Data processing method, device, equipment and computer readable storage medium

Abstract

The present invention provides a data processing method, device, equipment and computer-readable storage medium, the method comprising: obtaining a path analysis request sent by a terminal device; obtaining historical browsing data corresponding to an item to be analyzed and multiple candidate items related to the item to be analyzed in a preset data server according to the path analysis request; analyzing the browsing path corresponding to the item to be analyzed according to the historical browsing data to obtain an analysis result; establishing an analysis report including a visual illustration according to the analysis result, and sending the analysis report to the terminal device. Thus, the path corresponding to the item to be analyzed customized by the user can be analyzed to obtain the analysis result, which can meet the personalized needs of the user. After obtaining the analysis result, an analysis report including a visual illustration can be generated according to the analysis result, so that the user can understand the analysis result more intuitively and improve the user experience.

Description

Technical Field

[0001] The present invention relates to the field of data processing, and in particular to a data processing method, device, equipment and computer-readable storage medium. Background Art

[0002] With the development of the Internet, users are using websites or application software more and more frequently, and users can browse information, socialize, shop, etc. on websites or application software. In order to understand user behavior preferences and measure the effect of optimization or marketing promotion when optimizing websites or application software, it is necessary to analyze the user's access behavior path on the website or application software.

[0003] In the prior art, generally all historical data corresponding to a certain item or a certain user is obtained, and a preset analysis model is used to perform data analysis on all the historical data.

[0004] However, the above path analysis methods are often only based on data analysis of specific data, and the analysis content and results are relatively fixed, which cannot meet the actual needs of users for path analysis. Summary of the invention

[0005] The present invention provides a data processing method, device, equipment and computer-readable storage medium, which are used to solve the technical problem that the existing path analysis method is only based on data analysis of specific data, the analysis content and results are relatively fixed, and cannot meet the actual needs of users for path analysis.

[0006] A first aspect of the present invention is to provide a data processing method, comprising:

[0007] Obtaining a path analysis request sent by a terminal device, wherein the path analysis request includes brand information, category information, store information corresponding to the item to be analyzed, and a time range selected by a user;

[0008] According to the path analysis request, obtaining historical browsing data corresponding to the object to be analyzed and a plurality of candidate objects related to the object to be analyzed from a preset data server;

[0009] Analyze the browsing path corresponding to the item to be analyzed according to the historical browsing data to obtain an analysis result;

[0010] An analysis report including visual drawings is created according to the analysis results, and the analysis report is sent to the terminal device.

[0011] A second aspect of the present invention is to provide a data processing device, comprising:

[0012] An acquisition module, used to acquire a path analysis request sent by a terminal device, wherein the path analysis request includes brand information, category information, store information corresponding to the item to be analyzed, and a time range selected by the user;

[0013] A screening module, configured to obtain, in a preset data server, historical browsing data corresponding to the object to be analyzed and a plurality of candidate objects related to the object to be analyzed according to the path analysis request;

[0014] An analysis module, used to analyze the browsing path corresponding to the item to be analyzed according to the historical browsing data to obtain an analysis result;

[0015] The sending module is used to create an analysis report including visual illustrations according to the analysis results, and send the analysis report to the terminal device.

[0016] A third aspect of the present invention is to provide a data processing device, comprising: a memory, a processor;

[0017] Memory; Memory for storing instructions executable by the processor;

[0018] The processor is used to call the program instructions in the memory to execute the method described in the first aspect.

[0019] A fourth aspect of the present invention is to provide a computer-readable storage medium, wherein the computer-readable storage medium stores computer-executable instructions, and when the computer-executable instructions are executed by a processor, they are used to implement the method described in the first aspect.

[0020] The data processing method, device, equipment and computer-readable storage medium provided by the present invention can analyze the path corresponding to the item to be analyzed customized by the user by acquiring the path analysis request sent by the terminal device, obtain the analysis result, and meet the personalized needs of the user. In addition, after obtaining the analysis result, an analysis report including a visual illustration can be generated according to the analysis result, so that the user can understand the analysis result more intuitively and improve the user experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention, and a person skilled in the art can also obtain other drawings based on these drawings.

[0022] Figure 1 A schematic diagram of the network architecture based on which the present invention is based;

[0023] Figure 2 A flowchart of a data processing method provided in Embodiment 1 of the present disclosure;

[0024] Figure 3 A schematic diagram of a display interface provided in an embodiment of the present disclosure;

[0025] Figure 4 A flowchart of a data processing method provided in Embodiment 2 of the present disclosure;

[0026] Figure 5 A flowchart of a data processing method provided in Embodiment 3 of the present disclosure;

[0027] Figure 6 A schematic diagram of a user set of at least one category provided in an embodiment of the present disclosure;

[0028] Figure 7 A flowchart of a data processing method provided in Embodiment 4 of the present disclosure;

[0029] Figure 8 A flowchart of a data processing method provided in Embodiment 5 of the present disclosure;

[0030] Fig. 9 A structural diagram of a data processing device provided in Embodiment 6 of the present disclosure;

[0031] Fig.10 A structural diagram of a data processing device provided in Embodiment 7 of the present disclosure;

[0032] Fig.11 A schematic diagram of the structure of a data processing device provided in Embodiment 8 of the present disclosure;

[0033] Fig.12 A schematic diagram of the structure of a data processing device provided in Embodiment 9 of the present disclosure;

[0034] Fig.13 A schematic diagram of the structure of a data processing device provided in Embodiment 10 of the present disclosure;

[0035] Fig.14 A schematic diagram of the structure of a data processing device provided in Example 11 of the present disclosure. DETAILED DESCRIPTION

[0036] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. All other embodiments obtained based on the embodiments in the present invention belong to the scope of protection of the present invention.

[0037] In response to the technical problem that the existing path analysis method mentioned above is only based on data analysis of specific data, the analysis content and results are relatively fixed, and cannot meet the actual needs of users for path analysis, the present invention provides a data processing method, device, equipment and computer-readable storage medium.

[0038] It should be noted that the data processing method, apparatus, device and computer-readable storage medium provided by the present application can be used in various path analysis scenarios.

[0039] Existing path analysis methods generally target a certain item or a certain user, obtain all browsing data corresponding to the item or user from the database, and perform path analysis. However, the above methods can only perform path analysis based on all browsing data, and the analysis results obtained are often relatively fixed and not comprehensive enough to meet the personalized needs of users.

[0040] In the process of solving the above technical problems, the inventors found through research that in order to improve the pertinence of path analysis and meet the personalized needs of users, user-defined path analysis requests can be obtained, and path analysis can be performed according to the user-defined path analysis requests, without being restricted to fixed data corresponding to a certain product. Thus, the obtained path analysis results can be more in line with the actual needs of users.

[0041] Figure 1 This is a schematic diagram of the network architecture based on the present invention, such as Figure 1 As shown, the network architecture based on the present invention at least includes: a terminal device 1, a server 2 and a data server 3. Among them, the server 2 is provided with a data analysis device, which is written in languages ​​such as C / C++, Java, Shell or Python; the terminal device 1 can be, for example, a desktop computer, a tablet computer, etc. The data server 3 can be a cloud server or a server cluster, which stores a large amount of data. The server 2 is respectively connected to the terminal device 1 and the data server 3 in communication, so that it can exchange information with the terminal device 1 and the data server 3 respectively.

[0042] Figure 2 A flowchart of a data processing method provided in the first embodiment of the present disclosure is shown in FIG. Figure 2 As shown, the method includes:

[0043] Step 101: Obtain a path analysis request sent by a terminal device, wherein the path analysis request includes category information corresponding to the item to be analyzed, store information, and a time range selected by the user.

[0044] The execution subject of this embodiment is a data processing device. The data processing device can be coupled to a server. The server is respectively connected to a terminal device and a data server for communication. Thus, information can be exchanged with the terminal device and the server respectively.

[0045] In this embodiment, in order to analyze the browsing path of a certain item to be analyzed, the user can input the brand information, category information, store information and the time range selected by the user on the terminal device according to actual needs. The terminal device can generate a path analysis request according to the information input by the user, and send the path analysis request to the data processing device for the data processing device to perform data processing operations. Accordingly, the data processing device can obtain the path analysis request sent by the terminal device.

[0046] Figure 3 A schematic diagram of a display interface provided by an embodiment of the present disclosure, such as Figure 3 As shown, the display interface is provided with an input box for inputting a time range, category information corresponding to the item to be analyzed, and store information. The user can input corresponding data in the input box to realize the generation of a path analysis request.

[0047] Taking practical application as an example, the item to be analyzed may be a commodity in an e-commerce platform. Accordingly, the category information corresponding to the item to be analyzed may include brand information corresponding to the commodity, the specific category of the commodity under the brand information, price information of competing products corresponding to the commodity, etc.

[0048] Step 102: According to the path analysis request, historical browsing data corresponding to the object to be analyzed and a plurality of candidate objects related to the object to be analyzed is obtained from a preset data server.

[0049] In this embodiment, each object to be analyzed corresponds to a plurality of candidate objects related thereto. For example, if the object to be analyzed is a commodity on an e-commerce platform, the candidate object may be a competitor of the commodity. For example, the candidate object may be a commodity of a different brand but with the same efficacy as the object to be analyzed.

[0050] In order to implement the path analysis of the item to be analyzed, after obtaining the path analysis request, the data processing device can obtain the historical browsing data corresponding to the item to be analyzed and multiple candidate items related to the item to be analyzed from the preset data server. The historical browsing data can be the browsing records of multiple users who have browsed the item to be analyzed in the past, and can also include the purchase record, collection information, shopping cart information, etc. corresponding to the item to be analyzed.

[0051] Step 103: Analyze the browsing path corresponding to the item to be analyzed according to the historical browsing data to obtain an analysis result.

[0052] In this embodiment, after the historical browsing data is obtained, the browsing path analysis operation can be performed on the item to be analyzed according to the historical browsing data to obtain the analysis result. Since the historical browsing data includes all the browsing information of the item to be analyzed within a preset time range, the browsing path analysis operation can be accurately performed according to the historical browsing data.

[0053] Step 104: Create an analysis report including visual drawings according to the analysis results, and send the analysis report to the terminal device.

[0054] In this embodiment, in order to make the user understand the analysis results more intuitively, after obtaining the analysis results, a visual drawing can be generated according to the analysis results, and an analysis report including the visual drawing can be further generated. In addition, the analysis report can also be sent to the user's terminal device so that the user can view the analysis report directly on the terminal device.

[0055] The data processing method provided in this embodiment can analyze the path corresponding to the item to be analyzed customized by the user and obtain the analysis result by acquiring the path analysis request sent by the terminal device, which can meet the personalized needs of the user. In addition, after obtaining the analysis result, an analysis report including a visual illustration can be generated according to the analysis result, so that the user can understand the analysis result more intuitively and improve the user experience.

[0056] Figure 4 This is a flow chart of a data processing method provided in the second embodiment of the present disclosure, based on the first embodiment, as shown in FIG. Figure 4 As shown, before step 102, the following steps are also included:

[0057] Step 201: Calculate the target vector corresponding to the object to be analyzed.

[0058] Step 202: Calculate the similarity between the target vector and all preset candidate items respectively.

[0059] Step 203: Determine the plurality of candidate items related to the item to be analyzed according to the similarity.

[0060] In this embodiment, each object to be analyzed corresponds to a plurality of candidate objects related thereto. For example, if the object to be analyzed is a commodity on an e-commerce platform, the candidate object may be a competitor of the commodity. For example, the candidate object may be a commodity of a different brand but with the same efficacy as the object to be analyzed.

[0061] Therefore, before obtaining historical browsing data, it is first necessary to determine multiple candidate items corresponding to the item to be analyzed.

[0062] Specifically, the target vector corresponding to the object to be analyzed may be calculated, the similarities between the target vector and vectors of all preset candidate objects may be calculated respectively, and a plurality of candidate objects related to the object to be analyzed may be determined according to the similarities.

[0063] Furthermore, step 201 specifically includes:

[0064] Determining an initial vector of the object to be analyzed according to a preset word vector and attribute information of the object to be analyzed;

[0065] Obtaining historical behavior data corresponding to the item to be analyzed from a preset data server, and screening target entity pairs from the historical data;

[0066] The target vector is calculated according to the initial vector and the target entity pair.

[0067] In this embodiment, the preset word vectors can be matched with the attribute information of the object to be analyzed, and vector combination can be performed to obtain the initial vector of the object to be analyzed. The attribute information of the object to be analyzed includes but is not limited to the main product word, function attribute, style attribute, material attribute, style attribute, crowd attribute, region attribute, color attribute, scene attribute, taste attribute, season attribute, and size attribute.

[0068] Obtain historical behavior data corresponding to the item to be analyzed from a preset data server, wherein the historical behavior data includes but is not limited to user operations such as clicks, adding to shopping carts, and purchases. Filter target entity pairs based on the historical behavior data. Calculate the target vector based on the initial vector and the target entity pair.

[0069] The data processing method provided in this embodiment can improve the accuracy of subsequent path analysis by first determining multiple candidate objects corresponding to the object to be analyzed according to the target vector of the object to be analyzed before acquiring historical browsing data.

[0070] Based on any of the above embodiments, before step 102, the method further includes:

[0071] The set of items effectively placed by the user within the time range is calculated through a preset network model, wherein the item combination includes the multiple candidate items.

[0072] In this embodiment, a preset network model can be used to calculate the set of items effectively placed by the user within a time range, wherein the item combination includes the multiple candidate items. Specifically, the network model can make statistics according to four dimensions: time, store, category, and brand, and calculate the corresponding consumption of the user. Statistics are made according to the data whose total consumption ranking exceeds the preset threshold within the time range, and statistical indicators are added to each data according to the above four dimensions: average consumption, maximum consumption of a single user ID, store ranking, and consumption ratio with the first ranking under the same dimension. Among them, the user can specifically be an advertiser who places advertisements.

[0073] Specifically, the network model includes the following access conditions:

[0074] 1. Under the above four dimensions, the consumption of a single user ID = the minimum consumption of a single user ID;

[0075] 2. If the user's consumption is greater than the average consumption or the minimum consumption requirement, the higher the ratio of the user's consumption to the first-ranked consumption, the higher the user's admission can be, and vice versa.

[0076] 3. The user's plan has a time range. There may be some fluctuations or even windows in the delivery of stores, categories, and brands. Therefore, the idea of ​​the leaky bucket algorithm for flow control can be adopted. When the user meets conditions 1 and 2, a certain credit value is given. When it does not meet the conditions, deductions are made according to the current credit value. If the credit value is zero, query access is prohibited. If the conditions are met again, the credit value is reset, and the above steps are repeated according to actual needs.

[0077] The data processing method provided in this embodiment uses a preset network model to calculate the set of items effectively placed by the user within a time range, thereby improving the access experience and reducing the risk of data leakage.

[0078] Figure 5 The flowchart of the data processing method provided in the third embodiment of the present disclosure is based on any of the above embodiments. Figure 5 As shown, step 103 specifically includes:

[0079] Step 301: Detect whether multiple users in the historical browsing data trigger a preset target operation on the item to be analyzed and / or the candidate item to obtain a detection result.

[0080] Step 302: Classify the multiple users according to the detection result to obtain a user set of at least one category.

[0081] Step 303: for each user set, analyze the browsing paths corresponding to the items to be analyzed according to the analysis time interval corresponding to the user set to obtain analysis results.

[0082] In this embodiment, after the effective set of items is determined, the user types may be further classified.

[0083] Optionally, it is possible to detect whether multiple users in the historical browsing data have triggered preset target operations on the items to be analyzed and / or the candidate items to obtain a detection result. The detection result may specifically include triggering the target operation on the items to be analyzed, not triggering the target operation on the items to be analyzed, triggering the target operation on the candidate items, triggering the target operation on the items to be analyzed and the candidate items, and not triggering the target operation on the items to be analyzed and the candidate items.

[0084] Then, a classification operation can be performed on the multiple users according to the detection result to obtain a user set of at least one category.

[0085] Specifically, the target operation may be a purchase operation of the item to be analyzed. Figure 6 A schematic diagram of a user set of at least one category provided in an embodiment of the present disclosure, such as Figure 6 As shown, the user set may specifically include a user set 1 that purchases the items to be analyzed, a user set 2 that purchases the candidate items, a user set 3 that purchases the items to be analyzed and the candidate items, and a user set 4 that purchases neither the items to be analyzed nor the candidate items.

[0086] Furthermore, different analysis time intervals may be set for each user set, so that the browsing paths corresponding to the items to be analyzed may be analyzed according to the analysis time intervals corresponding to the user sets to obtain analysis results.

[0087] Specifically, the analysis time interval corresponding to the set of users who purchased the items to be analyzed starts from the time of tracing back from the first purchase behavior, and ends on the day of the last purchase behavior. Taking the tracing back period as an example of 2 days, the analysis time interval is from two days before the first purchase behavior to the day of the last purchase behavior. The analysis time interval corresponding to the set of users who did not purchase the items to be analyzed starts from the time of tracing back from the first advertisement exposure, and ends on the day of the last advertisement exposure. Taking the tracing back period as an example of 2 days, the analysis time interval is from two days before the first advertisement exposure to the day of the last advertisement exposure.

[0088] The data processing method provided in this embodiment can further improve the accuracy of path analysis by classifying users and analyzing the browsing paths corresponding to the items to be analyzed according to the analysis time intervals corresponding to the classified user sets.

[0089] Figure 7 A flowchart of a data processing method provided in Embodiment 4 of the present disclosure is provided. Based on any of the above embodiments, Figure 7 As shown, step 103 specifically includes:

[0090] Step 401: Determine the page views of each page corresponding to the item to be analyzed and the candidate item according to the historical browsing data.

[0091] Step 402: Calculate the browsing ratio scores of the items to be analyzed and the candidate items viewed by users according to the page views to obtain the analysis results.

[0092] In this embodiment, after obtaining the historical browsing data, the page views of each page corresponding to the item to be analyzed and the candidate items can be determined respectively according to the historical browsing data. According to the page views, the browsing ratio score of the user viewing the item to be analyzed and the candidate items is calculated to obtain the analysis result. Specifically, the browsing ratio score is calculated based on the number of items to be analyzed and the number of candidate items browsed by the user before purchase, and the score reflects the user's interest and loyalty to the brand.

[0093] If the browsing ratio score is greater than 0, the number of items to be analyzed that the user browsed is greater than the number of candidate items, and the higher the score, the higher the user's interest in the brand. Conversely, if the browsing ratio score is less than 0, the number of candidate items that the user browsed is greater than the number of items to be analyzed, and the lower the score, the lower the user's interest in the brand.

[0094] The data processing method provided in this embodiment determines the page views of each page corresponding to the item to be analyzed and the candidate items respectively according to the historical browsing data, and calculates the browsing ratio score of the user viewing the item to be analyzed and the candidate items according to the page views, so as to accurately analyze the user's behavior path.

[0095] Specifically, based on any of the above embodiments, the visual illustrations include one or more of a path flow diagram, a hotspot path diagram, a path funnel diagram, and an item recognition diagram.

[0096] The path flow diagram may specifically be a Sankey diagram, which may intuitively display the main conversion flows between advertisements and page paths for user groups such as users who purchase items to be analyzed, users who purchase candidate items, users who purchase both items to be analyzed and candidate items, and potential purchasing users.

[0097] The hotspot path map can intuitively show the exposure combinations of the most popular ads or pages that are viewed or converted most frequently among different user groups.

[0098] Users can personalize the path funnel chart to quickly analyze the flow of key nodes of user flow in the specified behavior path on the user page and advertising path.

[0099] The item cognitive map can intuitively show the brand interest distribution of user groups such as users who purchase the item to be analyzed, users who purchase candidate items, users who purchase both the item to be analyzed and the candidate items, and potential purchasing users.

[0100] The product browsing ratio score is calculated based on the number of items to be analyzed and the number of candidate items browsed by users, and the user's awareness of the brand of the item to be analyzed and the brand of the candidate items are divided into intervals. This reflects the user's interest and loyalty to the brand, and can grasp the brand awareness of the item to be analyzed and the candidate items, so as to measure the relative loyalty of users to the item to be analyzed and the candidate items.

[0101] Figure 8 A flowchart of a data processing method provided in Embodiment 5 of the present disclosure is provided. Based on any of the above embodiments, Figure 8 As shown, it also includes:

[0102] Step 501: Acquire a trigger request sent by a terminal device, wherein the trigger request is generated according to a trigger operation of a preset element in the visual illustration by the user on the terminal device.

[0103] Step 502: Determine feedback information corresponding to the preset element according to the trigger operation.

[0104] Step 503: Send the feedback information to the terminal device.

[0105] In this embodiment, the user can also trigger the preset element in the visual figure through interface interaction. Correspondingly, according to the triggering operation, feedback information corresponding to the preset element can be determined and sent to the terminal device.

[0106] Specifically, when the visualization diagram is a path flow diagram, the feedback information can specifically be the behavior paths of different user groups. For users who purchase the item to be analyzed, the behavior path analysis of specific groups can be drilled down to new and old customers, different genders, and different age groups; the churn rate and the proportion of users flowing to candidate items / items to be analyzed and candidate items; the flow information and the inflow and outflow structure of each touch point; and a customized analysis conversion path funnel.

[0107] When the visualization attachment is a hotspot path map, the feedback information may specifically be the behavior paths of different user groups. For the users who purchase the items to be analyzed, the behavior paths of specific groups can be analyzed by drilling down to new and old customers, different genders, and different age groups.

[0108] When the visualization figure is a path funnel diagram, the feedback information may specifically be the behavior paths of different user groups.

[0109] The data processing method provided in this embodiment determines the feedback information corresponding to the preset element according to the trigger operation, and sends the feedback information to the terminal device, so that the user can view the current analysis results more clearly, thereby improving the user experience.

[0110] Fig. 9 A structural diagram of a data processing device provided in Embodiment 6 of the present disclosure is shown in FIG. Fig. 9 As shown, the device includes: an acquisition module 61, a screening module 62, an analysis module 63 and a sending module 64, wherein the acquisition module 61 is used to obtain a path analysis request sent by a terminal device, wherein the path analysis request includes brand information, category information, store information and a time range selected by a user corresponding to the item to be analyzed. The screening module 62 is used to obtain historical browsing data corresponding to the item to be analyzed and multiple candidate items related to the item to be analyzed in a preset data server according to the path analysis request. The analysis module 63 is used to analyze the browsing path corresponding to the item to be analyzed according to the historical browsing data to obtain an analysis result. The sending module 64 is used to establish an analysis report including a visual illustration according to the analysis result, and send the analysis report to the terminal device.

[0111] The data processing device provided in this embodiment can analyze the path corresponding to the item to be analyzed customized by the user by acquiring the path analysis request sent by the terminal device, and obtain the analysis result, which can meet the personalized needs of the user. In addition, after obtaining the analysis result, an analysis report including a visual illustration can be generated according to the analysis result, so that the user can understand the analysis result more intuitively and improve the user experience.

[0112] Fig.10 This is a structural diagram of a data processing device provided in Embodiment 7 of the present disclosure, based on Embodiment 6, as shown in FIG. Fig.10 As shown, the device also includes: a target vector calculation module 71, a similarity calculation module 72 and a determination module 73, wherein the target vector calculation module 71 is used to calculate the target vector corresponding to the object to be analyzed; the similarity calculation module 72 is used to respectively calculate the similarity between the target vector and all preset candidate objects; and the determination module 73 is used to determine the multiple candidate objects related to the object to be analyzed based on the similarity.

[0113] Further, on the basis of the sixth embodiment, the target vector calculation module is used for:

[0114] Determining an initial vector of the object to be analyzed according to a preset word vector and attribute information of the object to be analyzed;

[0115] Obtaining historical behavior data corresponding to the item to be analyzed from a preset data server, and screening target entity pairs from the historical data;

[0116] The target vector is calculated according to the initial vector and the target entity pair.

[0117] Furthermore, based on the sixth embodiment, the device further includes:

[0118] The item set calculation module is used to calculate the item set effectively placed by the user within the time range through a preset network model, wherein the item combination includes the multiple candidate items.

[0119] Fig.11 This is a structural diagram of a data processing device provided in Embodiment 8 of the present disclosure. Based on any of the above embodiments, Fig.11 As shown, the analysis module includes: a detection unit 81, a classification unit 82 and an analysis unit 83, wherein the detection unit 81 is used to detect whether multiple users in the historical browsing data trigger a preset target operation on the item to be analyzed and / or the candidate item to obtain a detection result; the classification unit 82 is used to classify the multiple users according to the detection result to obtain a user set of at least one category; the analysis unit 83 is used to analyze the browsing path corresponding to the item to be analyzed for each user set according to the analysis time interval corresponding to the user set to obtain an analysis result.

[0120] Fig.12 This is a structural diagram of a data processing device provided in Embodiment 9 of the present disclosure. Based on any of the above embodiments, Fig.12 As shown, the analysis module includes: a page view determination unit 91 and a calculation unit 92, wherein the page view determination unit 91 is used to determine the page views of each page corresponding to the item to be analyzed and the candidate item according to the historical browsing data; the calculation unit 92 is used to calculate the browsing ratio score of the user viewing the item to be analyzed and the candidate item according to the page views to obtain the analysis result.

[0121] Further, based on any of the above embodiments, the visual illustrations include one or more of a path flow diagram, a hotspot path diagram, a path funnel diagram, and an item recognition diagram.

[0122] Fig.13 This is a structural diagram of a data processing device provided in Embodiment 10 of the present disclosure. Based on any of the above embodiments, Fig.13As shown, it also includes: a trigger request acquisition module 111, a feedback information determination module 112 and a feedback module 113, wherein the trigger request acquisition module 111 is used to obtain a trigger request sent by a terminal device, and the trigger request is generated according to a trigger operation of the user on the terminal device for a preset element in the visual illustration; the feedback information determination module 112 is used to determine the feedback information corresponding to the preset element according to the trigger operation; the feedback module 113 is used to send the feedback information to the terminal device.

[0123] Fig.14 A structural diagram of a data processing device provided in the eleventh embodiment of the present disclosure, such as Fig.14 As shown, the data processing device includes: a memory 121, a processor 122;

[0124] Memory 121; Memory 121 for storing instructions executable by the processor 122;

[0125] The processor 122 is used to call the program instructions in the memory 121 to execute the method described in any of the above embodiments.

[0126] The memory 121 is used to store programs. Specifically, the program may include program codes, and the program codes include computer operation instructions. The memory 121 may include a high-speed RAM memory, and may also include a non-volatile memory, such as at least one disk memory.

[0127] The processor 122 may be a central processing unit (CPU), or an application specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of the present invention.

[0128] Optionally, in a specific implementation, if the memory 121 and the processor 122 are implemented independently, the memory 121 and the processor 122 can be connected to each other through a bus and communicate with each other. The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus. The bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Fig.14Only one thick line is used in the diagram, but this does not mean that there is only one bus or only one type of bus.

[0129] Optionally, in a specific implementation, if the memory 121 and the processor 122 are integrated on a chip, the memory 121 and the processor 122 can communicate with each other through an internal interface.

[0130] Yet another embodiment of the present disclosure provides a computer-readable storage medium, wherein the computer-readable storage medium stores computer-executable instructions, and when the computer-executable instructions are executed by a processor, they are used to implement the method described in any of the above embodiments.

[0131] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working process of the device described above can refer to the corresponding process in the aforementioned method embodiment, and will not be repeated here.

[0132] Those skilled in the art can understand that all or part of the steps of implementing the above-mentioned method embodiments can be completed by hardware related to program instructions. The aforementioned program can be stored in a computer-readable storage medium. When the program is executed, the steps of the above-mentioned method embodiments are executed; and the aforementioned storage medium includes: ROM, RAM, disk or optical disk and other media that can store program codes.

[0133] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or replace some or all of the technical features therein with equivalents. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention.

Claims

1. A data processing method, characterized in that: include: Obtaining a path analysis request sent by a terminal device, wherein the path analysis request includes brand information, category information, store information corresponding to the item to be analyzed input by the user, and a time range selected by the user; The set of items effectively placed by the user within the time range is calculated by a preset network model, and the network model at least includes the following admission conditions: under the dimensions of time, store, category and brand, the consumption of a single user ID is equal to the minimum consumption of a single user ID, and when the user's consumption is greater than the average consumption or the minimum consumption, the ratio between the user's consumption and the first-ranked consumption under the same dimension is proportional to the user's admission; According to the path analysis request, a target vector corresponding to the item to be analyzed is calculated; the target vector is determined according to an initial vector of the item to be analyzed and a target entity pair, the target entity pair is determined according to historical behavior data corresponding to the item to be analyzed, and the initial vector is determined according to a preset word vector and attribute information of the item to be analyzed; similarities between the target vector and all candidate items in the item set are calculated respectively; and multiple candidate items related to the item to be analyzed are determined according to the similarities; Acquiring historical browsing data of multiple users who have browsed the object to be analyzed and multiple candidate objects with the same efficacy as the object to be analyzed within the time range from a preset data server, wherein the candidate objects are competing products of the object to be analyzed; Analyze the browsing path corresponding to the item to be analyzed according to the historical browsing data to obtain an analysis result; An analysis report including visual drawings is created according to the analysis results, and the analysis report is sent to the terminal device.

2. The method according to claim 1, characterized in that The calculating the target vector corresponding to the object to be analyzed includes: Determining an initial vector of the object to be analyzed according to a preset word vector and attribute information of the object to be analyzed; Obtaining historical behavior data corresponding to the item to be analyzed from a preset data server, and screening target entity pairs from the historical behavior data; The target vector is calculated according to the initial vector and the target entity pair.

3. The method according to claim 1 or 2, characterized in that: The step of analyzing the browsing path corresponding to the item to be analyzed according to the historical browsing data to obtain the analysis result includes: Detecting whether multiple users in the historical browsing data trigger a preset target operation on the object to be analyzed and / or the candidate object, and obtaining a detection result; Classify the multiple users according to the detection result to obtain a user set of at least one category; For each user set, the browsing paths corresponding to the items to be analyzed are analyzed according to the analysis time interval corresponding to the user set to obtain analysis results.

4. The method according to claim 1 or 2, characterized in that: The step of analyzing the browsing path corresponding to the item to be analyzed according to the historical browsing data to obtain the analysis result includes: Determine the page views of each page corresponding to the item to be analyzed and the candidate item according to the historical browsing data; The browsing ratio scores of the items to be analyzed and the candidate items viewed by users are calculated according to the page views to obtain the analysis result.

5. The method according to claim 1 or 2, characterized in that: The visual illustrations include one or more of a path flow diagram, a hotspot path diagram, a path funnel diagram, and an item recognition diagram.

6. The method according to claim 5, characterized in that Also includes: Acquire a trigger request sent by a terminal device, where the trigger request is generated according to a trigger operation of a preset element in the visual illustration by the user on the terminal device; Determining feedback information corresponding to the preset element according to the trigger operation; The feedback information is sent to the terminal device.

7. A data processing device, characterized in that: include: An acquisition module, used to acquire a path analysis request sent by a terminal device, wherein the path analysis request includes brand information, category information, store information corresponding to the item to be analyzed input by the user, and a time range selected by the user; An item set calculation module is used to calculate the item set effectively placed by the user within the time range through a preset network model, wherein the network model at least includes the following admission conditions: under the dimensions of time, store, category and brand, the consumption of a single user ID is equal to the minimum consumption of a single user ID, and when the user's consumption is greater than the average consumption or the minimum consumption, the ratio between the user's consumption and the first-ranked consumption under the same dimension is proportional to the user's admission; a screening module, configured to obtain, from a preset data server, historical browsing data corresponding to the item to be analyzed and a plurality of candidate items related to the item to be analyzed within the time range according to the path analysis request, wherein the candidate items are competing products of the item to be analyzed; An analysis module, used to analyze the browsing path corresponding to the item to be analyzed according to the historical browsing data to obtain an analysis result; A sending module, used for creating an analysis report including a visual illustration according to the analysis result, and sending the analysis report to the terminal device; The device also includes: a target vector calculation module, used to calculate a target vector corresponding to the item to be analyzed before obtaining historical browsing data of multiple users who have browsed the item to be analyzed and multiple candidate items with the same efficacy as the item to be analyzed within the time range from a preset data server; the target vector is determined according to an initial vector of the item to be analyzed and a target entity pair, the target entity pair is determined according to historical behavior data corresponding to the item to be analyzed, and the initial vector is determined according to a preset word vector and attribute information of the item to be analyzed; A similarity calculation module, used to respectively calculate the similarity between the target vector and all candidate items in the item set; A determination module is used to determine a plurality of candidate objects related to the object to be analyzed according to the similarity.

8. The device according to claim 7, characterized in that The target vector calculation module is used for: Determining an initial vector of the object to be analyzed according to a preset word vector and attribute information of the object to be analyzed; Obtaining historical behavior data corresponding to the item to be analyzed from a preset data server, and screening target entity pairs from the historical behavior data; The target vector is calculated according to the initial vector and the target entity pair.

9. The device according to claim 7 or 8, characterized in that The analysis module comprises: A detection unit, used to detect whether multiple users in the historical browsing data trigger a preset target operation on the item to be analyzed and / or the candidate item, and obtain a detection result; A classification unit, configured to classify the plurality of users according to the detection result to obtain a user set of at least one category; The analysis unit is used to analyze the browsing paths corresponding to the items to be analyzed for each user set according to the analysis time interval corresponding to the user set to obtain analysis results.

10. The device according to claim 7 or 8, characterized in that The analysis module comprises: A page view determination unit, configured to determine the page views of each page corresponding to the item to be analyzed and the candidate item, respectively, based on the historical browsing data; A calculation unit is used to calculate the browsing ratio scores of the user viewing the item to be analyzed and the candidate item according to the page browsing volume to obtain the analysis result.

11. The device according to claim 7 or 8, characterized in that The visual illustrations include one or more of a path flow diagram, a hotspot path diagram, a path funnel diagram, and an item recognition diagram.

12. The device according to claim 11, characterized in that Also includes: A trigger request acquisition module, used to acquire a trigger request sent by a terminal device, wherein the trigger request is generated according to a trigger operation of a preset element in the visual illustration by the user on the terminal device; A feedback information determination module, used to determine the feedback information corresponding to the preset element according to the trigger operation; A feedback module is used to send the feedback information to the terminal device.

13. A data processing device, characterized in that: include: Memory, processor; Memory; a memory for storing instructions executable by the processor; The processor is used to call the program instructions in the memory to execute the method according to any one of claims 1-6.

14. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer-executable instructions, which are used to implement the method according to any one of claims 1 to 6 when executed by a processor.

15. A computer program product comprising: A computer program, characterized in that when the computer program is executed by a processor, it is used to implement the method according to any one of claims 1 to 6.

Images