reasonably selected.

[0164] Based on the first embodiment of the present application, in the third embodiment of the present application, the same or similar contents as those in the first embodiment can be referred to the above description, and will not be described in detail later. Figure 3 , step S10 may include steps S101 to S105:

[0165] Step S101: Obtain statistical analysis duration, data screening conditions, and preheating screening rules.

[0166] It should be noted that the statistical analysis duration, data screening conditions and preheating screening rules can all be set in advance by the administrator of the preheating point determination device, among which the statistical analysis duration is used to specify the collection time span of the historical data to be analyzed, for example: setting the statistical analysis duration to within 2 days or 1 day; the data screening conditions are used to filter part of the data that needs to be statistically analyzed from the historical playback behavior data, and the data screening conditions can be set according to one or more of the point identification, user identification, behavior category, etc.

[0167] Step S102: Determine the statistical time period according to the current time and the statistical analysis duration.

[0168] Step S103: searching for historical playback behavior data whose corresponding collection time is within the statistical period, and generating a behavior data set.

[0169] It should be noted that since the video platform may serve a large number of users, the historical playback behavior data is actually massive. Direct full analysis may take a very long time and require extremely high computing resources. This method is not ideal in practical application. In addition, the popularity of each playback point may change greatly over time. Historical data that is too far away from the current moment is not very referenceable. Therefore, only part of the data can be analyzed. Based on this, the administrator of the preheating point determination equipment can set the corresponding statistical analysis time.

[0170] In actual use, the collection time period of the historical playback behavior data to be extracted, that is, the statistical period, can be assembled according to the current time and the statistical analysis duration.

[0171] For example: Assuming the current time is 09-18 9:00 and the statistical analysis duration is within 1 day, the statistical period at this time is: 09-17 9:00 to 09-18 9:00.

[0172] It is understandable that after obtaining the statistical period, the historical playback behavior data whose corresponding collection time is within the statistical period can be searched, and then the found data can be aggregated into a set to obtain the behavior data set.

[0173] Step S104: filtering the behavior data set according to the data filtering condition to generate a filtered behavior data set.

[0174] It should be noted that when collecting historical user behaviors, some data may not be related to the pre-hotspots, for example: users performing configuration updates, playing historical videos cached locally, etc. At the same time, it is possible that some playback points have been set so that they cannot be used as pre-hotspots, or some users have been marked as not included in the statistical analysis (such as test users are used for testing and do not represent the actual user's operating habits, so they may not be included in the statistical analysis). In order to avoid analyzing such invalid data, the administrator of the pre-hotspot determination device can pre-set data filtering conditions. After obtaining the behavior data set, the behavior data set can be filtered according to the data filtering conditions to remove such invalid data from the collection, and the processed behavior data set can be used as the filtered behavior data set.

[0175] Step S105: determining the playback frequency and first screen playback time corresponding to each playback point according to the historical playback behavior data in the screening behavior data set.

[0176] It is understandable that after filtering, the filtered behavior data set actually contains historical playback behavior data related to the selected preheating point. Therefore, the historical playback behavior data in the filtered behavior data set can be analyzed and processed to determine the playback frequency corresponding to each playback point and the first screen playback time.

[0177] In a possible implementation of this embodiment, the update of the preheating point may be performed in an automatic triggering manner to ensure that the preheating point can be updated periodically. In this case, step S101 of this embodiment may include:

[0178] When monitoring that the triggering condition of the preheating update task is met, obtaining task information corresponding to the preheating update task;

[0179] Statistical analysis duration, data screening conditions, and preheating screening rules are extracted from the task information.

[0180] It should be noted that if it is monitored that the triggering conditions of the preheating update task are met, it means that the preheating hot spots need to be updated at this time. In order to ensure that the preheating hot spots can be correctly screened, the task information corresponding to the preheating update task can be obtained, and the statistical analysis time, data screening conditions and preheating screening rules can be extracted from the task information.

[0181] Among them, the task information can be set in advance by the administrator of the preheating point determination equipment. In addition to the statistical analysis duration, data screening conditions, preheating screening rules and other information, the task information can also include more information, such as task name, task identifier, etc. If necessary, the threshold required for determining the preheating point can also be included in the task information. For example, the task information can also include the N value when selecting the preheating point.

[0182] In actual use, the administrator of the preheating hot spot determination device may set multiple preheating update tasks according to actual needs. The task information of each preheating update task may be the same or different, which is not limited in this embodiment.

[0183] In a possible implementation of this embodiment, it may be set that if at least one of the following is met, it is determined that the trigger condition of the preheating update task is met:

[0184] The system always meets the time matching rules in the trigger conditions;

[0185] The task information of the warm-up update task is updated;

[0186] The task execution instruction corresponding to the warm-up update task is detected.

[0187] It should be noted that the preheating update task can be a scheduled task that is executed periodically. The time matching rule can be pre-set by the administrator of the preheating hot spot determination device. The time matching rule can be set based on a time expression. For example, if the time matching rule is set to "0 0 2**?*", it means that the time matching rule is met at 2 a.m. every day.

[0188] In order to ensure that the management personnel can quickly update the preheating point after updating the determination conditions of the preheating point, it can be determined that the triggering conditions of the preheating update task are met when the task information of the preheating update task is updated. For example, if the statistical analysis time, data screening conditions and / or preheating screening rules in the task information of the preheating update task are updated, it can be determined that the triggering conditions of the preheating update task are met.

[0189] Of course, the preheating update task can also be triggered manually by the management personnel, or be triggered in a chain reaction after other tasks are executed. After manual triggering or other tasks are executed or triggered in a chain reaction, the preheating point determination device will generate or receive a task execution instruction. Therefore, when the task execution instruction corresponding to the preheating update task is detected, it can be determined that the triggering condition of the preheating update task is met.

[0190] For ease of understanding, now combined Figure 3 This is for illustration only, but not for limitation. Figure 3 The figure is a schematic diagram of the overall process of determining the preheating point in this embodiment.

[0191] like Figure 4 As shown, in the process of determining the preheating point, the preheating point determining device may include the following core functions:

[0192] Intelligent analysis function: automatically collect and analyze user playback behavior data, and identify high-frequency playback points that take a long time to play the first screen.

[0193] Dynamic resource allocation function: Administrators can allocate network bandwidth resources required for intelligent preheating based on factors such as network conditions, server load and user behavior.

[0194] Preheating execution function: According to the results of intelligent analysis, the preheating task is automatically executed, the preheating hot spots are selected, and the streams are pre-fetched for the preheating hot spots, ensuring that the first screen loading speed can be increased for the high-frequency playback points and the first screen playback that loads slowly, so that it can achieve the effect of opening in seconds.

[0195] Real-time adjustment mechanism: Create a scheduled task to analyze and identify the information of the points that need the most preheating based on the latest streaming behavior data of the platform, so as to continuously and dynamically update the points for intelligent preheating, and improve the streaming and playback experience of the user platform under the condition of limited allocated intelligent preheating network resources.

[0196] The specific execution process is as follows:

[0197] After the deployment of the preheating point determination device is completed, it will review the previous (such as the previous day) streaming media playback data (i.e., historical playback behavior data) according to the statistical analysis time and data screening conditions, and store this data properly; afterwards, it will analyze the stored streaming media playback data to determine the playback frequency and first-screen playback time corresponding to each playback point, and screen out the playback node positions with preheating requirements (i.e., candidate preheating points) based on the screening criteria (i.e., preheating screening rules, such as screening based on playback frequency and first-screen playback loading time). Then, in combination with relevant algorithms or models, a heat score is calculated for each candidate preheating point (the calculation of this heat score comprehensively considers factors such as the importance of the playback point and the access frequency), and then, in combination with the currently available network resource ratio (such as the set N value), the point that most needs preheating is intelligently selected as the preheating point.

[0198] The execution process of the above pre-hotspot is executed through the scheduled task configuration. According to the configuration of the scheduled task, the historical playback behavior data will be automatically updated periodically, and the pre-hotspot will be automatically updated to ensure that the focus is always on the most popular playback point, making the most popular playback point the pre-hotspot;

[0199] In addition, if the administrator adjusts the network resource allocation ratio or modifies the point screening rules, that is, modifies the information related to the scheduled task, these new settings will be saved immediately and a scheduled task will be executed. According to the modification, the new rules will re-screen the most suitable preheating points to achieve timely dynamic updates, ensure the timeliness and accuracy of the preheating tasks, and automatically reallocate and prepare to execute new preheating update tasks according to the set time period.

[0200] This embodiment provides a method for determining a pre-hot spot. Since the historical playback behavior data can be screened at multiple levels according to relevant configurations, it is ensured that the screened data is reference-oriented, and data related to the pre-hot spot selection is analyzed, thereby avoiding the analysis and influence of invalid data and ensuring the effectiveness and accuracy of the method for determining the pre-hot spot.

[0201] It should be noted that the above examples are only used to understand the present application and do not constitute a limitation on the method for determining the preheating position of the present application. More simple transformations based on this technical concept are all within the scope of protection of the present application.

[0202] This application also provides a preheating point determination device, please refer to Figure 5 , the preheating point determining device comprises:

[0203] The determination module 10 is used to determine the playback frequency and first screen playback time corresponding to each playback point according to the historical playback behavior data. The first screen playback time is the interval between the time when the user requests to retrieve the image and the time when the image corresponding to the playback point is first displayed in the user device. The playback point is a device or apparatus for capturing images at a preset point;

[0204] A screening module 20, configured to select candidate preheating spots from the playback spots based on the playback frequency and the first screen playback time;

[0205] A heat module 30, for determining the heat corresponding to each candidate preheating point based on the heat parameter;

[0206] The selection module 40 is used to select a preheating point from the candidate preheating points based on the heat levels of the candidate preheating points.

[0207] The preheating point determination device provided by the present application adopts the preheating point determination method in the above-mentioned embodiment, and can solve the technical problems that the related technology manually sets the preheating point, which is costly, inefficient, and cannot be flexibly adjusted, resulting in poor actual effect. Compared with the prior art, the beneficial effects of the preheating point determination device provided by the present application are the same as the beneficial effects of the preheating point determination method provided by the above-mentioned embodiment, and other technical features in the preheating point determination device are the same as the features disclosed in the above-mentioned embodiment method, which will not be repeated here.

[0208] The present application provides a pre-hot spot position determination device, which includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the pre-hot spot position determination method in the above-mentioned embodiment 1.

[0209] Reference below Figure 6 , which shows a schematic diagram of the structure of a preheating point determination device suitable for implementing the embodiment of the present application. The preheating point determination device in the embodiment of the present application may include but is not limited to mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (Personal Digital Assistants), PADs (Portable Application Descriptions), PMPs (Portable Media Players), vehicle-mounted terminals (such as vehicle-mounted navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc. Figure 6 The preheating point determination device shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0210] like Figure 6 As shown, the preheating point determination device may include a processing device 1001 (e.g., a central processing unit, a graphics processor, etc.), which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM: Read Only Memory) 1002 or a program loaded from a storage device 1003 to a random access memory (RAM: Random Access Memory) 1004. In RAM1004, various programs and data required for the operation of the preheating point determination device are also stored. The processing device 1001, ROM1002, and RAM1004 are connected to each other through a bus 1005. An input / output (I / O) interface 1006 is also connected to the bus. Generally, the following systems can be connected to the I / O interface 1006: an input device 1007 including, for example, a touch screen, a touch pad, a keyboard, a mouse, an image sensor, a microphone, an accelerometer, a gyroscope, etc.; an output device 1008 including, for example, a liquid crystal display (LCD: Liquid Crystal Display), a speaker, a vibrator, etc.; a storage device 1003 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 1009. The communication device 1009 can allow the preheating point determination device to communicate with other devices wirelessly or by wire to exchange data. Although the preheating point determination device with various systems is shown in the figure, it should be understood that it is not required to implement or have all the systems shown. More or fewer systems can be implemented or provided instead.

[0211] In particular, according to the embodiments disclosed in the present application, the process described above with reference to the flowchart can be implemented as a computer software program. For example, the embodiments disclosed in the present application include a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network through a communication device, or installed from a storage device 1003, or installed from a ROM 1002. When the computer program is executed by the processing device 1001, the above-mentioned functions defined in the method of the embodiment disclosed in the present application are executed.

[0212] The preheating point determination device provided by the present application adopts the preheating point determination method in the above embodiment, which can solve the technical problem that the preheating point is set manually by the related technology, which is high in cost, low in efficiency, and cannot be flexibly adjusted, resulting in poor actual effect. Compared with the prior art, the beneficial effect of the preheating point determination device provided by the present application is the same as the beneficial effect of the preheating point determination method provided by the above embodiment, and the other technical features in the preheating point determination device are the same as the features disclosed in the method of the previous embodiment, which will not be repeated here.

[0213] It should be understood that the various parts disclosed in this application can be implemented by hardware, software, firmware or a combination thereof. In the description of the above embodiments, specific features, structures, materials or characteristics can be combined in any one or more embodiments or examples in a suitable manner.

[0214] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

[0215] The present application provides a computer-readable storage medium having computer-readable program instructions (ie, computer programs) stored thereon, and the computer-readable program instructions are used to execute the preheating point determination method in the above-mentioned embodiment.

[0216] The computer-readable storage medium provided in the present application may be, for example, a USB flash drive, but is not limited to electrical, magnetic, optical, electromagnetic, infrared systems or devices, or any combination thereof. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof. In this embodiment, the computer-readable storage medium may be any tangible medium containing or storing a program that may be used by or in conjunction with an instruction execution system, system, or device. The program code contained on the computer-readable storage medium may be transmitted using any suitable medium, including, but not limited to, wires, optical cables, RF (Radio Frequency), etc., or any suitable combination thereof.

[0217] The computer-readable storage medium may be included in the preheating point determination device; or may exist independently without being assembled into the preheating point determination device.

[0218] The computer-readable storage medium carries one or more programs. When the one or more programs are executed by the preheating point determination device, the preheating point determination device: determines the playback frequency and first screen playback time corresponding to each playback point according to the historical playback behavior data, the first screen playback time is the interval between the moment when the user requests to retrieve the image and the moment when the image corresponding to the playback point is first displayed in the user device, and the playback point is a device or apparatus for performing image acquisition at a preset point; based on the playback frequency and the first screen playback time, selects a candidate preheating point from the playback point through a preheating screening rule; scores each candidate preheating point to generate a heat score result corresponding to each candidate preheating point, and the heat score result is used to characterize the heat of the candidate preheating point; selects a preheating point from the candidate preheating point based on the heat score result.

[0219] Computer program code for performing the operations of the present application may be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0220] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present application. In this regard, each square box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two square boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0221] The modules involved in the embodiments described in this application may be implemented by software or hardware, wherein the name of the module does not constitute a limitation on the unit itself in some cases.

[0222] The readable storage medium provided by the present application is a computer-readable storage medium, which stores computer-readable program instructions (i.e., computer programs) for executing the above-mentioned preheating point determination method, and can solve the technical problems that the related art manually sets the preheating point, which is high in cost, low in efficiency, and cannot be flexibly adjusted, resulting in poor actual effect. Compared with the prior art, the beneficial effects of the computer-readable storage medium provided by the present application are the same as the beneficial effects of the preheating point determination method provided by the above-mentioned embodiment, and will not be repeated here.

[0223] The present application also provides a computer program product, including a computer program, which implements the steps of the preheating point determination method as described above when the computer program is executed by a processor.

[0224] The computer program product provided by the present application can solve the technical problems that the related art manually sets the preheating point, which is costly, inefficient, and cannot be flexibly adjusted, resulting in poor actual effects. Compared with the prior art, the beneficial effects of the computer program product provided by the present application are the same as those of the preheating point determination method provided in the above embodiment, and will not be elaborated here.

[0225] The above descriptions are only some embodiments of the present application, and are not intended to limit the patent scope of the present application. All equivalent structural changes made using the contents of the present application specification and drawings under the technical concept of the present application, or direct / indirect applications in other related technical fields are included in the patent protection scope of the present application.

Claims

1. A method for determining a preheating point, characterized in that: The method comprises: Determine the playback frequency and first screen playback time corresponding to each playback point according to the historical playback behavior data, wherein the first screen playback time is the interval between the time when the user requests to retrieve the image and the time when the image corresponding to the playback point is first displayed on the user's device, and the playback point is a device or apparatus for capturing images at a preset point; Selecting a candidate preheating point from the playback points based on the playback frequency and the first screen playback time; Based on the heat parameter, determine the heat corresponding to each candidate preheating point; A preheating point is selected from the candidate preheating points based on the heat levels of the candidate preheating points.

2. The method for determining the preheating point according to claim 1, wherein: The popularity parameters include playback frequency and first screen playback time; The step of determining the heat corresponding to each candidate preheating point based on the heat parameter includes: Determine the playback frequency score corresponding to each candidate preheating spot based on the playback frequency corresponding to the candidate preheating spot, and determine the first screen playback time score corresponding to each candidate preheating spot based on the first screen playback time corresponding to the candidate preheating spot; A heat score result corresponding to each candidate preheating hotspot is generated according to the playback frequency score and the first screen time consumption score, and the heat score result is used to characterize the heat level of the candidate preheating hotspot.

3. The method for determining the preheating point according to claim 2, wherein: The determining of the playback frequency score corresponding to each candidate preheating spot based on the playback frequency corresponding to the candidate preheating spot, and determining the first screen playback time score corresponding to each candidate preheating spot based on the first screen playback time corresponding to the candidate preheating spot, includes: Calculate the difference between the playback frequency of each candidate preheating point and the frequency threshold, and determine the frequency threshold difference corresponding to each candidate preheating point; Determine the target difference interval to which the frequency threshold difference of each candidate preheating point belongs; Determine the target time interval to which the first screen playback time corresponding to each candidate preheating spot belongs; The interval score corresponding to the target time-consuming interval is found to obtain the first screen time-consuming score corresponding to each candidate preheating hotspot, and the interval score corresponding to the target difference interval is found to obtain the playback frequency score corresponding to each candidate preheating hotspot.

4. The method for determining the preheating point according to claim 1, wherein: The popularity parameters include playback frequency, first screen playback time, and preheating improvement ratio; The step of determining the heat corresponding to each candidate preheating point based on the heat parameter includes: Estimate the time required to preheat the first screen for each candidate preheating hotspot; Determine the preheating improvement ratio corresponding to each candidate preheating hot spot according to the preheating first screen time consumption and the first screen playback time consumption; The heat corresponding to each candidate preheating hot spot is determined according to the preheating improvement ratio, the playback frequency and the first screen time consumption.

5. The method for determining the preheating point according to claim 1, wherein: The heat parameters include playback frequency, first screen playback time and historical preheating tags; The step of determining the heat corresponding to each candidate preheating point based on the heat parameter includes: Determine the historical preheating label corresponding to each candidate preheating point according to the historical preheating record, wherein the historical preheating label is used to indicate whether the candidate preheating point has been selected as the preheating point; The heat corresponding to each candidate preheating hot spot is determined according to the historical preheating label, the playback frequency, and the first screen time consumption.

6. The method for determining the preheating point according to claim 1, wherein: The step of determining the heat corresponding to each candidate preheating point based on the heat parameter includes: Determine the importance of each candidate preheating spot; Determine a correction coefficient corresponding to the importance of the preheating point; Determine a heat parameter score for each candidate preheating point, and correct each heat parameter score based on the correction coefficient; Based on the corrected scores of the heat parameters, the heat corresponding to each candidate preheating point is determined.

7. The method for determining the preheating point according to claim 6, wherein: Determining the importance of each candidate preheating point includes: Obtain the point location, point setting time and point-related services corresponding to each candidate preheating point; Determining the importance level of the location according to the location of the point; Determine the importance level of the moment according to the point setting moment; Obtaining the business importance level corresponding to the business associated with the point; The importance level corresponding to each candidate preheating spot is determined according to the location importance level, the time importance level and the service importance level, and the importance level is used to characterize the importance of the preheating spot.

8. The method for determining the preheating point according to any one of claims 1 to 7, characterized in that: The selecting a preheating point from the candidate preheating points based on the heat levels of the candidate preheating points includes: Estimate the single-point preheating resource demand according to the preheating resource demand corresponding to each candidate preheating hot spot, where the single-point preheating resource demand is the bandwidth resource required for prefetching a flow for a single preheating hot spot; Determine the preheating bandwidth resources based on the total platform resources and the preheating allocation ratio; Determine the total number of preheating spots according to the preheating bandwidth resources and the single-point preheating resource requirements; A preheating spot is selected from the candidate preheating spots based on the total number of preheating spots and the heat levels of the candidate preheating spots.

9. A preheating point determination device, characterized in that: The device comprises: A determination module, used to determine the playback frequency and first screen playback time corresponding to each playback point according to the historical playback behavior data, wherein the first screen playback time is the interval between the time when the user requests to retrieve the image and the time when the image corresponding to the playback point is first displayed in the user device, and the playback point is a device or apparatus for capturing images at a preset point; A screening module, configured to select candidate preheating spots from the playback spots based on the playback frequency and the first screen playback time; A heat module is used to determine the heat corresponding to each candidate preheating point based on the heat parameter; The selection module is used to select a preheating point from the candidate preheating points based on the heat levels of the candidate preheating points.

10. A preheating point determination device, characterized in that: The device comprises: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the computer program is configured to implement the steps of the preheating point determination method according to any one of claims 1 to 8.

Images