An operation information push method, device, terminal device and storage medium

Abstract

The present invention discloses an operation information pushing method, device, terminal device and storage medium. The method includes: comparing the similarity between the product to be pushed corresponding to the current operation information to be pushed and the product that has been pushed corresponding to the previous pushing cycle; in the case of determining that the two are not similar, comparing the population similarity between the target user group of the product to be pushed and the active populations of each channel; then, based on the population similarity, the historical active duration of users in each pushing channel, and the proposed promotion situation of each pushing channel in the current pushing cycle, calculating the first pushing weight corresponding to each pushing channel in the current pushing cycle; finally, based on the first pushing weight, determining the number of pushing times corresponding to each pushing channel. By implementing the present invention, the pushing strategy can be made more in line with the actual scenario requirements, thereby increasing the opening rate of the pushed operation information and enhancing the publicity effect.

Description

Technical Field

[0001] The present invention relates to the field of computer technologies, and in particular, to an operation information pushing method, apparatus, terminal device, and storage medium. Background Art

[0002] With the rapid development of the e-commerce industry, various e-commerce platforms have become important channels for product promotion and sales. To increase user stickiness and enhance the exposure of products, many merchants will, within the same pushing cycle, select different e-commerce platforms as pushing channels to push corresponding operation messages to users, such as event promotion, consultation pushing, advertisement notification, etc. By pushing operation messages to actively interact with users, the exposure of products can be increased.

[0003] Generally, after a pushing cycle ends, merchants often count the opening rates of the operation information pushed through each pushing channel in the previous pushing cycle. The opening rate represents the proportion of users who open the corresponding operation information. Based on the counted opening rates of each pushing channel, the pushing intensity of each pushing channel in the next pushing cycle is adjusted. For example, for a pushing channel with a high opening rate, the number of pushes is increased, and for a pushing channel with a low opening rate, the number of pushes is decreased, so as to improve the overall opening rate of the pushed operation information and enhance the promotion effect of the product.

[0004] However, the above method ignores the fitness of the products pushed in the previous and current push cycles to each push channel, and does not consider the traffic conditions of each push channel itself. It only adjusts based on the open rate of the operation information in the previous push, which may not improve the overall open rate of the operation information. For example, in the previous push cycle, the product corresponding to the pushed operation information is Product A, and the target user group of Product A is young women, and the most frequently used channel by young women is Channel B. At this time, the open rate of the operation information of Product A in Channel B may be higher than that in other channels. However, if the product corresponding to the pushed operation information in the next push cycle is Product C, and the target user group of Product B is young men, and the most frequently used channel by young men is Channel D, then the number of push times of the operation information corresponding to C in Channel D should be increased at this time. If only the open rate of the previous push cycle is used to push the operation information corresponding to C and increase its push times on Platform A, this obviously does not conform to the actual scenario and may even cause a decrease in the overall open rate. In addition, the traffic heat of each channel is also an important factor affecting the open rate. The larger the traffic and the higher the heat, the more users use the corresponding channel, and the greater the probability that the operation information is opened by users. Therefore, when adjusting the push strategy, the characteristics of the channel itself, such as channel traffic, should also be a factor to be considered. In summary, the existing push strategy does not comprehensively consider the adaptability of products and channels and the characteristics of the channels themselves, does not meet the actual scenario requirements, and is likely to lead to a poor open rate of the pushed operation information. Summary of the Invention

[0005] An embodiment of the present invention provides an operation information push method, device, terminal device and storage medium, which can make the push strategy more in line with the actual scenario, improve the open rate of the pushed operation information, and enhance the publicity effect.

[0006] An embodiment of the present invention provides an operation information push method, including:

[0007] When the current push cycle arrives, compare the similarity between the product to be pushed corresponding to the current operation information to be pushed and the product that has been pushed corresponding to the previous push cycle;

[0008] When the similarity is less than a preset similarity threshold, extract the historical purchase information of the similar products of the product to be pushed in all push channels, and determine the target user group of the product to be pushed according to the historical purchase information; wherein, the purchase information includes: the age of each purchaser and the gender of each purchaser; determine the active population of each push channel according to the historical active duration, age and gender of each user in each push channel;

[0009] With the number of people as the X-axis, age as the Y-axis, and gender as the Z-axis, the first projection space of the target user population and the second projection space of the active population of each push channel are constructed respectively; the first projection space is compared with each second projection space respectively, and the similarity between the first projection space and each second projection space is calculated according to the overlap rate of the projection points in the projection space, so as to obtain the population similarity between the target user population and the active population of each channel;

[0010] Determine the first push weight corresponding to each push channel in the current push cycle according to the similarity of each group, the historical active time of users in each push channel, and the proposed promotion of each push channel in the current push cycle;

[0011] According to the first push weight of each push channel, the first push number of the operation information to be pushed in each push channel in the current push cycle is determined, and according to the first push number, the current operation information to be pushed is pushed in each push channel; wherein, the first push weight is proportional to the first push number.

[0012] Furthermore, it also includes: when the similarity is greater than or equal to a preset similarity threshold, according to the push information opening rate of the operation information corresponding to the pushed product in each push channel in the previous push cycle, and the proposed promotion situation of each push channel in the current push cycle, determining the second push weight of each push channel in the current push cycle;

[0013] According to the second push weight of each push channel, the second push number of the operation information to be pushed in each push channel in the current push cycle is determined, and according to the second push number, the operation information to be pushed is pushed in each push channel; wherein the second push weight is proportional to the second push number.

[0014] Furthermore, before the operation information to be pushed is pushed on each push channel, it also includes:

[0015] For each push channel, the product with the largest sales volume and which is relevant to the product to be pushed in terms of product function in the current push channel is used as the product to be combined, and then the operation information of the product to be combined is generated; wherein the relevance between the product to be combined and the product to be pushed includes: the product functions are the same or they are products in the same package;

[0016] According to the correlation between the products to be combined and the products to be pushed, determine the connection information required for connecting the operation information of the products to be combined with the operation information to be pushed;

[0017] According to the acceptance information, the operation information of the product to be combined with the operation information to be pushed is combined to generate updated operation information to be pushed.

[0018] Further, before pushing the operation information to be pushed to each push channel, it further includes:

[0019] For each push channel, determine the display style of the operation information to be pushed according to the age range and gender of the active population in the current push channel, so as to push the operation information to be pushed to each push channel in the corresponding display style.

[0020] Further, when pushing the operation information to be pushed to each push channel, for each push channel, determine the push times of each time period according to the active time period distribution of the active population in the current push channel and the push times of the current push channel, and push the operation information to be pushed to the corresponding push channel according to the push times of each time period.

[0021] Further, after pushing the current operation information to be pushed to each push channel, it further includes:

[0022] For the open rate of the pushed operation information in each push channel, when it is detected that the growth rate of the open rate of the pushed information in any push channel exceeds the threshold, increase the push times of the corresponding push channel of the operation information to be pushed.

[0023] Based on the above method item embodiments, the present invention correspondingly provides device item embodiments;

[0024] An embodiment of the present invention provides an operation information push device, a product similarity calculation module, a population selection module, a population similarity calculation module, a first push weight determination module, and a first push module;

[0025] The product similarity calculation module is used to compare the similarity between the product to be pushed corresponding to the current operation information to be pushed and the product that has been pushed corresponding to the previous push cycle when the current push cycle arrives;

[0026] The population selection module is used to extract the historical purchase information of the similar products of the product to be pushed in all push channels when the similarity is less than the preset similarity threshold, and determine the target user group of the product to be pushed according to the historical purchase information; wherein, the purchase information includes: the age of each purchaser and the gender of each purchaser; determine the active population of each push channel according to the historical active duration, age and gender of each user in each push channel;

[0027] The population similarity calculation module is used to construct the first projection space of the target user population and the second projection spaces of the active populations of each push channel respectively with the number of people as the X-axis, age as the Y-axis, and gender as the Z-axis; compare the first projection space with each of the second projection spaces respectively, and calculate the similarity between the first projection space and each of the second projection spaces according to the coincidence rate of the projection points in the projection space, so as to obtain the population similarity between the target user population and the active populations of each channel.

[0028] The first push weight determination module is used to determine the first push weight corresponding to each push channel in the current push cycle according to the population similarities, the historical active duration of the users in each push channel, and the proposed promotion situation of each push channel in the current push cycle.

[0029] The first push module is used to determine the first push times of the operation information to be pushed in each push channel in the current push cycle according to the first push weight of each push channel, and push the current operation information to be pushed in each push channel according to the first push times; wherein, the first push weight is proportional to the first push times.

[0030] Furthermore, it further includes a second push weight determination module and a second push module;

[0031] The second push weight determination module is used to, when the similarity is greater than or equal to a preset similarity threshold, determine the second push weight of each push channel in the current push cycle according to the push information opening rate of the operation information corresponding to the products that have been pushed in each push channel in the previous push cycle and the proposed promotion situation of each push channel in the current push cycle.

[0032] The second push module is used to determine the second push times of the operation information to be pushed in each push channel in the current push cycle according to the second push weight of each push channel, and push the operation information to be pushed in each push channel according to the second push times; wherein, the second push weight is proportional to the second push times.

[0033] Based on the above method item embodiments, the present invention correspondingly provides terminal device item embodiments;

[0034] An embodiment of the present invention provides a terminal device, including a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor. When the processor executes the computer program, it implements the operation information push method described in any embodiment of the present invention.

[0035] Based on the above method item embodiments, the present invention correspondingly provides a storage medium item embodiment;

[0036] An embodiment of the present invention provides a storage medium, which includes a stored computer program. When the computer program runs, it controls the device where the storage medium is located to execute the operation information pushing method described in any one of the present invention.

[0037] By implementing the embodiments of the present invention, the following beneficial effects can be obtained:

[0038] The embodiments of the present invention provide an operation information pushing method, device, terminal device and storage medium. In the method, when a new pushing cycle arrives, first compare the similarity between the product to be pushed corresponding to the current operation information to be pushed and the product that has been pushed corresponding to the previous pushing cycle. When it is determined that the two are not similar, based on the number of people as the X-axis, age as the Y-axis, and gender as the Z-axis, respectively construct the first projection space of the target user group of the product to be pushed and the second projection space of the active user groups of each pushing channel; obtain the population similarity between the target user group of the product to be pushed and the active user groups of each pushing channel through the similarity between the first projection space and each second projection space; in this way, the population similarity between the target user group of the product to be pushed and the active user groups of each channel can be comprehensively compared from two dimensions of gender and age, and the adaptation degree of the current product to be pushed and each pushing channel can be learned through the similarity. Then, based on the population similarity, the historical active duration of the users in each pushing channel, and the proposed promotion situation of each pushing channel in the current pushing cycle, calculate the first pushing weight corresponding to each pushing channel in the current pushing cycle; the historical active duration of the users in each pushing channel can reflect the traffic heat of each pushing channel in the past period of time, and the proposed promotion situation of each pushing channel can reflect whether there will be a large increase in traffic in each pushing channel in the future. Generally speaking, if a channel sets a promotion activity, it will cause a rapid increase in traffic in the short term. By comprehensively considering the adaptation degree of the current product to be pushed and each pushing channel, the traffic heat of each pushing channel in the past period of time, and the traffic increase situation of each pushing channel in the future, determine the first pushing weight of each pushing channel. Finally, based on the first pushing weight, determine the number of pushing times corresponding to each pushing channel, so that the pushing channels with high adaptation degree and high traffic heat correspond to more pushing times, making the pushing channels more in line with the actual scenario requirements, thereby improving the opening rate of the pushed operation information and enhancing the publicity effect. Description of the Drawings

[0039] Figure 1 It is a flowchart of an operation information pushing method provided by an embodiment of the present invention.

[0040] Figure 2 It is a schematic diagram of the operation information of the product to be jointly promoted provided by an embodiment of the present invention.

[0041] Figure 3 It is a schematic diagram after combining operation information provided by an embodiment of the present invention.

[0042] Figure 4 It is a schematic structural diagram of an operation information push device provided by an embodiment of the present invention. Detailed implementation manners

[0043] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0044] As Figure 1 shown, an embodiment of the present invention provides an operation information push method, which at least includes the following steps:

[0045] Step S1: When the current push cycle arrives, compare the similarity between the product to be pushed corresponding to the current operation information to be pushed and the product that has been pushed corresponding to the previous push cycle.

[0046] Specifically, taking the operation information of product promotion as an example, the current operation information to be pushed corresponds to a product to be pushed, and the operation information that has been pushed in the previous push cycle corresponds to a product that has been pushed; respectively extract the features such as the specifications, functions, materials, and uses of the product to be pushed and the product that has been pushed. Combine the extracted features to generate the combined features of the product to be pushed and the combined features of the product that has been pushed respectively. Then, by calculating the Euclidean distance between the two combined features, determine the similarity between the product to be pushed and the product that has been pushed.

[0047] Step S2: When the similarity is less than a preset similarity threshold, extract the historical purchase information of the similar products of the product to be pushed in all push channels, and determine the target user group of the product to be pushed according to the historical purchase information; wherein, the purchase information includes: the age of each purchaser and the gender of each purchaser; determine the active population of each push channel according to the historical active duration, age, and gender of each user in each push channel.

[0048] Specifically, when it is determined that the similarity is less than the preset similarity threshold, it means that the product to be pushed in the current push cycle and the product that has been pushed corresponding to the previous push cycle are two different categories of products. At this time, the push strategy of the previous push cycle cannot be adopted and needs to be adjusted.

[0049] In a preferred embodiment, similar products to the products to be pushed refer to products whose similarity with the products to be pushed exceeds a preset similarity threshold, and the calculation method of the similarity is the same as the calculation method of the similarity in step S1. The above-mentioned historical purchase information refers to the purchase information of users in the previous push cycle; according to the age and gender of the purchasers who purchased similar products in all push channels, grouping is carried out by gender and age, and the age and gender of the purchasers in each group are the same; then the number of purchasers in each group is counted, and the group with a number greater than the preset number threshold is used as the group of the target user population. According to the grouping of the target user population, the age and gender of the target user population of similar products can be determined, that is, the target user population of similar products is determined, and finally the target user population of similar products is used as the target user population of the products to be pushed.

[0050] In a preferred embodiment, the active duration of each user in each push channel in the previous push cycle is used as the historical active duration of each user in the above push channels; based on the historical active duration, users whose active duration is less than the preset active duration are eliminated, and the remaining users are used as active users. Based on the age and gender of the active users, the active population of each push channel can be determined.

[0051] Step S3: With the number of people as the X-axis, age as the Y-axis, and gender as the Z-axis, construct the first projection space of the target user population and the second projection space of the active population of each push channel respectively; compare the first projection space with each second projection space respectively, and calculate the similarity between the first projection space and each second projection space according to the overlap rate of the projection points in the projection space, so as to obtain the population similarity between the target user population and the active population of each channel.

[0052] Specifically, for the target user population, according to the grouping of the target user population in the previous step, the number of people in each group is counted, and according to the number of people, age and gender of each group, projection points are generated in a three-dimensional direct coordinate system with the number of people as the X-axis, the age as the Y-axis, and the gender as the Z-axis to obtain the above-mentioned first projection space;

[0053] For the active population of each channel, firstly, the active users are grouped according to age and gender. Similarly, the age and gender of each active user in the same group are the same. The number of people in each group is counted. According to the number, age and gender of each group, projection points are generated in a three-dimensional direct coordinate system with the number of people as the X-axis, age as the Y-axis and gender as the Z-axis to obtain the above-mentioned second projection space.

[0054] Then, the first projection space is compared with the second projection space of each channel, the overlap rate in the projection space is calculated, and the similarity is determined according to the overlap rate, thereby obtaining the population similarity between the target user population and the active population of each channel.

[0055] Age and gender are two major influencing factors affecting the products demanded by users. The products demanded by men and women will show obvious differences, and the product demands among users of different age groups vary even more significantly. In this embodiment of the present invention, a similarity calculation method based on three-dimensional space projection is creatively adopted to calculate the similarity of the population by comprehensively considering two important dimensions of age and gender, which can better measure the similarity between the target user group of the product to be pushed and the active population of each push channel, so as to obtain the adaptation degree between the current product to be pushed and each push channel.

[0056] Step S4: Determine the first push weight corresponding to each push channel in the current push cycle according to the population similarity, the historical active duration of the users in each push channel, and the proposed promotion situation of each push channel in the current push cycle.

[0057] Specifically, the proposed promotion situation of each push channel in the current push cycle refers to whether each push channel has formulated a promotion activity in the current push cycle. For example, a certain push channel will carry out a promotion activity of 10% off for all-channel products on November 11th. The implementation of the promotion activity will bring more users and more traffic to the push channel in a short period of time. At this time, the push weight of the corresponding channel should be increased, and the number of pushes should be increased to achieve a better promotion effect.

[0058] In an embodiment of the present invention, for each channel, a total score is calculated according to the population similarity, the historical active duration of the users, and the proposed promotion situation of each push channel in the current push cycle. Schematically, the calculation formula can be: A = ax + by + cz; A is the total score of a push channel, x is the similarity score between the active population of the push channel and the target user group of the product to be pushed, that is, the score of the population similarity, a is the weight value corresponding to the score of the population similarity, y is the score of the historical active duration corresponding to the push channel, b is the weight value corresponding to the score of the historical active duration, z is the score of the proposed promotion situation of the push channel, z is 1 if there is a promotion activity, and z is 0 if there is no promotion activity, c is the weight value of the score of the proposed promotion situation. It should be noted that the specific values of a, b, and c can be adjusted according to the actual situation. In an optional embodiment, the correlation degree between the population similarity, the historical active duration, and the proposed promotion situation and the open rate of the operation information can be analyzed one by one through historical data, and the corresponding weight values can be determined according to the correlation degree.

[0059] After calculating the total score corresponding to each push channel, calculate the score ratio between the total scores of each push channel, and convert the score ratio into the corresponding weight value to obtain the first push weight corresponding to each push channel in the current push cycle.

[0060] In this embodiment, the historical active time of users in each push channel can reflect the traffic heat of each push channel in the past period of time, and the planned promotion of each push channel can reflect whether each push channel will have a substantial increase in traffic in the future. Generally speaking, if a channel has a promotion activity, it will cause a rapid increase in traffic in a short period of time. The first push weight of each push channel is determined by comprehensively considering the degree of compatibility between the current product to be pushed and each push channel, the traffic heat of each push channel in the past period of time, and the traffic increase of each push channel in the future, thereby improving the rationality of the subsequent push times.

[0061] Step S5: Determine the first push times of the operation information to be pushed in each push channel in the current push cycle according to the first push weight of each push channel, and push the current operation information to be pushed in each push channel according to the first push times.

[0062] Specifically, based on the calculated first push weight and the total number of pushes in the entire push cycle, the number of pushes of the operational information to be pushed in each push channel in the current push cycle is calculated proportionally, that is, the above-mentioned first push number, and then the operational information to be pushed is pushed according to the corresponding first push number.

[0063] In a preferred embodiment, before pushing the operation information to be pushed on each push channel, it also includes:

[0064] For each push channel, the product with the largest sales volume and which is relevant to the product to be pushed in terms of product function in the current push channel is used as the product to be combined, and then the operation information of the product to be combined is generated; wherein the relevance between the product to be combined and the product to be pushed includes: the product functions are the same or they are products in the same package;

[0065] According to the correlation between the products to be combined and the products to be pushed, determine the connection information required for connecting the operation information of the products to be combined with the operation information to be pushed;

[0066] According to the acceptance information, the operation information of the product to be combined with the operation information to be pushed is combined to generate updated operation information to be pushed.

[0067] In the present invention, the product to be combined refers to the product in the current push channel that is relevant to the product to be pushed in terms of product function and has the largest sales volume, and the relevance includes: the products have the same functions or are products in a set; the same product functions refer to similar products, and products in a set refer to products that support each other in function and are used as a set to complete a specific function. For example, if the product to be recommended is a powder puff, the product with the same product function may be a powder puff of other brands, and the product in the same set may be liquid foundation, setting powder, etc.

[0068] In this embodiment, for each push channel, based on the transaction status of each product in the current channel, the product that is relevant to the product to be pushed in terms of product function and has the largest sales volume is found as the product to be combined; then the name, picture and product introduction of the product to be combined can be extracted to generate the corresponding operation information of the product to be combined.

[0069] Indicatively Figure 2 As shown, in area 1, a picture of the product to be combined is set; in area 2, a preset font and font size are used to set the name of the product to be combined; in area 3, a font and font size different from that of the name of the product to be combined is used to set a product introduction of the product to be combined, and then the operation information of the product to be combined is generated.

[0070] Next, according to the correlation between the product to be combined and the product to be pushed, the connection information required for connecting the operation information of the product to be combined with the operation information to be pushed is determined. The above connection information refers to the connection description used to connect the operation information of the product to be combined with the operation information of the product to be pushed, which is equivalent to the role of connecting the previous and the next.

[0071] As an illustration, if the correlation between the product to be combined and the product to be pushed is that the product functions are the same, then the above-mentioned follow-up information is to set the following text according to the set font and font size and display "In order to broaden your choices, we recommend the following similar products to you."

[0072] Indicatively, if the correlation between the product to be combined and the product to be pushed is that they are products within a set, then the above-mentioned acceptance information is to set the following text according to the set font and font size and display "In order to better match the use of the above products, the following products are recommended for you."

[0073] After the corresponding acceptance information is generated, the acceptance information, the operation information of the product to be combined with the operation information to be pushed are combined in the order of the operation information of the product to be combined first, the acceptance information in the middle, and the operation information to be pushed last, to generate the updated operation information to be pushed. Figure 3As shown, area 4 is the display area for the operation information of the products to be combined, area 5 is the display area for the received information, and area 6 is the display area for the operation information to be pushed.

[0074] In this embodiment of the present invention, by combining the operation information of the products to be combined with the operation information to be pushed, it is possible to utilize the situation of the hot-selling products that combine the information pushed through various channels, and use the products that are relevant and hot-selling to the products to be pushed for drainage, so as to increase the opening rate of the finally pushed operation information and further enhance the publicity effect. On the other hand, according to the relationship between the products to be combined and the products to be pushed, the received information is embedded in the updated operation information to be pushed, so as to avoid the rigid and fragmented connection between the operation information of the products to be combined and the operation information to be pushed, and make the updated operation information to be pushed still maintain good integrity.

[0075] In a preferred embodiment, before pushing the operation information to be pushed through each push channel, it further includes:

[0076] For each push channel, according to the age range and gender of the active population in the current push channel, determine the display style of the operation information to be pushed, so as to push the operation information to be pushed in each push channel according to the corresponding display style when pushing.

[0077] Specifically, the above display style includes: the font of the text, the font size of the text, the color of the font, the background color, and the background pattern, etc., and the display style is set in advance according to the preferences of the corresponding age range and gender. For example, for female users in the age range of 16-18 years old, most of them like cute things and are fond of pink. At this time, the corresponding display style can be to set the color of the font to pink and set some cute plush toy patterns as the background pattern, and the rest are set according to the default style. Through such settings, the attention of the active population on each platform can be attracted to the greatest extent, and the opening rate of the operation information can be further increased.

[0078] In a preferred embodiment, when pushing the operation information to be pushed through each push channel, for each push channel, according to the active time period distribution of the active population in the current push channel and the number of push times of the current push channel, determine the number of push times for each time period, and push the operation information to be pushed in the corresponding push channel according to the number of push times for each time period.

[0079] Specifically, in the present invention, according to the active time period distribution of the active population, the number of active people in each time period can be calculated, and then the proportion of the number of active people in each time period and the total number of push times of the current channel on the same day are used to determine the number of push times for each time period, and then push.

[0080] In this embodiment, it is mainly considered that different types of active populations are active at different times on the channels. For example, young people usually go to bed late, and the period from 11 pm to 1 am is their most active time. Therefore, the number of pushes can be appropriately increased from 11 pm to 1 am, thereby further increasing the opening rate of the operation information.

[0081] In a preferred embodiment, the above operation information pushing method further includes: if the similarity is greater than or equal to a preset similarity threshold, then according to the opening rate of the operation information corresponding to the products already pushed in each push channel in the previous push cycle, and the proposed promotion situation of each push channel in the current push cycle, determine the second push weight of each push channel in the current push cycle;

[0082] According to the second push weight of each push channel, determine the second push times of the operation information to be pushed in each push channel in the current push cycle, and push the operation information to be pushed in each push channel according to the second push times; wherein, the second push weight is proportional to the second push times.

[0083] In this embodiment, if the similarity is greater than or equal to the preset similarity threshold, it means that the product to be pushed at this time belongs to the same category as the product already pushed in the previous push cycle, and the target populations between the same category of products are not very different. If the product to be pushed is pushed according to the push strategy of the previous push cycle, its corresponding opening rate should be similar to the opening rate of the operation information of the products already pushed in each push channel in the previous push cycle. Therefore, on the basis of the opening rate of the operation information of the products already pushed in each push channel in the previous push cycle, combined with the proposed promotion situation of each push channel in the current push cycle, the push times of each push channel in the current push cycle can be adjusted.

[0084] On the basis of the above method item embodiment, the present invention correspondingly provides an apparatus item embodiment;

[0085] As Figure 4 shown, an embodiment of the present invention provides an operation information pushing apparatus, including: a product similarity calculation module, a population selection module, a population similarity calculation module, a first push weight determination module, and a first push module;

[0086] The product similarity calculation module is used to compare the similarity between the product to be pushed corresponding to the operation information to be pushed in the current push cycle and the product already pushed in the previous push cycle when the current push cycle arrives;

[0087] The population selection module is used to extract the historical purchase information of similar products of the product to be pushed on all push channels when the similarity is less than a preset similarity threshold, and determine the target user population of the product to be pushed according to the historical purchase information; wherein, the purchase information includes the age of each purchaser and the gender of each purchaser; determine the active population of each push channel according to the historical active duration, age and gender of each user in each push channel.

[0088] The population similarity calculation module is used to respectively construct a first projection space of the target user population and a second projection space of the active population of each push channel with the number of people as the X-axis, age as the Y-axis, and gender as the Z-axis; compare the first projection space with each second projection space respectively, and calculate the similarity between the first projection space and each second projection space according to the coincidence rate of the projection points in the projection space, so as to obtain the population similarity between the target user population and the active population of each channel.

[0089] The first push weight determination module is used to determine the first push weight corresponding to each push channel in the current push cycle according to each population similarity, the historical active duration of the users in each push channel, and the proposed promotion situation of each push channel in the current push cycle.

[0090] The first push module is used to determine the first push times of the operation information to be pushed in each push channel in the current push cycle according to the first push weight of each push channel, and push the current operation information to be pushed in each push channel according to the first push times; wherein, the first push weight is proportional to the first push times.

[0091] In a preferred embodiment, it further includes a second push weight determination module and a second push module.

[0092] The second push weight determination module is used to determine the second push weight of each push channel in the current push cycle according to the push information opening rate of the operation information corresponding to the product already pushed in each push channel in the previous push cycle and the proposed promotion situation of each push channel in the current push cycle when the similarity is greater than or equal to the preset similarity threshold.

[0093] The second push module is used to determine the second push times of the operation information to be pushed in each push channel in the current push cycle according to the second push weight of each push channel, and push the operation information to be pushed in each push channel according to the second push times; wherein, the second push weight is proportional to the second push times.

[0094] It should be noted that the device embodiments described above correspond to the method embodiments of the present invention and can implement the operation information push method described in any of the above method embodiments of the present invention. In addition, the devices described above in the present invention are merely illustrative. The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed to multiple network units. Some or all of the modules can be selected according to actual needs to achieve the purpose of the solution of this embodiment. In addition, in the accompanying drawings of the device embodiments provided by the present invention, the connection relationships between the modules indicate that there is a communication connection between them, which can be specifically implemented as one or more communication buses or signal lines. Those of ordinary skill in the art can understand and implement it without creative work.

[0095] Based on the above method embodiments, the present invention correspondingly provides a terminal device embodiment.

[0096] An embodiment of the present invention provides a terminal device including a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor. When the processor executes the computer program, it implements the operation information push method described in any embodiment of the present invention.

[0097] Among them, the terminal device may be a computing device such as a desktop computer, a notebook, a palm computer, and a cloud server.

[0098] The so-called processor may be a central processing unit (CPU), or may also be other general-purpose processors, digital signal processors (DSPs), application specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc. The processor is the control center of the terminal device and connects various parts of the entire terminal device through various interfaces and lines.

[0099] The memory can be used to store the computer program. By running or executing the computer program stored in the memory and invoking the data stored in the memory, the processor realizes various functions of the terminal device. In addition, the memory may include high-speed random access memory and may also include non-volatile memory, such as a hard disk, memory, plug-in hard disk, smart media card (SMC), secure digital (SD) card, flash card, at least one magnetic disk storage device, flash memory device, or other volatile solid-state storage devices.

[0100] The computer program includes computer program code, which may be in the form of source code, object code, executable file, or some intermediate form, etc.

[0101] Based on the above method item embodiments, the present invention correspondingly provides storage medium item embodiments.

[0102] An embodiment of the present invention provides a storage medium. The storage medium includes a stored computer program, wherein when the computer program runs, it controls the device where the storage medium is located to execute the operation information push method described in any one of the present invention.

[0103] The storage medium is a computer-readable medium, which may include: any entity or device capable of carrying the computer program code, recording medium, USB flash drive, mobile hard disk, magnetic disk, optical disc, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signal, telecommunication signal, and software distribution medium, etc.

[0104] The above is the preferred embodiment of the present invention. It should be noted that for those of ordinary skill in the art, without departing from the principle of the present invention, several improvements and refinements can be made, and these improvements and refinements are also regarded as the protection scope of the present invention.

Claims

1. An operation information push method, characterized in that, include: When the current push cycle arrives, the similarity between the product to be pushed corresponding to the current operation information to be pushed and the product that has been pushed corresponding to the previous push cycle is compared; When the similarity is less than a preset similarity threshold, extract the historical purchase information of similar products of the product to be pushed in all push channels, and determine the target user group of the product to be pushed based on the historical purchase information; wherein the purchase information includes: the age of each purchaser and the gender of each purchaser; determine the active population of each push channel based on the historical active time of each user in each push channel, the age of each user and the gender of each user; With the number of people as the X-axis, age as the Y-axis, and gender as the Z-axis, the first projection space of the target user population and the second projection space of the active population of each push channel are constructed respectively; the first projection space is compared with each second projection space respectively, and the similarity between the first projection space and each second projection space is calculated according to the overlap rate of the projection points in the projection space, so as to obtain the population similarity between the target user population and the active population of each push channel; Determine the first push weight corresponding to each push channel in the current push cycle according to the similarity of each group, the historical active time of users in each push channel, and the proposed promotion of each push channel in the current push cycle; According to the first push weight of each push channel, the first push number of the operation information to be pushed in each push channel in the current push cycle is determined, and according to the first push number, the current operation information to be pushed is pushed in each push channel; wherein, the first push weight is proportional to the first push number.

2. The operation information push method according to claim 1, wherein Also includes: If the similarity between the product to be pushed corresponding to the current operation information to be pushed and the pushed product corresponding to the previous push cycle is greater than or equal to the preset similarity threshold, the second push weight of each push channel in the current push cycle is determined according to the push information opening rate of the operation information corresponding to the pushed product in each push channel in the previous push cycle and the proposed promotion situation of each push channel in the current push cycle; According to the second push weight of each push channel, the second push number of the operation information to be pushed in each push channel in the current push cycle is determined, and according to the second push number, the operation information to be pushed is pushed in each push channel; wherein the second push weight is proportional to the second push number.

3. The operation information pushing method according to claim 2, characterized in that Before pushing the operational information to be pushed on each push channel, it also includes: For each push channel, the product with the largest sales volume and which is relevant to the product to be pushed in terms of product function in the current push channel is used as the product to be combined, and then the operation information of the product to be combined is generated; wherein the relevance between the product to be combined and the product to be pushed includes: the product functions are the same or they are products in the same package; According to the correlation between the products to be combined and the products to be pushed, determine the connection information required for connecting the operation information of the products to be combined with the operation information to be pushed; According to the received information, combine the operation information of the product to be associated with the operation information to be pushed, and generate the updated operation information to be pushed.

4. The operation information pushing method according to claim 2, wherein Before pushing the operation information to be pushed on each push channel, it further includes: For each push channel, determine the display style of the operation information to be pushed according to the age range and gender of the active population in the current push channel, so that when pushing the operation information to be pushed on each push channel, it is pushed according to the corresponding display style.

5. The operation information pushing method according to claim 2, wherein When pushing the operation information to be pushed on each push channel, for each push channel, determine the push times for each time period according to the active time period distribution of the active population in the current push channel and the push times of the current push channel, and push the operation information to be pushed on the corresponding push channel according to the push times for each time period.

6. The operation information push method according to claim 2, wherein After pushing the current operation information to be pushed on each push channel, it further includes: Regarding the open rate of the pushed operation information in each push channel, when detecting that the growth rate of the open rate of the pushed information in any push channel exceeds the threshold, increase the push times of the operation information to be pushed corresponding to the push channel.

7. An operation information push device, characterized in that It includes: A product similarity calculation module, a population selection module, a population similarity calculation module, a first push weight determination module, and a first push module; The product similarity calculation module is used to compare the similarity between the product to be pushed corresponding to the current operation information to be pushed and the product that has been pushed corresponding to the previous push cycle when the current push cycle arrives; The population selection module is used to extract the historical purchase information of similar products of the product to be pushed in all push channels when the similarity is less than the preset similarity threshold, and determine the target user group of the product to be pushed according to the historical purchase information; wherein, the purchase information includes: the age of each purchaser and the gender of each purchaser; determine the active population of each push channel according to the historical active duration, age, and gender of each user in each push channel; The population similarity calculation module is used to respectively construct a first projection space of the target user group and a second projection space of the active population of each push channel with the number of people as the X-axis, age as the Y-axis, and gender as the Z-axis; compare the first projection space with each second projection space respectively, and calculate the similarity between the first projection space and each second projection space according to the coincidence rate of the projection points in the projection space, and obtain the population similarity between the target user group and the active population of each channel; The first push weight determination module is used to determine the first push weight corresponding to each push channel in the current push cycle according to each population similarity, the historical active duration of the users in each push channel, and the proposed promotion situation of each push channel in the current push cycle; The first push module is configured to determine the first push times of the operation information to be pushed in each push channel in the current push cycle according to the first push weights of the push channels, and push the current operation information to be pushed in each push channel according to the first push times; wherein, the first push weight is directly proportional to the first push times.

8. The operation information push device according to claim 7, wherein It further includes a second push weight determination module and a second push module; The second push weight determination module is configured to, if the similarity between the product to be pushed corresponding to the current operation information to be pushed and the product that has been pushed corresponding to the previous push cycle is greater than or equal to a preset similarity threshold, determine the second push weights of the push channels in the current push cycle according to the push information opening rates of the operation information corresponding to the products that have been pushed in each push channel in the previous push cycle and the proposed promotion situation of each push channel in the current push cycle; The second push module is configured to determine the second push times of the operation information to be pushed in each push channel in the current push cycle according to the second push weights of the push channels, and push the operation information to be pushed in each push channel according to the second push times; wherein, the second push weight is directly proportional to the second push times.

9. A terminal device, characterized in that, It includes a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor. When the processor executes the computer program, it implements the operation information push method according to any one of claims 1 to 6.

10. A storage medium, characterized in that, The storage medium includes a stored computer program. When the computer program runs, it controls the device where the storage medium is located to execute the operation information push method according to any one of claims 1 to 6.

Images