Data processing method and device, equipment and storage medium

Abstract

The invention provides a data processing method and device, equipment and a storage medium. The method comprises the steps of receiving current question content of a user; determining to-be-selected content according to the current question content, wherein the to-be-selected content comprises at least one of the following items: a to-be-selected display dimension related to the current question content and a to-be-selected relevancy; determining at least one target display dimension, wherein the target display dimension is determined based on a trigger operation of a user for the to-be-selected content; processing the original data according to the at least one target display dimension to obtain target reply content for the current question content; and sending the target reply content to the client, so that the client displays the target reply content to improve the data acquisition efficiency.

Description

Technical Field

[0001] The embodiments of the present application relate to the field of computer technology, and in particular to a data processing method, apparatus, device, and storage medium. Background Art

[0002] When users interact with artificial intelligence (AI) dialogue systems, they can provide personalized services through precise data screening. For example, intelligent customer service can select the best answer based on a user's question; recommendation systems can push relevant content based on user preferences; and in education, AI dialogue systems can select appropriate learning materials based on a student's learning progress.

[0003] At present, AI dialogue systems generally rely entirely on user questions to output continuous answers. Users need to read the complete answers before they can extract the required data fragments. Therefore, there is a problem of low data acquisition efficiency. Summary of the Invention

[0004] The present application provides a data processing method, apparatus, device and storage medium, which can improve data acquisition efficiency.

[0005] In a first aspect, a data processing method is provided, comprising: receiving a user's current question content; determining content to be selected based on the current question content, the content to be selected including at least one of the following: a display dimension to be selected and a relevance to be selected related to the current question content; determining at least one target display dimension, the target display dimension being determined based on a user's trigger operation for the content to be selected; processing raw data according to at least one target display dimension to obtain target reply content for the current question content; and sending the target reply content to a client so that the client displays the target reply content.

[0006] In a second aspect, a data processing method is provided, including: obtaining the user's current question content; receiving and displaying content to be selected, the content to be selected including at least one of the following: a display dimension to be selected and a relevance to be selected related to the current question content, and the content to be selected is determined based on the current question content; in response to the user's trigger operation on the content to be selected, sending the content corresponding to the trigger operation in the content to be selected to a server, so that the server determines at least one target display dimension according to the content corresponding to the trigger operation and processes the original data according to the at least one target display dimension to obtain a target reply content for the current question content; receiving and displaying the target reply content.

[0007] According to a third aspect, a data processing device is provided, including: a content receiving module for receiving a user's current question content; a content determination module for determining content to be selected based on the current question content, the content to be selected including at least one of the following: a display dimension to be selected and a relevance to be selected related to the current question content; a dimension determination module for determining at least one target display dimension, the target display dimension being determined based on a user's trigger operation for the content to be selected; a data processing module for processing raw data according to at least one target display dimension to obtain target reply content for the current question content; and a content sending module for sending the target reply content to a client so that the client displays the target reply content.

[0008] In a fourth aspect, a data processing device is provided, including: a content acquisition module, used to: acquire the user's current question content; a receiving and display module, used to: receive and display content to be selected, the content to be selected includes at least one of the following: a display dimension to be selected and a relevance to be selected related to the current question content, and the content to be selected is determined based on the current question content; a response sending module, used to: respond to the user's trigger operation on the content to be selected, and send the content corresponding to the trigger operation in the content to be selected to the server, so that the server determines at least one target display dimension according to the content corresponding to the trigger operation and processes the original data according to the at least one target display dimension to obtain the target reply content for the current question content; a content display module, used to: receive and display the target reply content.

[0009] In a fifth aspect, an electronic device is provided, comprising: a processor and a memory, wherein the memory is used to store a computer program, and the processor is used to call and run the computer program stored in the memory to execute the method as in the first aspect or its various implementations.

[0010] In a sixth aspect, a computer-readable storage medium is provided for storing a computer program, wherein the computer program enables a computer to execute the method as in the first aspect or its various implementations.

[0011] In a seventh aspect, a computer program product is provided, comprising computer program instructions, which enable a computer to execute the method as in the first aspect or its various implementations.

[0012] In an eighth aspect, a computer program is provided, which enables a computer to execute the method in the first aspect or its various implementations.

[0013] In summary, the present application can first determine the content to be selected based on the keywords in the user's current question content, including at least one of the display dimensions to be selected and the relevance to be selected related to the keywords. Then, the display dimensions can be determined based on the user's trigger operation on the content to be selected. Finally, the original data can be processed according to the display dimensions to obtain the reply content for the current question content. In this process, the display dimensions can be determined according to the user's selection, and then the original data can be processed according to the display dimensions to obtain the final reply content, thereby ensuring that the reply content can accurately meet the user's needs and solving the problem that the user needs to read the complete answer content before extracting the required data fragments. Therefore, the data acquisition efficiency can be improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] The following is an introduction to the drawings required for describing the embodiments.

[0015] Figure 1 A flowchart of a data processing method provided in an embodiment of the present application;

[0016] Figure 2 A schematic diagram of a data processing method provided in an embodiment of the present application;

[0017] Figure 3 A schematic diagram of another data processing method provided in an embodiment of the present application;

[0018] Figure 4A A schematic diagram of another data processing method provided in an embodiment of the present application;

[0019] Figure 4B A schematic diagram of another data processing method provided in an embodiment of the present application;

[0020] Figure 4C A schematic diagram of another data processing method provided in an embodiment of the present application;

[0021] Figure 5 A flowchart of another data processing method provided in an embodiment of the present application;

[0022] Figure 6 A schematic diagram of a data processing device 600 provided in an embodiment of the present application;

[0023] Figure 7 A schematic diagram of another data processing device 700 provided in an embodiment of the present application;

[0024] Figure 8 Schematic diagram of an electronic device 800 provided in an embodiment of the present application. DETAILED DESCRIPTION

[0025] The technical solution of this application will be introduced below in conjunction with the drawings in this application.

[0026] It should be noted that the information, data (including, but not limited to: data used for analysis, stored data, displayed data, etc., such as the current question content, content to be selected, display dimensions, original data and reply content, etc.) and signals involved in this application are all authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with the relevant laws, regulations and standards of the relevant countries and regions. For example, the question content and original data involved in this application, as well as the operations performed on the question content and original data, are all obtained with full authorization.

[0027] In one embodiment, the technical solution of this application can be used in data interaction scenarios. For example, it can be applied to AI dialogue scenarios, but is not limited to such scenarios. In this scenario, the AI ​​dialogue system can obtain the content of the user's question and determine and display the reply content based on the user's question content.

[0028] For example, a user's question might be a request for business data, such as sales figures for a particular brand. The response might be structured data representing sales figures obtained by processing the original data into display dimensions such as stores, positions, regions, and personnel. Specifically, this might be a tree-like table or tree diagram, but is not limited thereto. The original data might include historical responses to previous user questions, such as unstructured text content related to sales figures, or data in a database storing sales figures.

[0029] For another example, the question content and the reply content may also be content related to product parameters, or content related to product recommendations (eg, information push, learning material recommendations), but are not limited thereto.

[0030] In one embodiment, the solution provided by the present application can be executed by any terminal device and server with data processing capabilities, for example: the server can be an independent physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server that provides cloud computing services; the terminal device can be a tablet computer, a laptop computer or a desktop computer, etc.

[0031] The following is an introduction to various embodiments of the technical solution of this application:

[0032] It should be noted that all technical solutions in this application can be combined in any way to form optional embodiments of this application, which will not be described one by one here.

[0033] The following first introduces the data processing method involved in this application from the server perspective.

[0034] Figure 1 This is a flow chart of a data processing method provided in an embodiment of the present application, which can be executed by the server in the above content. Figure 1 As shown, the method includes:

[0035] S110: Receive the user's current question content;

[0036] S120: Determine content to be selected based on the current question content, where the content to be selected includes at least one of the following: a display dimension to be selected and a relevance to be selected related to the current question content;

[0037] S130: Determine at least one target display dimension, where the target display dimension is determined based on a triggering operation of the user on the content to be selected;

[0038] S140: Processing the original data according to at least one target display dimension to obtain target response content for the current question content;

[0039] S150: Send the target reply content to the client, so that the client displays the target reply content.

[0040] Regarding S110, in one embodiment, the user can input the current question content based on the client installed on the terminal device, wherein the client can be a client with AI dialogue function; then, the terminal device can obtain the current question content, and then, the terminal device can send the current question content to the server, so that the server can receive the user's current question content.

[0041] For example, the current question may be a request for a summary display of historical responses (i.e., responses to historical questions). Accordingly, the original data corresponding to this situation may be historical conversations, specifically historical responses within the historical conversations. The historical responses may be content determined based on data in the original database.

[0042] For example, Figure 2 As shown in (a) in the figure, the current question content may be "The above sales data is too much. Is there a way to combine the above data into a set of structurally related data for display?" The historical reply content corresponding to the current question content may be sales data. For example, Figure 3 As shown in (a), the current question content may be "There are too many sales data above. Is there any way for me to select sales-related data for analysis?" The historical response content corresponding to the current question content may be sales data.

[0043] For example, the current question content may be a request for data summary display of specific data. Accordingly, the original data corresponding to this situation may be specific data, and the specific data may be stored in the original database.

[0044] For example, the current question content may be “Please display the sales data” or “Please display the sales data with a structural relationship”, or the current question content may also be “Please analyze the sales-related data”.

[0045] In one embodiment, after receiving the current question content, the server can trigger a determination as to whether the conversation content contains a data sample (i.e., original data). If it is determined that the conversation content contains a data sample, S120 is executed; if it is determined that the conversation content does not contain a data sample, the current process is terminated.

[0046] In addition, after determining that the conversation content does not contain data samples, the server may send a prompt message to the terminal device, so that the terminal device prompts the user that the historical conversation is missing or the data sample is missing in the historical conversation.

[0047] Through this, the server can retrieve user questions and perform subsequent actions based on them, processing the original data to determine the response content and enabling real-time interaction with the user. Furthermore, the server can first determine whether the historical conversation content contains original data, avoiding the possibility that subsequent steps cannot be executed due to missing original data.

[0048] Regarding S120, in one embodiment, determining the content to be selected based on the current question content may include the following situations, but is not limited thereto:

[0049] Scenario 1: In response to the current question content involving multiple display dimensions in the original data, it is determined that the content to be selected is multiple display dimensions.

[0050] Scenario 2: In response to the current question content involving a specified display dimension in the original data, the content to be selected is determined to be the relevance to be selected.

[0051] Specifically, the server may first extract keywords from the current question content and, based on the keywords, determine whether the current question content involves multiple display dimensions or a specified display dimension in the original data. Specifically, if the keywords involve multiple display dimensions in the original data, then the current question content is determined to involve multiple display dimensions in the original data; if the keywords involve a specified display dimension in the original data, then the current question content is determined to involve the specified display dimension in the original data.

[0052] For example, the keywords for the current question "The above sales data are too much. Is there a way to combine the above data to form a set of structurally related data for display?" can be "the above data" and "combine to form", which determines that the current question involves multiple display dimensions in the original data.

[0053] For another example, the keywords for the current question "There are too many sales data above. Is there any way for me to select sales-related data for analysis?" may be "sales" and "related data", which determines that the current question involves the specified display dimension "sales" in the original data.

[0054] For scenario one, in one embodiment, the server may query multiple display dimensions in the original data through a Structured Query Language (SQL) statement (or, may obtain multiple display dimensions in the original data through keyword extraction), and determine that the content to be selected contains the display dimensions to be selected, determine that the display dimensions to be selected are multiple display dimensions in the original data, or determine that the display dimensions to be selected are multiple display dimensions involved in the current question content in the original data (specifically, the display dimensions involved in its keywords).

[0055] The multiple display dimensions in the original data may be field names stored in the corresponding database. For example, if the fields stored in the corresponding database for the original data are store, company, position, and region, then the multiple display dimensions in the original data may be determined to be store, company, position, and region.

[0056] For example, the server may determine that the data to be selected is the following display dimensions in the sales data in the historical conversation: store, company, position, region, and personnel. Then, the server may send the display dimensions to be selected to the terminal device, such as Figure 2 As shown in (b), the terminal device can display the selected data.

[0057] For situation two, in one embodiment, the relevance to be selected may include at least one of the following: a relevance randomly generated by the server, and a relevance between multiple preset display dimensions in the original data and the specified display dimension (this application will explain the calculation process of this relevance in subsequent embodiments), but is not limited to this.

[0058] The correlation may be in the form of a percentage or a numerical value, but is not limited thereto.

[0059] For example, the server may determine the data to be selected as the following relevances to be selected: 100%, 90%, ..., 0%, and then the server may send the relevances to be selected to the terminal device, such as Figure 3As shown in (b) of FIG, the terminal device may display the relevance to be selected. The darker the color of the box to be selected, the higher the relevance to the specified display dimension.

[0060] In addition, the data to be selected may also include the display dimensions to be selected and the relevance to be selected. Accordingly, the terminal device may display the display dimensions to be selected and the relevance to be selected at the same time.

[0061] Through the above content, users can be provided with display dimensions and relevance to be selected that are related to the question content. This not only avoids the need for users to use complex natural language to describe their needs in detail, simplifies user input, and improves user interaction experience, but also improves the accuracy of describing the question content, thereby improving the accuracy of the reply content.

[0062] Regarding S130, in one embodiment, determining at least one target display dimension includes, but is not limited to, the following situations:

[0063] In case 1, a display dimension triggered by a user in a display dimension to be selected is received to obtain a target display dimension. Case 1 corresponds to the above-mentioned case 1.

[0064] It should be noted that the trigger operations and other operations in this application can be specifically single-clicking, double-clicking, pressing, dragging to a designated area or floating touch gestures, etc., and this application does not impose any restrictions on this.

[0065] For example, Figure 2 As shown in (c) and (d) in the figure, the user can click on "store" and "personnel", or "store", "region" and "personnel" in the selected display dimensions based on the terminal device, so that the terminal device can determine "store" and "personnel", or "store", "region" and "personnel" as the target display dimensions, and send them to the server, so that the server can obtain the target display dimensions.

[0066] In the second scenario, a user triggers a relevance in the selected relevances to obtain a target relevance; and a relevance between keywords in the current question and the multiple preset display dimensions is determined as a preset display dimension with the target relevance, obtaining at least one target display dimension. This scenario corresponds to the second scenario above.

[0067] In addition, the terminal device may also display a relevance input box, in which the user may input the relevance to be selected, so that the server may receive the relevance to be selected input by the user from the terminal device and obtain the target relevance.

[0068] For example, Figure 2As shown in (c), (d) and (e) in the figure, the user can click on "100%", "100%" and "90%" or "100%", "90%" and "80%" in the relevance to be selected based on the terminal device, so that the terminal device can determine that the relevance to be selected that the user clicked on is the target relevance, and send it to the server, so that the server can obtain the target relevance.

[0069] Exemplarily, the preset display dimensions may be multiple display dimensions in the original data, but are not limited thereto. In conjunction with the above embodiment, the keywords of the current question content may be the specific data targeted by the current question content in the above embodiment, and the specific data may be a display dimension, specifically a designated display dimension in the above embodiment.

[0070] For example, the server can first process the raw data into a structured table, where the fields in the table correspond to multiple preset display dimensions. The multiple preset display dimensions can then be standardized. For example, the preset display dimension "sales" can be standardized to "sales," the preset display dimension "number of stores" can be standardized to "stores," and the preset display dimension "staff" can be standardized to "staff." Next, the correlation between the preset display dimensions and the keywords can be quantitatively calculated. For example, the correlation between the preset display dimensions and the keywords can be calculated using the Pearson correlation coefficient.

[0071] For example, the server may first search for specific values ​​of the preset display dimensions and keywords in a structured table; then, based on the corresponding specific values, the server may calculate the correlation between the preset display dimensions and keywords based on formula (1).

[0072]

[0073] Among them, ρXY represents the correlation between the preset display dimension and the keyword, X and Y represent the specific values ​​of the preset display dimension and the keyword respectively, μx and μy represent the mean of the specific values ​​of the preset display dimension and the keyword respectively, σX and σY represent the standard deviation of the preset display dimension and the keyword respectively, and cov(X, Y) represents the covariance of the preset display dimension and the keyword.

[0074] Next, the server may output a relevance list as shown in Table 1 according to the corresponding standardized names and relevance, wherein a preset display dimension and a keyword or two preset display dimensions may constitute a display dimension pair.

[0075] Table 1

[0076] Display dimension Relevance Display priority sales-stores 0.92(92％) 1 sales-staff 0.75(75％) 2

[0077] The server can then determine the relevance of multiple preset display dimensions to the keyword based on the relevance list. Furthermore, the server can use the relevance in the relevance list as the relevance to be selected. The server can then determine the preset display dimension corresponding to the target relevance triggered by the user, or the preset display dimension corresponding to the relevance closest to the target relevance, as the target display dimension.

[0078] Through the above content, users can be provided with data selection, and then the target display dimension can be determined according to the user's selection, thereby determining the data that needs to be structured and assembled for the original data. Moreover, the determined target display dimension is related to the current question data and can better meet user needs. Therefore, it can be further ensured that the generated response data is more in line with user needs, thereby improving data interaction efficiency.

[0079] Regarding S140 , in one embodiment, in combination with the above content, the original data may come from at least one of the following: historical conversation content, and an original database.

[0080] In one embodiment, the server's processing of the raw data may specifically generate structured data, and accordingly, the target response content obtained is structured data. For example, it may be a table, a tree diagram, etc., but is not limited thereto. The nodes in the tree diagram and the fields in the table may be consistent with the target display dimensions.

[0081] The following describes S140 in conjunction with Case 1 and Case 2 in the above embodiment:

[0082] For situation one, the server may first determine the sorting sequence number of at least one target display dimension; then, according to the at least one sorting sequence number and the at least one target display dimension, the server may perform structured data processing on the original data to obtain target response content.

[0083] For example, before determining the sorting sequence number for the target display dimension, the server may first determine target data content in the original data for which the similarity between the data content in the first target display dimension or the second target display dimension is greater than a preset similarity, for either the first target display dimension or the second target display dimension. The target data content in the first target display dimension and the second target display dimension may then be merged. This allows for deduplication of the same data within the same display dimension, thereby improving the accuracy of the response content.

[0084] For example, the server can first parse the original data to determine the target display dimension in the original data and its corresponding data content, that is, the specific value. For example, if the original data is a raw data table, the target display dimension can be a field in the raw data table, and its specific value can be a field value, specifically a field value of a discrete attribute. Then, the server can remove duplicates and merge the target display dimension and its corresponding specific value by merging duplicate edge records (specifically, this can be achieved through edge merging in graph data modeling). Specifically, the first target display dimension can be determined as the starting point and the second target display dimension can be determined as the end point. The edge between the end point and the starting point can correspond to the data content under the first target display dimension and the second target display dimension. Then, the feature similarity under the same starting point and end point can be calculated. The feature similarity refers to the similarity between the data content under the first target display dimension or the second target display dimension. Then, the edges with feature similarity greater than the preset similarity can be merged. The preset similarity can be 80%.

[0085] For example, assuming that the first target display dimension or the second target display dimension is name and sales respectively, the data content 11 under the first target display dimension is "admin", and the corresponding data content 12 under the second target display dimension is "20", and the data content 21 under the first target display dimension is "Admin", and the corresponding data content 22 under the second target display dimension is "30". If it is determined that the similarity between "admin" and "Admin" is greater than 80%, the data content 11 and data content 21, and the data content 12 and data content 22 can be merged to obtain the new data content: the data content under the first target display dimension is "admin" or "Admin", and the corresponding data content under the second target display dimension is "50".

[0086] Exemplarily, the server may determine the sorting sequence of the target display dimension in the following manner, but not limited thereto: determining the frequency of occurrence of at least one target display dimension in the original data and the corresponding number of data content types; determining a weight value of at least one target display dimension based on each frequency of occurrence and each number of data content types; and determining the order of the size of at least one weight value as the sorting sequence of at least one target display dimension.

[0087] For example, assuming that the target display dimensions include: region, store, and personnel, the server can count the number of non-empty values ​​corresponding to each target display dimension in the original data, that is, the number of non-empty data contents, to obtain the frequency of occurrence of the target display dimension in the original data; then, the server can count the number of data content types of the target display dimension in the original data. For example, if there are 8 regions in the original data, it can be determined that the number of data content types of the region is 8; then, the number of data contents under each target display dimension in the original data is determined to obtain the total number of samples of the target display dimension. Finally, the weight value of each target display dimension can be calculated according to the following formula: weight value = occurrence frequency / (number of data content types * total number of samples) to obtain the sorting sequence number of each target display dimension as shown in Table 2.

[0088] Table 2

[0089]

[0090] Exemplarily, the server may first determine the level number corresponding to each of the at least one target display dimensions based on at least one sorting sequence number; and perform structured data processing on the original data based on the at least one level number to obtain target response content based on a tree structure.

[0091] For example, the server may determine the sorting number as the layer number of the target display dimension, or may determine the layer of the target display dimension whose sorting number is a preset percentage (e.g., 10%) before all sorting numbers as the parent layer, and determine the target display dimensions corresponding to the remaining sorting numbers (the sorting numbers are not the preset percentage before all sorting numbers) in descending order of the sorting numbers as the sub-layer numbers of the child nodes (specifically, this may be dynamically generated, for example, and updated in real time based on updates in the frequency of occurrence, etc.). At the same time, the server may determine the identifier of the field value combination corresponding to the two target display dimensions (i.e., the data content under the two target display dimensions) based on SHA-256 (specifically, this may be obtained by hashing the fused feature using SHA-256, and the fused feature may be obtained based on the data content under the two target display dimensions) to obtain the field value combination identifier. Then, the server may construct a partition map based on the layer number and the field value combination identifier. For example, the layer map may include three fields: a parent layer number (parent_layer), a child layer number (child_layer), and a field value combination identifier (feature_hash). Then, according to the hierarchical mapping table, the following Figure 2 The tree-structured tables shown in (c) and (d) are the target reply contents. The data contents corresponding to the child nodes may be data that has not been updated or newly added within the last preset number of days, such as 30 days.

[0092] For the second scenario, the server may first determine the display priority of each of the at least one target display dimension; then, based on the at least one display priority and the at least one target display dimension, perform structured data processing on the original data to obtain target response content.

[0093] Exemplarily, in combination with the above embodiment, the order of the relevance between at least one target display dimension and the keyword may be correspondingly determined as at least one display priority.

[0094] For example, when the original data is structured according to the display priority, the target display dimension with high relevance can be displayed on the left, generating the following Figure 3 The front-end visualization table shown in (c), (d) or (e) is the target reply content.

[0095] Through the above content, a structured display of data associations and combinations across different display dimensions can be achieved. Since each display dimension is determined from the question data and is selected by the user, it not only better meets user needs, but also ensures that the resulting response content is consistent with the user's question, ensuring comprehensive, complete, and highly relevant responses to user questions in any situation. Furthermore, since the response data is structured, the data presentation format is relatively clear, making it easier for users to accurately locate the information they need and meeting their needs for quick data analysis scenarios. This effectively improves the usability of data analysis in dialog boxes, provides users with more reliable data support and analysis basis, and improves user work efficiency and quality.

[0096] Moreover, multi-scenario display and analysis of data can be realized. For example, the above situation one can realize comparative analysis of data. Specifically, separated data can be combined into structured data through structural combination to help users understand the data more clearly; the above situation two can realize correlation relationship analysis of data. Specifically, the correlation display of different display dimensions can be used to allow users to quickly select relevant data to form a data table, thereby helping users analyze the root cause relationship of the data.

[0097] The following is an introduction to the above content with the help of a schematic diagram:

[0098] In one embodiment, in combination with the above, Figure 4AAs shown, you can first obtain the conversation query keywords, that is, the keywords in the user's current question content. Then, if it is determined based on the historical conversation that there is no data sample, that is, it is determined that there is no historical conversation, then you can skip the subsequent embodiments; if it is determined based on the historical conversation that there is a data sample, that is, it is determined that there is a historical conversation, then you can determine how many display dimensions the current question content involves (specifically, you can determine how many display dimensions the current question content involves in the historical conversation based on the keywords in the current question content). If the current question content involves multiple display dimensions, then execute Figure 4B If the current question does not involve multiple display dimensions (for example, it involves one display dimension), execute Figure 4C The process in .

[0099] Specifically, such as Figure 4B As shown, the server can search the database for fields that are the same as the sample data (for example, multiple display dimensions involved in historical conversations). If it is not found, the subsequent steps will not be executed; if it is found, all sample fields will be displayed. Then, the fields selected by the user, namely the display dimensions, can be obtained, and they can be sorted in order according to the frequency of occurrence to establish a tree-structured display data (for example, the display dimension with the highest frequency of occurrence is in the first layer of the tree-structured display data, for example, the first column of the list), that is, a reply to the current question content. After obtaining the display dimension selected by the user, the server can parse the metadata corresponding to the display dimension to parse the original data corresponding to the display dimension, use the display dimension as a node, and the data content under the display dimension as the original edge, and perform duplicate edge merging processing (based on EdgeAttr.duplicates (the duplicate attribute of the edge, indicating that there are multiple edges with the same node)) to achieve data deduplication. Then, according to the above embodiment, frequency statistics can be performed on each display dimension to calculate its hierarchical weight, that is, weight data, to obtain an adjacency table as shown in Table 2 above. Then, the hierarchical mapping table in the above embodiment can be generated based on the adjacency table (which can be implemented based on the Partition Map), and a data map with a tree structure, that is, display data with a tree structure, can be generated accordingly.

[0100] Specifically, such as Figure 4CAs shown, the server can calculate the relevance of multiple display dimensions to a display dimension involved in the current conversation (for example, the server can first search for multiple dimension nodes, i.e., display dimensions, in the database, and then determine the dimension identifier of the display dimension, i.e., the dimension identifier after standardization, and perform value distribution statistics and correlation sorting on the display dimension based on the Pearson correlation coefficient to obtain the correlation sorting result in the form of a matrix), and display the optional relevance according to the level of relevance. Then, the relevance selected by the user can be obtained, and data can be displayed according to the relevance (the displayed data can be data under the display dimension with a relevance of the display dimension involved in the current conversation. Specifically, the server can determine and display the display dimension corresponding to the relevance, and match the corresponding dimension value, i.e., the data content, according to its standardized dimension identifier; and display the data content in a table), that is, reply to the current conversation.

[0101] The following describes the data processing method involved in this application from the perspective of a terminal device.

[0102] Figure 5 This is a flow chart of another data processing method provided in an embodiment of the present application, which can be executed by the terminal device in the above content. Figure 5 As shown, the method includes:

[0103] S510: Obtain the current question content of the user;

[0104] S520: Receive and display content to be selected, where the content to be selected includes at least one of the following: a display dimension to be selected and a relevance to be selected related to the current question content, and the content to be selected is determined based on the current question content;

[0105] S530: In response to a user triggering an operation on the to-be-selected content, the content corresponding to the triggering operation in the to-be-selected content is sent to the server, so that the server determines at least one target display dimension based on the content corresponding to the triggering operation and processes the raw data based on the at least one target display dimension to obtain target reply content for the current question content;

[0106] S540: Receive and display the target reply content.

[0107] It should be noted that the corresponding embodiments on the server side and the terminal device side can refer to each other. To avoid repetition, this application will not go into details.

[0108] Figure 6 A schematic diagram of a data processing device 600 provided in an embodiment of the present application is shown as follows: Figure 6As shown, the device 600 includes: a content receiving module 601, a content determining module 602, a dimension determining module 603, a data processing module 604, a content sending module 605, a content selecting module 606, and a data merging module 607.

[0109] In one embodiment, the content receiving module 601 is used to receive the user's current question content; the content determination module 602 is used to determine the content to be selected based on the current question content, and the content to be selected includes at least one of the following: a display dimension to be selected and a relevance to be selected related to the current question content; the dimension determination module 603 is used to determine at least one target display dimension, and the target display dimension is determined based on the user's trigger operation for the content to be selected; the data processing module 604 is used to process the original data according to at least one target display dimension to obtain the target reply content for the current question content; the content sending module 605 is used to send the target reply content to the client so that the client displays the target reply content.

[0110] Exemplarily, the content determination module 602 is specifically used to: determine that the content to be selected is multiple display dimensions in response to the current question content involving multiple display dimensions in the original data; or, determine that the content to be selected is the relevance to be selected in response to the current question content involving a specified display dimension in the original data.

[0111] Exemplarily, the dimension determination module 603 is specifically configured to receive a display dimension triggered by a user in the display dimensions to be selected, and obtain a target display dimension.

[0112] Exemplarily, the data processing module 604 is specifically configured to: determine a sorting sequence number of at least one target display dimension; and perform structured data processing on the original data according to the at least one sorting sequence number and the at least one target display dimension to obtain target reply content.

[0113] Exemplarily, the content selection module 606 is used to: for any first target display dimension and second target display dimension in at least one target display dimension, determine target data content whose similarity between the data content in the first target display dimension or the second target display dimension in the original data is greater than a preset similarity; the data merging module 607 is used to merge the target data content in the first target display dimension and the second target display dimension.

[0114] Exemplarily, the data processing module 604 is specifically used to: determine the frequency of occurrence of at least one target display dimension in the original data and the corresponding number of data content types; determine the weight value of at least one target display dimension based on each frequency of occurrence and each number of data content types; and determine the order of the size of at least one weight value as the sorting number of at least one target display dimension.

[0115] Exemplarily, the data processing module 604 is specifically used to: determine the level number corresponding to at least one target display dimension according to at least one sorting sequence number; perform structured data processing on the original data according to at least one level number to obtain target response content based on a tree structure.

[0116] Exemplarily, the dimension determination module 603 is specifically used to: receive the relevance of the user's trigger operation in the relevance to be selected, and obtain the target relevance; determine the preset display dimension whose relevance with the keywords of the current question content is the target relevance among multiple preset display dimensions, and obtain at least one target display dimension.

[0117] Exemplarily, the data processing module 604 is specifically configured to: determine the display priority of each of at least one target display dimension; and perform structured data processing on the original data according to the at least one display priority and the at least one target display dimension to obtain target reply content.

[0118] Exemplarily, the data processing module 604 is specifically configured to determine the order of relevance between at least one target display dimension and the keyword as at least one display priority.

[0119] Exemplarily, the original data comes from at least one of the following: historical conversation content, and an original database.

[0120] It should be understood that the device embodiment and the method embodiment may correspond to each other, and similar descriptions may refer to the method embodiment. To avoid repetition, they will not be described here. Specifically, Figure 6 The device 600 shown can execute the above method embodiment, and the above and other operations and / or functions of each module in the device 600 are respectively for implementing the corresponding processes in the above method, which will not be repeated here for the sake of brevity.

[0121] Figure 7 A schematic diagram of a data processing device 700 provided in an embodiment of the present application is shown as follows: Figure 7 As shown, the device 700 includes: a content acquisition module 701, a receiving and displaying module 702, a response sending module 703, and a content display module 704.

[0122] In one embodiment, the content acquisition module 701 is used to: acquire the user's current question content; the receiving and displaying module 702 is used to: receive and display the content to be selected, and the content to be selected includes at least one of the following: a display dimension to be selected and a relevance to be selected related to the current question content, and the content to be selected is determined based on the current question content; the response sending module 703 is used to: respond to the user's trigger operation on the content to be selected, and send the content corresponding to the trigger operation in the content to be selected to the server, so that the server determines at least one target display dimension according to the content corresponding to the trigger operation and processes the original data according to the at least one target display dimension to obtain the target reply content for the current question content; the content displaying module 704 is used to: receive and display the target reply content.

[0123] Exemplarily, the original data comes from at least one of the following: historical conversation content, and an original database.

[0124] Exemplarily, the target response content is structured data.

[0125] It should be understood that the device embodiment and the method embodiment may correspond to each other, and similar descriptions may refer to the method embodiment. To avoid repetition, they will not be described here. Specifically, Figure 7 The device 700 shown can execute the above method embodiment, and the above and other operations and / or functions of each module in the device 700 are respectively for implementing the corresponding processes in the above method, which will not be repeated here for the sake of brevity.

[0126] The apparatus of the embodiment of the present application is described above from the perspective of functional modules in conjunction with the accompanying drawings. It should be understood that the functional module can be implemented in hardware form, can be implemented by instructions in software form, or can be implemented by a combination of hardware and software modules. Specifically, the steps of the method embodiment in the embodiment of the present application can be completed by the hardware integrated logic circuit and / or software form instructions in the processor, and the steps of the method disclosed in the embodiment of the present application can be directly embodied as being executed by a hardware decoding processor, or can be executed by a combination of hardware and software modules in the decoding processor. Optionally, the software module can be located in a mature storage medium in the art such as a random access memory, a flash memory, a read-only memory, a programmable read-only memory, an electrically erasable programmable memory, a register, etc. The storage medium is located in the memory, and the processor reads the information in the memory and completes the steps in the above method embodiment in conjunction with its hardware.

[0127] Figure 8 A schematic diagram of an electronic device 800 provided in an embodiment of the present application.

[0128] like Figure 8 As shown, the electronic device 800 may include:

[0129] The memory 810 and the processor 820 are configured to store computer programs and transmit the program code to the processor 820. In other words, the processor 820 can call and run the computer program from the memory 810 to implement the method in the embodiment of the present application.

[0130] For example, the processor 820 may be configured to execute the above method embodiments according to instructions in the computer program.

[0131] In some embodiments of the present application, the processor 820 may include but is not limited to:

[0132] General-purpose processor, digital signal processor (DSP), application-specific integrated circuit (ASIC), field-programmable gate array (FPGA) or other programmable logic device, discrete gate or transistor logic device, discrete hardware components, etc.

[0133] In some embodiments of the present application, the memory 810 includes but is not limited to:

[0134] Volatile memory and / or non-volatile memory. Non-volatile memory can be read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), or flash memory. Volatile memory can be random access memory (RAM), which is used as an external cache. By way of example and not limitation, many forms of RAM are available, such as static random access memory (SRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access memory (DDR SDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous link dynamic random access memory (SL DRAM), and direct RAM bus random access memory (DR RAM).

[0135] In some embodiments of the present application, the computer program may be divided into one or more modules, which are stored in the memory 810 and executed by the processor 820 to implement the method provided by the present application. The one or more modules may be a series of computer program instruction segments capable of implementing specific functions, and the instruction segments are used to describe the execution process of the computer program in the electronic device.

[0136] like Figure 8 As shown, the electronic device may further include:

[0137] The transceiver 830 may be connected to the processor 820 or the memory 810 .

[0138] The processor 820 may control the transceiver 830 to communicate with other devices. Specifically, the processor 820 may send information or data to other devices or receive information or data sent by other devices. The transceiver 830 may include a transmitter and a receiver. The transceiver 830 may further include one or more antennas.

[0139] It should be understood that the various components in the electronic device are connected via a bus system, wherein the bus system includes not only a data bus but also a power bus, a control bus and a status signal bus.

[0140] The present application also provides a computer storage medium having a computer program stored thereon, which, when executed by a computer, enables the computer to perform the method of the above-mentioned method embodiment. In other words, the present application also provides a computer program product containing instructions, which, when executed by a computer, enables the computer to perform the method of the above-mentioned method embodiment.

[0141] When software is used to implement, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instruction is loaded and executed on a computer, the computer can be made to perform the corresponding flow in each method in the embodiment of the present application, generate the function that each method in the embodiment of the present application can realize in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instruction can be stored in a computer-readable storage medium, or transmitted from a computer-readable storage medium to another computer-readable storage medium. For example, the computer instruction can be transmitted from a website, computer, server, or data center by wired (such as coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (such as infrared, wireless, microwave, etc.) mode to another website, computer, server, or data center. The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server, a data center, etc. that includes one or more available media integrations. The available medium may be a magnetic medium (eg, a floppy disk, a hard disk, a magnetic tape), an optical medium (eg, a digital video disc (DVD)), or a semiconductor medium (eg, a solid state disk (SSD)).

[0142] Those skilled in the art will appreciate that the modules and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0143] In the several embodiments provided in this application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the system embodiments described above are merely illustrative. For example, the division of the modules is merely a logical function division. In actual implementation, there may be other division methods, such as multiple modules or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, and the indirect coupling or communication connection of the system, device or module can be electrical, mechanical or other forms.

[0144] Modules described as separate components may or may not be physically separate, and components displayed as modules may or may not be physical modules, i.e., they may be located in one place or distributed across multiple network elements. Some or all of the modules may be selected based on actual needs to achieve the purpose of the present embodiment. For example, the functional modules in the various embodiments of the present application may be integrated into a processing module, or each module may exist physically separately, or two or more modules may be integrated into a single module.

Claims

1. A data processing method, characterized in that: include: Receive the user's current question content; Determine the content to be selected based on the current question content, where the content to be selected includes at least one of the following: a display dimension to be selected and a relevance to be selected related to the current question content; determining at least one target display dimension, where the target display dimension is determined based on a triggering operation of the user on the content to be selected; Processing the original data according to the at least one target display dimension to obtain target response content for the current question content; The target reply content is sent to the client, so that the client displays the target reply content.

2. The method according to claim 1, characterized in that The determining of the content to be selected according to the current question content includes: In response to the current question content involving multiple display dimensions in the original data, determining that the content to be selected is the multiple display dimensions; or, In response to the current question content being related to a specified display dimension in the original data, the content to be selected is determined to be the relevance to be selected.

3. The method according to claim 1, characterized in that The determining of at least one target display dimension includes: The display dimension triggered by the user in the display dimension to be selected is received to obtain the target display dimension.

4. The method according to claim 3, characterized in that The processing of the original data according to the at least one target display dimension to obtain target response content for the current question content includes: Determining a sort order of each of the at least one target display dimension; According to at least one of the sorting numbers and the at least one target display dimension, structured data processing is performed on the original data to obtain the target reply content.

5. A data processing method, characterized in that: include: Get the user's current question content; Receive and display content to be selected, the content to be selected including at least one of the following: a display dimension to be selected and a relevance to be selected related to the current question content, the content to be selected being determined based on the current question content; In response to the user's triggering operation on the content to be selected, sending the content corresponding to the triggering operation in the content to be selected to the server, so that the server determines at least one target display dimension based on the content corresponding to the triggering operation and processes the raw data according to the at least one target display dimension to obtain target reply content for the current question content; Receive and display the target reply content.

6. A data processing device, characterized in that: include: The content receiving module is used to: receive the current question content of the user; A content determination module is configured to determine content to be selected based on the current question content, wherein the content to be selected includes at least one of the following: a display dimension to be selected and a relevance to be selected related to the current question content; a dimension determination module, configured to: determine at least one target display dimension, wherein the target display dimension is determined based on a triggering operation of the user on the content to be selected; A data processing module is configured to process the original data according to the at least one target display dimension to obtain target response content for the current question content; The content sending module is used to send the target reply content to the client so that the client displays the target reply content.

7. A data processing device, characterized in that: include: Content acquisition module, used to: obtain the user's current question content; a receiving and displaying module, configured to receive and display content to be selected, wherein the content to be selected includes at least one of the following: a display dimension to be selected and a relevance to be selected related to the current question content, wherein the content to be selected is determined based on the current question content; a response sending module, configured to: in response to a trigger operation by the user on the content to be selected, send the content corresponding to the trigger operation in the content to be selected to a server, so that the server determines at least one target display dimension based on the content corresponding to the trigger operation and processes the raw data based on the at least one target display dimension to obtain target reply content for the current question content; The content display module is used to receive and display the target reply content.

8. An electronic device, characterized in that: include: processor; as well as a memory for storing executable instructions of the processor; The processor is configured to perform the method according to any one of claims 1 to 5 by executing the executable instructions.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method according to any one of claims 1 to 5 is implemented.

10. A computer program product comprising instructions, characterized in that When the computer program product is run on an electronic device, the electronic device is enabled to execute the method according to any one of claims 1 to 5.

Images