A data analysis method, device, storage medium and electronic equipment

Abstract

The data analysis method and device, the storage medium and the electronic equipment provided in the specification can obtain historical browsing data corresponding to target recommendation information, input the historical browsing data into a pre-trained prediction model, so that the prediction model predicts browsing data corresponding to the target recommendation information at a specified time in the future as standard browsing data, obtain actual browsing data of the target recommendation information at the specified time, and determine the deviation between the actual browsing data and the standard browsing data. When the deviation is greater than a preset deviation, it is determined that the actual browsing data is abnormal data, and data analysis is performed on the abnormal data to obtain an analysis result.

Description

TECHNICAL FIELD

[0001] The present specification relates to the technical field of computer, and particularly relates to a data analysis method and device, a storage medium and an electronic device. BACKGROUND

[0002] At present, in order to meet the personalized needs of users, enterprises can recommend information meeting the needs of users to users, so as to improve the experience of users. For example, the purchase behavior of users can be analyzed, so as to recommend the goods links interested by users to users. For another example, the corresponding advertisements can be pushed to users according to the historical browsing record information authorized by users. After the corresponding information is recommended to users, the browsing data of users on the information can be collected, and the collected browsing data can be analyzed, so as to recommend the contents more interested by users to users, so as to further improve the experience of users.

[0003] However, in the prior art, the browsing data is often analyzed by using the artificial analysis mode, so that the execution efficiency is low. SUMMARY

[0004] The present specification provides a data analysis method and device, a storage medium and an electronic device, to partially solve the above problems existing in the prior art.

[0005] The present specification adopts the following technical solutions:

[0006] The present specification provides a data analysis method, comprising:

[0007] Obtaining historical browsing data corresponding to target recommendation information, the historical browsing data being used to reflect the browsing situation of the target recommendation information in history;

[0008] Inputting the historical browsing data into a pre-trained prediction model, so that the prediction model predicts the browsing data corresponding to the target recommendation information at a specified time in the future as standard browsing data;

[0009] Obtaining the actual browsing data of the target recommendation information at the specified time, and determining the deviation between the actual browsing data and the standard browsing data;

[0010] When the deviation is greater than a preset deviation, determining that the actual browsing data is abnormal data, and performing data analysis on the abnormal data to obtain an analysis result.

[0011] Optionally, the step of obtaining the historical browsing data corresponding to the target recommendation information specifically comprises:

[0012] Obtaining initial browsing data of the target recommendation information in a historical period;

[0013] The initial browsing data is preprocessed to obtain the historical browsing data corresponding to the target recommendation information as the preprocessed data, wherein the preprocessing includes at least one of de-duplication processing, outlier processing, and standardization processing.

[0014] Optionally, the method further comprises:

[0015] When the deviation is not greater than the preset deviation, determining a browsing data reasonable interval according to the historical browsing data, and judging whether the actual browsing data is located in the browsing data reasonable interval;

[0016] If not, the actual browsing data is taken as abnormal data, and data analysis is performed on the abnormal data to obtain an analysis result.

[0017] Optionally, the step of performing data analysis on the abnormal data to obtain an analysis result specifically comprises:

[0018] Obtaining recommendation strategy information corresponding to the abnormal data under each business dimension;

[0019] For the recommendation strategy information corresponding to each business dimension, the recommendation strategy information corresponding to the business dimension is matched with the historical recommendation strategy information under the business dimension, and in a case where it is determined that the recommendation strategy information corresponding to the business dimension does not match the historical recommendation strategy information under the business dimension, the recommendation strategy information corresponding to the business dimension is taken as abnormal recommendation strategy information;

[0020] The abnormal recommendation strategy information is taken as abnormal reason information for the abnormal data, and an analysis result is obtained according to the abnormal reason information.

[0021] Optionally, the method further comprises:

[0022] The abnormal recommendation strategy information and a prompt sentence are input into a preset large model to generate adjustment strategy information for avoiding the abnormal data through the large model;

[0023] The abnormal recommendation strategy information is adjusted according to the adjustment strategy information, so that business is executed according to the adjusted strategy information.

[0024] Optionally, the step of pre-training the prediction model specifically comprises:

[0025] Obtaining sample browsing information and label browsing data corresponding to the sample browsing information;

[0026] The sample browsing information is input into a prediction model to be trained, so that the prediction model to be trained determines the prediction browsing data corresponding to the sample browsing information;

[0027] According to the deviation between the predicted browsing data and the label browsing data, a loss value is determined, and the trained prediction model is trained according to the loss value, wherein the deviation and the loss value are in a positive correlation.

[0028] Optionally, the step of performing data analysis on the abnormal data to obtain an analysis result specifically comprises:

[0029] On the premise that the browsing situation reflected by the abnormal data is regarded as a normal browsing situation, a group distribution of a user group that can produce the browsing situation reflected by the abnormal data after receiving the target recommendation information is predicted as a reference group distribution;

[0030] A group distribution of a user group that produces the browsing situation reflected by the actual browsing data after receiving the target recommendation information is determined as an actual group distribution;

[0031] According to the actual group distribution and the reference group distribution, abnormal recommendation strategy information is determined from each recommendation strategy information corresponding to each business dimension of the abnormal data, so that the analysis result is obtained according to the abnormal recommendation strategy information.

[0032] The specification provides a data analysis device, comprising:

[0033] The first acquisition module is configured to acquire historical browsing data corresponding to the target recommendation information, wherein the historical browsing data is used to reflect a browsing situation of the target recommendation information in history.

[0034] The prediction module is configured to input the historical browsing data into a pre-trained prediction model, so that the prediction model predicts browsing data corresponding to the target recommendation information at a specified time in the future as standard browsing data.

[0035] The second acquisition module is configured to acquire actual browsing data of the target recommendation information at the specified time, and determine a deviation between the actual browsing data and the standard browsing data.

[0036] The analysis module is configured to determine the actual browsing data as abnormal data when the deviation is greater than a preset deviation, and perform data analysis on the abnormal data to obtain an analysis result.

[0037] The specification provides a computer readable storage medium, wherein the storage medium stores a computer program, and the computer program is executed by a processor to implement the above data analysis method.

[0038] The specification provides an electronic device, comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, wherein the processor implements the above-mentioned data analysis method when executing the program.

[0039] The above-mentioned at least one technical solution adopted by the specification can achieve the following beneficial effects:

[0040] The data analysis method provided by the specification can obtain historical browsing data corresponding to target recommendation information, input the historical browsing data into a pre-trained prediction model, so that the prediction model predicts browsing data corresponding to the target recommendation information at a specified time in the future as standard browsing data, obtains actual browsing data of the target recommendation information at the specified time, and determines the deviation between the actual browsing data and the standard browsing data. When the deviation is greater than a preset deviation, the actual browsing data is determined as abnormal data, and data analysis is performed on the abnormal data to obtain an analysis result.

[0041] It can be seen from the above that the above-mentioned method can judge and analyze whether the actual browsing data is abnormal data according to the deviation between the standard browsing data predicted by the prediction model and the actual browsing data, i.e. without using manual analysis to analyze the browsing data as in the prior art, thereby greatly improving the execution efficiency. BRIEF DESCRIPTION OF DRAWINGS

[0042] The drawings described herein are used to provide further understanding of the specification, and form a part of the specification. The illustrative embodiments of the specification and their descriptions are used to explain the specification, and do not constitute an improper limitation on the specification. In the drawings:

[0043] Figure 1 A flowchart of a data analysis method provided in the specification;

[0044] Figure 2 A flowchart of a data analysis method provided in the specification;

[0045] Figure 3 A flowchart of a data analysis method provided in the specification;

[0046] Figure 4 A schematic diagram of a data analysis device provided in the specification;

[0047] Figure 5 A schematic diagram of a data analysis device provided in the specification; Figure 1 A schematic structural diagram of an electronic device. DETAILED DESCRIPTION

[0048] In order to make the purpose, technical solutions and advantages of the present specification clearer, the technical solutions of the present specification will be described clearly and completely in the following combined with specific embodiments of the present specification and corresponding drawings. Obviously, the described embodiments are only a part of the embodiments of the present specification, rather than all the embodiments. Based on the embodiments in the present specification, all other embodiments obtained by those skilled in the art without creative labor fall within the scope of protection of the present specification.

[0049] At present, in order to meet the personalized needs of users, enterprises can recommend information meeting the needs of users to users, so as to improve the experience of users. For example, the purchase behavior of users can be analyzed, so as to recommend the interested goods link of users to users. For another example, the corresponding advertisement can be pushed to users according to the authorized historical browsing record information of users. After the corresponding information is recommended to users, the browsing data of users on the information can be collected, and the collected browsing data can be analyzed, so as to recommend the more interested content of users to users, so as to further improve the experience of users. However, in the prior art, the browsing data is often analyzed by using artificial analysis, so as to cause low execution efficiency.

[0050] Therefore, the present specification provides a data analysis method, by which the problems in the prior art can be effectively solved.

[0051] The technical solutions provided by the embodiments of the present specification will be described in detail below combined with the drawings.

[0052] Figure 1 For the flowchart of the data analysis method provided in the present specification, the following steps are included:

[0053] S101: Obtain historical browsing data corresponding to target recommendation information, wherein the historical browsing data is used to reflect the browsing situation of the target recommendation information in history.

[0054] The execution subject of the data analysis method involved in the present specification can be a terminal device such as a desktop computer, a notebook computer, etc., can be a client installed in a terminal device, or can be a server. In the following, only the server is taken as an example of the execution subject, and the data analysis method in the embodiments of the present specification is described.

[0055] In the present specification, the server can obtain historical browsing data corresponding to target recommendation information, and then determine abnormal data therefrom, and analyze the abnormal data to obtain a corresponding analysis result. The target recommendation information can be a link information of a product that a user is interested in, or the target recommendation information can also be corresponding advertising information pushed to the user according to the historical browsing record information authorized by the user. Correspondingly, the browsing data can be a click rate of the user corresponding to the target recommendation information, a conversion rate of the user corresponding to the target recommendation information, and other data that can reflect the browsing situation of the target recommendation information.

[0056] Firstly, the server can obtain historical browsing data corresponding to target recommendation information, so as to subsequently analyze the actual browsing data according to the obtained historical browsing data to obtain an analysis result. The historical browsing data can reflect the browsing situation of the target recommendation information in history.

[0057] Of course, the data can also be preprocessed during the process of obtaining the historical browsing data corresponding to the target recommendation information. Specifically, the server can first obtain initial browsing data of the target recommendation information in a historical period, and then can preprocess the initial browsing data, and take the preprocessed data as the obtained historical browsing data corresponding to the target recommendation information. For example, the initial browsing data can be de-duplicated. For another example, the initial browsing data can be processed for abnormal values. For another example, the initial browsing data can be standardized (such as converting the initial browsing data into data in the same format).

[0058] S102: inputting the historical browsing data into a pre-trained prediction model, so that the prediction model predicts the browsing data corresponding to the target recommendation information at a specified time in the future as standard browsing data.

[0059] In the present specification, the browsing data corresponding to the target recommendation information at a specified time in the future can be predicted by a pre-trained prediction model, so as to judge whether the actual browsing data at the specified time is abnormal data according to the predicted data.

[0060] Specifically, in the process of training the to-be-trained prediction model, sample browsing information and label browsing data corresponding to the sample browsing information can be acquired first. The sample browsing information can be understood as sample browsing data from a sample data set. The server can input the sample browsing information into the to-be-trained prediction model, and the model can determine predicted browsing data corresponding to the sample browsing information. Then, a loss value can be determined according to a deviation between the predicted browsing data and the label browsing data, wherein the deviation and the loss value are positively correlated. The server can train the prediction model with the goal of gradually reducing the loss value. Of course, in actual application, different training methods can be used to train the prediction model according to actual needs, such as reinforcement learning, semi-supervised learning, etc., which will not be described herein.

[0061] After the prediction model is trained, the server can input the historical browsing data corresponding to the target recommendation information into the prediction model, and then the prediction model can predict the browsing data corresponding to the target recommendation information at a specified future time as standard browsing data. For example, the prediction model can predict the browsing data corresponding to the target recommendation information in the future one week, or predict the browsing data corresponding to the target recommendation information in the future certain day, etc.

[0062] S103: Acquire actual browsing data of the target recommendation information at the specified time, and determine a deviation between the actual browsing data and the standard browsing data.

[0063] S104: When the deviation is greater than a preset deviation, determine that the actual browsing data is abnormal data, and perform data analysis on the abnormal data to obtain an analysis result.

[0064] After predicting the browsing data at the specified future time, the server can acquire actual browsing data of the target recommendation information at the specified time, and determine a deviation between the actual browsing data and the standard browsing data. When the determined deviation is less than a preset deviation, the actual browsing data can be regarded as abnormal data.

[0065] Of course, in addition to judging the abnormal data according to the standard browsing data, the actual browsing data can also be judged according to a reasonable interval of browsing data. Specifically, when the deviation between the actual browsing data and the standard browsing data is not greater than a preset deviation, the server can further judge whether the actual browsing data is located in the reasonable interval of browsing data. If not, the actual browsing data can be regarded as abnormal data. Correspondingly, if the actual browsing data is located in the reasonable interval of browsing data, the actual browsing data can be regarded as normal data.

[0066] The reasonable interval of the browsing data can be set by the administrator in advance. Of course, the reasonable interval of the browsing data can also be determined by the server according to the historical browsing data obtained. Specifically, since the historical browsing data obtained in actual application is usually multiple, the minimum historical browsing data in each historical browsing data can be taken as the left end point of the reasonable interval of the browsing data, and the maximum historical browsing data in each historical browsing data can be taken as the right end point of the reasonable interval of the browsing data. For example, the reasonable interval of the browsing data can be conversion rate 45%---conversion rate 65%.

[0067] In addition, in the present specification, it can also be directly judged whether the actual browsing data is abnormal data according to the reasonable interval of the browsing data. Specifically, the server can directly judge whether the actual browsing data of the target recommendation information is located in the reasonable interval of the browsing data, and if not, the actual browsing data can be determined as abnormal data. Of course, when the actual browsing data of the target recommendation information is located in the reasonable interval of the browsing data, further, the deviation between the actual browsing data and the corresponding standard browsing data predicted by the prediction model can be determined, if the deviation is greater than the preset deviation, the actual browsing data is determined as abnormal data, on the contrary, if the deviation is not greater than the preset deviation, the actual browsing data is determined as normal data.

[0068] When it is determined that the actual browsing data is abnormal data, the abnormal data can be analyzed to obtain an analysis result. For example, the click rate of the user corresponding to the target recommendation information in a specified time period can be displayed in the form of a line chart, and the abnormal click rate (such as an abnormally high click rate) in the line chart can be highlighted.

[0069] In addition, the cause of the abnormal data can also be analyzed. Specifically, the server can obtain the recommendation strategy information corresponding to the abnormal data under each business dimension, and the recommendation strategy information corresponding to each business dimension can include the specific time of the recommendation information, the cost (such as the cost of content design, the cost of information delivery, etc.) spent by the recommendation information, the recommended user group, etc.

[0070] Further, for the recommendation strategy information corresponding to each business dimension, the recommendation strategy information corresponding to the business dimension can be matched with the historical recommendation strategy information under the business dimension, and in the case where the recommendation strategy information corresponding to the business dimension is determined to be unmatched with the historical recommendation strategy information under the business dimension, the recommendation strategy information corresponding to the business dimension is determined as abnormal recommendation strategy information. Further, the abnormal recommendation strategy information can be taken as the abnormal cause information of the abnormal data, and the analysis result can be obtained according to the abnormal cause information.

[0071] For example, when the user click rate in the browsing data corresponding to the target recommendation information on a certain day is abnormally low, the server can match the specific time of the recommendation information on the day with the average time of the recommendation information in the past month. If the specific time of the recommendation information on the day is significantly later than the average time, it can be determined that the abnormal recommendation strategy information is the time of the recommendation information on the day, i.e., the abnormally low click rate is due to the late time of the recommendation.

[0072] For example, when the user click rate in the browsing data corresponding to the target recommendation information on a certain day is abnormally high, the server can compare the cost of the target recommendation information on the day with the average cost of the target recommendation information in the past month. If the cost of the target recommendation information on the day is significantly higher than the average cost, it can be determined that the abnormal recommendation strategy information is the cost of the target recommendation information on the day. Further, the server can also compare the cost of the information in the cost of the target recommendation information on the day with the average cost of the information in the cost of the target recommendation information in the past month. If the cost of the information is significantly higher than the average cost of the information, it can be further determined that the abnormal recommendation strategy information is the cost of the information in the cost of the target recommendation information on the day, i.e., the abnormally high click rate on the day is due to the abnormally high cost of the information.

[0073] In addition, the server can also generate adjustment strategy information to avoid abnormal data. Specifically, the abnormal recommendation strategy information and the corresponding prompt sentence can be input into a preset large model (such as GPT-4), and then the large model can generate adjustment strategy information to avoid abnormal data. For example, the time of the abnormal recommendation information and the prompt sentence "please generate the corresponding adjustment strategy according to the current abnormal recommendation strategy information" can be input into the large model, and then the large model can generate the adjustment strategy information "please appropriately advance the time of the corresponding information to avoid the abnormal data again". Of course, in addition to generating the corresponding adjustment strategy information through the above-mentioned large model, the abnormal recommendation strategy information can also be analyzed through the pre-set program code to generate the corresponding adjustment strategy information.

[0074] Further, the server can adjust the abnormal recommendation strategy information according to the adjustment strategy information to perform the business according to the adjusted strategy information. For example, when the adjustment strategy information is "please appropriately advance the time of the corresponding information to avoid the abnormal data again", the abnormal recommendation time can be advanced according to the adjustment strategy information, so as to avoid the abnormally low click rate of the user, and the target recommendation information recommended according to the adjusted recommendation strategy can also be more in line with the user's own needs.

[0075] Of course, in actual application process, the abnormal data may also be due to the abnormal group distribution of the recommended user group, and therefore, in the data analysis process of the abnormal data, data analysis can also be performed on the user group corresponding to the target recommendation information.

[0076] Specifically, when it is determined that the actual browsing data is abnormal data, the browsing situation reflected by the abnormal data can be regarded as a normal browsing situation, so that under the premise that it is a normal browsing situation, the group distribution of the user group that can produce the browsing situation reflected by the abnormal data after receiving the target recommendation information is predicted as a reference group distribution. For example, the actual browsing data can be input into a preset analysis model, so that the analysis model predicts the reference group distribution that can produce the browsing situation reflected by the actual browsing data. For another example, the reference group distribution that can produce the browsing situation reflected by the actual browsing data can be analyzed according to the browsing situation reflected by the abnormal data through a preset program code.

[0077] Then, the group distribution of the user group that produces the browsing situation reflected by the actual browsing data after receiving the target recommendation information can be determined as an actual group distribution. The server can determine the abnormal recommendation strategy information in the corresponding recommendation strategy information of each business dimension of the abnormal data according to the actual group distribution and the reference group distribution, so that the analysis result can be obtained according to the abnormal recommendation strategy information.

[0078] For example, when the abnormal click rate of 10% occurs, the reference group distribution corresponding to the normal click rate of 10% can be predicted as follows: the proportion of males aged 18-28 is 40%, the proportion of females aged 18-28 is 35%, the proportion of males aged 29-40 is 15%, and the proportion of females aged 29-40 is 10%. The actual group distribution corresponding to the abnormal click rate of 10% is: the proportion of males aged 18-28 is 30%, the proportion of females aged 18-28 is 45%, the proportion of males aged 29-40 is 10%, and the proportion of females aged 29-40 is 15%. Then, the actual group distribution and the reference group distribution are compared, so that it can be determined that the proportions of males and females in the two age groups in the actual group distribution are abnormal, and therefore, the corresponding user group distribution can be adjusted, and at the same time, the content of the target recommendation information can be adjusted and optimized, so as to provide more information that meets the needs of the corresponding user group.

[0079] Of course, in the actual application process, the target recommendation information can be placed in different delivery platforms according to actual needs, and the corresponding browsing data can be obtained from different delivery platforms for data analysis, and the analysis results can also be returned to the corresponding management personnel in the form of word documents, pdf documents, etc. for viewing.

[0080] In order to further illustrate the above data analysis method, the overall flow of data analysis will be illustrated in the form of a diagram as follows Figure 2 、 Figure 3 .

[0081] Figure 2 A schematic diagram of a data analysis process is provided for the present specification.

[0082] As can be seen from Figure 2 , in the process of data analysis, the historical browsing data corresponding to the target recommendation information can be input into the prediction model to make the prediction model predict the corresponding standard browsing data. Then, the deviation between the actual browsing data and the standard browsing data can be determined, and it is judged whether the deviation is less than the preset deviation. When the deviation is not less than the preset deviation, the actual browsing data is regarded as abnormal data, and the abnormal data is analyzed to obtain the analysis result. On the contrary, when the deviation is less than the preset deviation, further judgment can be made on whether the actual browsing data is abnormal. When the actual browsing data is within the reasonable interval of the browsing data, the actual browsing data is regarded as normal data; when the actual browsing data is not within the reasonable interval of the browsing data, the actual browsing data is regarded as abnormal data, and the abnormal data is analyzed to obtain the analysis result.

[0083] Figure 3 A schematic diagram of a data analysis process is provided for the present specification.

[0084] As can be seen from Figure 3It can be seen that, for the actual browsing data, only one abnormality judgment can determine whether the actual browsing data is abnormal data, thereby performing subsequent data analysis. Specifically, when the actual browsing data is located in the reasonable interval of the browsing data, the actual browsing data can be regarded as normal data; when the actual browsing data is not located in the reasonable interval of the browsing data, the actual browsing data is regarded as abnormal data, and data analysis is performed on the abnormal data to obtain an analysis result. Alternatively, the corresponding standard browsing data can be predicted from the historical browsing data by the prediction model, when the deviation between the actual browsing data and the standard browsing data is less than the preset deviation, the actual browsing data can be regarded as normal data; when the deviation between the actual browsing data and the standard browsing data is not less than the preset deviation, the actual browsing data is regarded as abnormal data, and data analysis is performed on the abnormal data to obtain an analysis result.

[0085] It can be seen that the above method can judge and analyze whether the actual browsing data is abnormal data according to the deviation between the standard browsing data predicted by the prediction model and the actual browsing data, that is, without using manual analysis to analyze the browsing data as in the prior art, thereby greatly improving the execution efficiency.

[0086] In addition, in the above method, the abnormal reason information of the abnormal data can be analyzed, so that the abnormal recommendation strategy information can be adjusted according to the analyzed abnormal reason information, and then the information more suitable for the user's own needs can be recommended to the user according to the adjusted recommendation strategy, thereby improving the execution effect.

[0087] The above is the method of one or more embodiments of the present specification. Based on the same idea, the present specification also provides a corresponding data analysis device, as shown in Figure 4 .

[0088] Figure 4 A schematic diagram of a data analysis device provided by the present specification comprises:

[0089] The first acquisition module 401 is configured to acquire historical browsing data corresponding to target recommendation information, wherein the historical browsing data is used to reflect the browsing situation of the target recommendation information in history;

[0090] The prediction module 402 is configured to input the historical browsing data into a pre-trained prediction model, so that the prediction model predicts the browsing data corresponding to the target recommendation information at a specified time in the future as standard browsing data;

[0091] The second acquisition module 403 is configured to acquire actual browsing data of the target recommendation information at the specified time, and determine the deviation between the actual browsing data and the standard browsing data;

[0092] The analysis module 404 is configured to determine that the actual browsing data is abnormal data when the deviation is greater than the preset deviation, and perform data analysis on the abnormal data to obtain an analysis result.

[0093] Optionally, the first obtaining module 401 is specifically configured to: obtain initial browsing data of target recommendation information in a historical period; and pre-process the initial browsing data to take the pre-processed data as historical browsing data corresponding to the target recommendation information.

[0094] Optionally, the apparatus further includes a judgment module 405.

[0095] The judgment module 405 is specifically configured to: when the deviation is not greater than the preset deviation, determine a browsing data reasonable interval according to the historical browsing data, and judge whether the actual browsing data is located in the browsing data reasonable interval; if not, take the actual browsing data as abnormal data, and perform data analysis on the abnormal data to obtain an analysis result.

[0096] Optionally, the analysis module 404 is specifically configured to: obtain recommendation strategy information corresponding to the abnormal data under each business dimension; for the recommendation strategy information corresponding to each business dimension, match the recommendation strategy information corresponding to the business dimension with historical recommendation strategy information under the business dimension, and in a case where it is determined that the recommendation strategy information corresponding to the business dimension does not match the historical recommendation strategy information under the business dimension, take the recommendation strategy information corresponding to the business dimension as abnormal recommendation strategy information; take the abnormal recommendation strategy information as abnormal reason information for the abnormal data, and obtain an analysis result according to the abnormal reason information.

[0097] Optionally, the method further includes an adjustment module 406.

[0098] The adjustment module 406 is specifically configured to: input the abnormal recommendation strategy information and a prompt statement into a preset large model to generate adjustment strategy information for avoiding the abnormal data through the large model; and adjust the abnormal recommendation strategy information according to the adjustment strategy information to perform business according to the adjusted strategy information.

[0099] Optionally, the prediction module 402 is specifically configured to: acquire sample browsing information and label browsing data corresponding to the sample browsing information; input the sample browsing information into a prediction model to be trained, so that the prediction model to be trained determines predicted browsing data corresponding to the sample browsing information; determine a loss value according to a deviation between the predicted browsing data and the label browsing data, and train the prediction model to be trained according to the loss value, wherein the deviation and the loss value are in a positive correlation.

[0100] Optionally, the analysis module 404 is specifically configured to: under the premise that the browsing situation reflected by the abnormal data is regarded as a normal browsing situation, predict a group distribution of a user group that can produce the browsing situation reflected by the abnormal data after receiving the target recommendation information, as a reference group distribution; determine a group distribution of a user group that produces the browsing situation reflected by the actual browsing data after receiving the target recommendation information, as an actual group distribution; determine abnormal recommendation strategy information in each recommendation strategy information corresponding to each business dimension of the abnormal data according to the actual group distribution and the reference group distribution, so as to obtain an analysis result according to the abnormal recommendation strategy information.

[0101] The specification also provides a computer-readable storage medium storing a computer program, and the computer program can be used to execute the data analysis method shown in the specification. Figure 1 The specification also provides a computer-readable storage medium storing a computer program, and the computer program can be used to execute the data analysis method shown in the specification.

[0102] The specification also provides a computer-readable storage medium storing a computer program, and the computer program can be used to execute the data analysis method shown in the specification. Figure 5 The specification also provides a computer-readable storage medium storing a computer program, and the computer program can be used to execute the data analysis method shown in the specification. Figure 1 The specification also provides a computer-readable storage medium storing a computer program, and the computer program can be used to execute the data analysis method shown in the specification. Figure 5 The specification also provides a computer-readable storage medium storing a computer program, and the computer program can be used to execute the data analysis method shown in the specification. Figure 1 The specification also provides a computer-readable storage medium storing a computer program, and the computer program can be used to execute the data analysis method shown in the specification.

[0103] Of course, in addition to the software implementation, the specification does not exclude other implementation manners, such as logic devices or a combination of software and hardware, that is, the execution subject of the following processing flow is not limited to each logic unit, but can also be hardware or a logic device.

[0104] In the 1990s, it was quite obvious to distinguish whether an improvement in a technology was in hardware (e.g., improvement in circuit structures of diodes, transistors, switches, etc.) or in software (improvement in method flow). However, as technology has evolved, many improvements in method flow today can be considered as direct improvements in hardware circuit structures. Designers almost always obtain the corresponding hardware circuit structures by programming the improved method flow into hardware circuits. Therefore, it cannot be said that an improvement in a method flow cannot be implemented by hardware entity modules. For example, a programmable logic device (PLD) (e.g., a field programmable gate array (FPGA)) is an integrated circuit whose logic function is determined by user programming of the device. A digital system is "integrated" on a PLD by the designer programming it, rather than by asking a chip manufacturer to design and fabricate a custom integrated circuit chip. Moreover, instead of manually fabricating integrated circuit chips, this programming is now mostly implemented by "logic compiler" software, which is similar to software compilers used in program development, and the original code to be compiled is written in a specific programming language, which is called a hardware description language (HDL), and there are many such languages, such as ABEL (Advanced Boolean Expression Language), AHDL (Altera Hardware Description Language), Confluence, CUPL (Cornell University Programming Language), HDCal, JHDL (Java Hardware Description Language), Lava, Lola, MyHDL, PALASM, RHDL (Ruby Hardware Description Language), etc., and the most commonly used are VHDL (Very-High-Speed Integrated Circuit Hardware Description Language) and Verilog. Those skilled in the art should be aware that, as long as the method flow is logically programmed in the above-mentioned hardware description languages and programmed into an integrated circuit, a hardware circuit implementing the logical method flow can be easily obtained.

[0105] The controller can be implemented in any suitable way, for example, the controller can take the form of a microprocessor or processor and a computer readable medium storing computer readable program code, such as software or firmware, executable by the (micro)processor, logic gates, switches, an application specific integrated circuit (ASIC), a programmable logic controller and an embedded microcontroller, examples of which include but are not limited to the following microcontrollers: ARC 625D, Atmel AT91SAM, Microchip PIC18F26K20 and Silicone Labs C8051F320, the memory controller can also be implemented as part of the control logic of the memory. Those skilled in the art will also know that, in addition to being implemented in pure computer readable program code, the controller can equally well be implemented to perform the same functions using logic gates, switches, an application specific integrated circuit, a programmable logic controller and an embedded microcontroller, etc. by means of a logical programming of the method steps. The controller can thus be considered as a hardware component, and the means comprised therein for performing the various functions can be considered as structures within the hardware component. Alternatively, the means for performing the various functions can even be considered as both a software module implementing the method and a structure within the hardware component.

[0106] The systems, apparatuses, modules or units illustrated by the above embodiments can be implemented by computer chips or entities, or by products with certain functions. A typical implementation device is a computer. Specifically, the computer can be a personal computer, a laptop computer, a cellular phone, a camera phone, a smart phone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or a combination of any of these devices.

[0107] For the sake of description, the above apparatuses are described in various units by functions respectively. Of course, the functions of each unit can be implemented in one or more software and / or hardware in implementing the present specification.

[0108] Those skilled in the art will understand that the embodiments of the present specification can be provided as a method, a system or a computer program product. Therefore, the present specification can take the form of a complete hardware embodiment, a complete software embodiment or an embodiment combining software and hardware aspects. Moreover, the present specification can take the form of a computer program product implemented on one or more computer usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) containing computer usable program code.

[0109] The specification is presented with reference to flow diagrams and / or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the specification. It will be understood that each block of the flow diagrams and / or block diagrams, and combinations of blocks in the flow diagrams and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general purpose computer, special purpose computer, embedded processing element or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flow diagrams and / or block diagrams block or blocks. Figure 1 The flow diagrams and / or block diagrams in the specification can present a method, apparatus or computer program product according to embodiments of the specification. Although the flow diagrams and / or block diagrams can present a method, apparatus or computer program product in a particular, it is understood that the method, apparatus and computer program product can include one or more additional steps, operations, or functions, and the method, apparatus and computer program product can include one or more other steps, operations, functions or combinations of steps, operations, or functions in Figure 1 The flow diagrams and / or block diagrams in the specification can present a method, apparatus or computer program product according to embodiments of the specification. Although the flow diagrams and / or block diagrams can present a method, apparatus or computer program product in a particular, it is understood that the method, apparatus and computer program product can include one or more additional steps, operations, or functions, and the method, apparatus and computer program product can include one or more other steps, operations, functions or combinations of steps, operations, or functions in

[0110] The computer program instructions can also be loaded into a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flow diagrams and / or block diagrams block or blocks. Figure 1 The flow diagrams and / or block diagrams in the specification can present a method, apparatus or computer program product according to embodiments of the specification. Although the flow diagrams and / or block diagrams can present a method, apparatus or computer program product in a particular, it is understood that the method, apparatus and computer program product can include one or more additional steps, operations, or functions, and the method, apparatus and computer program product can include one or more other steps, operations, functions or combinations of steps, operations, or functions in Figure 1 The flow diagrams and / or block diagrams in the specification can present a method, apparatus or computer program product according to embodiments of the specification. Although the flow diagrams and / or block diagrams can present a method, apparatus or computer program product in a particular, it is understood that the method, apparatus and computer program product can include one or more additional steps, operations, or functions, and the method, apparatus and computer program product can include one or more other steps, operations, functions or combinations of steps, operations, or functions in

[0111] The computer program instructions can also be loaded into a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flow diagrams and / or block diagrams block or blocks. Figure 1 The flow diagrams and / or block diagrams in the specification can present a method, apparatus or computer program product according to embodiments of the specification. Although the flow diagrams and / or block diagrams can present a method, apparatus or computer program product in a particular, it is understood that the method, apparatus and computer program product can include one or more additional steps, operations, or functions, and the method, apparatus and computer program product can include one or more other steps, operations, functions or combinations of steps, operations, or functions in ​ The flow diagrams and / or block diagrams in the specification can present a method, apparatus or computer program product according to embodiments of the specification. Although the flow diagrams and / or block diagrams can present a method, apparatus or computer program product in a particular, it is understood that the method, apparatus and computer program product can include one or more additional steps, operations, or functions, and the method, apparatus and computer program product can include one or more other steps, operations, functions or combinations of steps, operations, or functions in

[0112] In a typical configuration, a computing device includes one or more processors (CPUs), input / output interfaces, network interfaces, and memory.

[0113] The memory can include non-persistent memory, random access memory (RAM), and / or non-volatile memory, etc. in the form of a computer-readable medium, such as read only memory (ROM) or flash memory. The memory is an example of computer-readable media.

[0114] Computer-readable media includes permanent and non-permanent, movable and non-movable media that can be implemented by any method or technology to store information. The information can be computer-readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, compact disc read-only memory (CD-ROM), digital versatile disc (DVD) or other optical storage, magnetic cassette, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other non-transmission medium that can be used to store information accessible to a computing device. According to the definition herein, computer-readable media does not include transitory media such as modulated data signals and carriers.

[0115] It should also be noted that the terms "comprising", "containing", or any other variant thereof are intended to cover non-exclusive inclusion, such that a process, method, article or apparatus that comprises a list of elements does not only include those elements, but can also include other elements not expressly listed or inherent to such process, method, article or apparatus. Without more limitations, the element defined by the statement "comprising a" does not exclude the presence of additional identical elements in the process, method, article or apparatus that includes the element.

[0116] Those skilled in the art will appreciate that embodiments of the present specification can be provided as methods, systems or computer program products. Therefore, the present specification can take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Moreover, the present specification can take the form of a computer program product implemented on one or more computer-usable storage media (including, but not limited to, magnetic disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0117] The present specification can be described in the general context of computer-executable instructions, such as program modules, being executed by a computer. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform particular tasks or implement particular abstract data types. The present specification can also be practiced in distributed computing environments where tasks are performed by remote processing devices that are connected through a communication network. In a distributed computing environment, program modules can be located in both local and remote computer storage media including storage devices.

[0118] The various embodiments described in this specification are described using a numbering of embodiments approach: these are each individually integrated contributions pertaining to different but related aspects of the description. Each of the various embodiments can stand on its own, and each can be combined with the subject matter of other embodiments to produce further embodiments. Where appropriate, therefore, the contents of the specification can be regarded as being incorporated by reference, including the description, drawings, claims, abstract and the like.

[0119] The above only describes the embodiments of the specification and is not intended to limit the specification. The specification can have various modifications and changes for those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the specification shall be included in the scope of claims of the specification.

Claims

1. A data analysis method, characterized by, The method comprises the following steps: obtaining historical browsing data corresponding to target recommendation information, wherein the historical browsing data is used to reflect the browsing situation of the target recommendation information in history; inputting the historical browsing data into a pre-trained prediction model, so that the prediction model predicts the browsing data corresponding to the target recommendation information at a specified future time as standard browsing data; obtaining actual browsing data of the target recommendation information at the specified time, and determining the deviation between the actual browsing data and the standard browsing data; when the deviation is greater than a preset deviation, determining that the actual browsing data is abnormal data, and performing abnormal reason analysis on the abnormal data to obtain an analysis result; wherein the abnormal reason comprises a recommendation user group abnormality, and the recommendation user group abnormality can be obtained according to actual group distribution and reference group distribution analysis; the actual group distribution is the group distribution of the user group that produces the browsing situation reflected by the actual browsing data after receiving the target recommendation information; and the reference group distribution is the group distribution of the user group that can produce the browsing situation reflected by the abnormal data after receiving the target recommendation information under the premise that the browsing situation reflected by the abnormal data is normal browsing situation.

2. The method of claim 1, wherein, The step of obtaining the historical browsing data corresponding to the target recommendation information specifically comprises: obtaining initial browsing data of the target recommendation information in a historical period; preprocessing the initial browsing data, so that the preprocessed data is used as the obtained historical browsing data corresponding to the target recommendation information, wherein the preprocessing comprises at least one of de-duplication processing, abnormal value processing and standardization processing.

3. The method of claim 1, wherein, The method further comprises: when the deviation is not greater than the preset deviation, determining a browsing data reasonable interval according to the historical browsing data, and judging whether the actual browsing data is located in the browsing data reasonable interval; if not, the actual browsing data is regarded as abnormal data, and data analysis is performed on the abnormal data to obtain an analysis result.

4. The method of claim 1 or 3, wherein, The step of performing abnormal reason analysis on the abnormal data to obtain an analysis result specifically comprises: obtaining recommendation strategy information corresponding to the abnormal data under each business dimension; for the recommendation strategy information corresponding to each business dimension, matching the recommendation strategy information corresponding to the business dimension with historical recommendation strategy information under the business dimension, and in the case where the recommendation strategy information corresponding to the business dimension is determined to be unmatched with the historical recommendation strategy information under the business dimension, taking the recommendation strategy information corresponding to the business dimension as abnormal recommendation strategy information; taking the abnormal recommendation strategy information as abnormal reason information for the occurrence of the abnormal data, and obtaining an analysis result according to the abnormal reason information.

5. The method of claim 4, wherein, The method further comprises: inputting the abnormal recommendation strategy information and prompt sentences into a pre-set large model, so as to generate adjustment strategy information for avoiding the occurrence of the abnormal data through the large model; adjusting the abnormal recommendation strategy information according to the adjustment strategy information, so as to perform business according to the adjusted strategy information.

6. The method of claim 1, wherein, The step of pre-training the prediction model specifically comprises: obtaining sample browsing information and label browsing data corresponding to the sample browsing information; inputting the sample browsing information into a to-be-trained prediction model, so that the to-be-trained prediction model determines predicted browsing data corresponding to the sample browsing information; determining a loss value according to a deviation between the predicted browsing data and the label browsing data, and training the to-be-trained prediction model according to the loss value, wherein the deviation and the loss value are in a positive correlation.

7. The method of claim 1, wherein, The step of performing abnormal reason analysis on the abnormal data to obtain an analysis result specifically comprises: determining abnormal recommendation strategy information in each recommendation strategy information corresponding to each business dimension of the abnormal data according to the actual population distribution and the reference population distribution, so as to obtain an analysis result according to the abnormal recommendation strategy information.

8. A data analysis device, characterized by, comprises: a first obtaining module configured to obtain historical browsing data corresponding to target recommendation information, the historical browsing data being used to reflect browsing of the target recommendation information in history; a prediction module configured to input the historical browsing data into a pre-trained prediction model, so that the prediction model predicts browsing data corresponding to the target recommendation information at a specified time in the future as standard browsing data; a second obtaining module configured to obtain actual browsing data of the target recommendation information at the specified time, and determine a deviation between the actual browsing data and the standard browsing data; an analysis module configured to, when the deviation is greater than a preset deviation, determine that the actual browsing data is abnormal data, and perform abnormal reason analysis on the abnormal data to obtain an analysis result; wherein the abnormal reason comprises a recommendation user population abnormality, and the recommendation user population abnormality can be analyzed according to an actual population distribution and a reference population distribution; the actual population distribution is a population distribution of a user population that produces browsing reflected by the actual browsing data after receiving the target recommendation information; and the reference population distribution is a population distribution of a user population that is predicted to be able to produce browsing reflected by the abnormal data under the premise that the browsing reflected by the abnormal data is normal browsing.

9. A computer-readable storage medium, characterized in that, The storage medium stores a computer program, and the computer program is executed by the processor to implement the method in any one of claims 1-7.

10. An electronic device comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, characterized in that, The processor executes the program to implement the method in any one of claims 1-7.

Images