Answer generation method and device, electronic equipment, storage medium and program product
By screening and statistical feature information of multiple data groups, the project management tools automatically handle statistical conditions during statistical events information, realize automated statistics, and improve efficiency.
Patent Information
- Application Number
- CN202411548960.1
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-10-31
- Publication Date
- 2025-01-24
AI Technical Summary
When stating event information, existing project management tools are difficult to automatically deal with diversified statistical conditions, resulting in cumbersome manual counting and inefficient efficiency.
By obtaining the characteristic information of multiple data groups, the relevant data groups are filtered out according to the input question text to form a data set, and the statistical tools corresponding to the question text are used for statistical processing to automatically generate the answer text.
Automatically count event information based on question text, reducing manual counting steps and improving the efficiency of counting event information.
Smart Images
Figure CN119357362A_ABST
Abstract
Description
Technical Field
[0001] The embodiments of the present application relate to the field of intelligent question-answering technology, and in particular, to an answer generation method, device, electronic device, storage medium, and program product. Background Art
[0002] Statistical event information is of great reference significance for the work of relevant personnel. For example, after the vehicle operation and maintenance personnel have obtained the recent case numbers of different models, they can formulate more targeted vehicle after-sales plans for models with a large number of cases.
[0003] At present, each event information is generally stored through a project management tool (for example, in the form of a jira web page). When counting event information, if the project management tool can automatically count according to the statistical conditions of this statistics, the statistical results can be obtained directly. If the project management tool cannot automatically count according to the statistical conditions of this statistics, manual counting is required to obtain the statistical results.
[0004] However, since the main function of project management tools is to track and manage the progress of projects, even project management tools with automatic statistical functions only support automatic provision of statistical results for a relatively small number of statistical conditions. The statistical conditions for actual statistical event information are relatively diverse. Therefore, in most cases, manual counting is required one by one according to the actual statistical conditions to realize statistical event information. This process is very cumbersome and complicated, resulting in low efficiency in statistical event information. Summary of the invention
[0005] In view of this, embodiments of the present application provide an answer generation method, device, electronic device, storage medium and program product to at least partially solve the above problems.
[0006] According to a first aspect of an embodiment of the present application, there is provided an answer generation method, comprising: obtaining a plurality of data groups, wherein the data groups include feature information corresponding to a plurality of feature identifiers, the feature information being information of an event corresponding to the data group in which the feature information is located, and different data groups correspond to different events; based on an input question text, and feature information in the plurality of data groups corresponding to a target identifier in the plurality of feature identifiers, screening out at least some of the data groups from the plurality of data groups to form a first data set, wherein the feature information corresponding to the target identifier is the feature identifier of any preset information corresponding to the target identifier; based on the question text, performing a search with at least some of the data in the first data set as the search range, and determining an answer text corresponding to the question text based on the search result.
[0007] According to a second aspect of an embodiment of the present application, an answer generation device is provided, comprising: an acquisition unit, for acquiring multiple data groups, wherein the data groups include feature information corresponding to multiple feature identifiers, the feature information being information about an event corresponding to the data group where the feature information is located, and different data groups correspond to different events; a screening unit, for screening out at least part of the data groups from the multiple data groups according to an input question text and feature information corresponding to a target identifier in the multiple feature identifiers in the multiple data groups to form a first data set, wherein the feature information corresponding to the target identifier is the feature identifier of any preset information corresponding to the target identifier; a determination unit, for searching according to the question text with at least part of the data in the first data set as the search range, and determining an answer text corresponding to the question text according to the search result.
[0008] According to the third aspect of an embodiment of the present application, there is provided an electronic device comprising: a processor, a memory, a communication interface and a communication bus, wherein the processor, the memory and the communication interface communicate with each other via the communication bus; the memory is used to store at least one executable instruction, and the executable instruction enables the processor to perform operations corresponding to the method of the first aspect described above.
[0009] According to a fourth aspect of an embodiment of the present application, a computer storage medium is provided, on which a computer program is stored, and the program is executed by a processor to perform the method of the first aspect.
[0010] According to a fifth aspect of an embodiment of the present application, a computer program product is provided, comprising computer instructions, wherein the computer instructions instruct a computing device to execute the method of the first aspect described above.
[0011] According to the answer generation scheme provided by the embodiment of the present application, multiple data groups can be obtained, and according to the question text for indicating the acquisition of the statistical results based on the multiple data groups, multiple feature identifiers and the feature information corresponding to the multiple feature identifiers, at least part of the data groups can be screened out from the multiple data groups to form a data set, and then the numerical value obtained by statistical processing based on the data set is obtained according to the question text through the statistical tool corresponding to the question text, and then the answer text including the numerical value is determined according to the numerical value and the question text. Therefore, compared with manually counting one by one according to the actual statistical conditions to realize statistical event information, the present application automatically realizes statistical event information according to the question text and the constructed multiple data groups, and the statistical processing is performed based on the data set obtained after screening the multiple data groups. Compared with the multiple data groups, the data set has less data, which can speed up the processing process of statistical processing, thereby improving the efficiency of statistical event information. BRIEF DESCRIPTION OF THE DRAWINGS
[0012] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in the embodiments of the present application. For ordinary technicians in this field, other drawings can also be obtained based on these drawings.
[0013] Figure 1 is a flow chart of an answer generation method according to an embodiment of the present application;
[0014] Figure 2 is a schematic diagram of an answer generating device according to an embodiment of the present application;
[0015] Figure 3 It is a schematic diagram of an electronic device according to an embodiment of the present application. DETAILED DESCRIPTION
[0016] Application environment of this application
[0017] The embodiment of the present application proposes an answer generation scheme. The entire answer generation scheme is relatively general and can be used to provide users with automatic replies indicating statistical results during the event information statistics process, such as providing after-sales customer service personnel with automatic replies indicating statistical results during vehicle after-sales service. The answer generation scheme can be executed by a data center, a server, a personal computer, an Internet of Things (IoT) device, an embedded device, etc. The answer generation scheme is independent of the hardware deployed by the computing device that executes the scheme.
[0018] Answer generation method
[0019] Based on the above application environment, an embodiment of the present application provides an answer generation method, and the answer generation method is described in detail through multiple embodiments below.
[0020] Figure 1 FIG. 1 is a flow chart of a method for generating an answer according to an embodiment of the present invention. Figure 1 As shown, the answer generation method includes the following steps:
[0021] Step 101: Acquire multiple data groups.
[0022] The data group includes characteristic information corresponding to a plurality of characteristic identifiers, and the characteristic information is information about an event corresponding to the data group where the characteristic information is located, and different data groups correspond to different events.
[0023] In a specific implementation, multiple data groups may be obtained from a database, that is, multiple data groups are stored in the same database, and the database may store data in rows and columns. Specifically, data of the same data group is stored in the same row of the database, and feature information corresponding to the same feature identifier is stored in the same column of the database. Based on this, the feature identifier may be a column name.
[0024] For example, the event is a vehicle after-sales event, and the multiple feature identifiers are respectively an identifier corresponding to the case number (for example, "case number"), an identifier corresponding to the vehicle identification code (for example, "VIN code"), an identifier corresponding to whether it has been resolved (for example, "whether it has been resolved"), an identifier corresponding to the brand (for example, "brand"), an identifier corresponding to the model (for example, "model"), an identifier corresponding to the date (for example, "date"), an identifier corresponding to the problem description (for example, "problem description"), an identifier corresponding to the cause (for example, "cause"), an identifier corresponding to the solution (for example, "solution"), and an identifier corresponding to the event recorder (for example, "event recorder"). Two of the multiple data groups are respectively a data group corresponding to the vehicle after-sales event of vehicle A and a data group corresponding to the vehicle after-sales event of vehicle B. The feature information of the vehicle after-sales event of vehicle A corresponding to the above multiple feature identifiers are respectively 01, CC0CCCC0011111111 (that is, the specific vehicle identification code of vehicle A), yes, D brand (that is, the specific brand name of vehicle A), SUV, 2023-11-11, headlights not on, headlights damaged, replace headlights, Person A, the vehicle after-sales event of vehicle B corresponds to the characteristic information of the above-mentioned multiple characteristic identifiers, respectively, 07, CC0CCCC0022222222 (that is, the specific vehicle identification code of vehicle B), no, E brand (that is, the specific brand name of vehicle B), sedan, 2021-05-22, car cannot start, battery power is low, replace battery, person B; based on this, the number of rows in the above-mentioned database is equal to the total number of data groups, and the number of columns in the above-mentioned database is 10, among which the data group corresponding to the vehicle after-sales event of vehicle A includes data stored in the same column of the above-mentioned database. In a row, the 10 columns of data in the row are, from front to back, 01, CC0CCCC0011111111, yes, brand D, SUV, 2023-11-11, headlights not on, headlights damaged, replace headlights, person A. The data group corresponding to the vehicle after-sales events of vehicle B is stored in the same row of the above database. The 10 columns of data in the row are, from front to back, 07, CC0CCCC0022222222, no, brand E, sedan, 2021-05-22, car cannot start, battery low, replace battery, person B.
[0025] Step 102: According to the input question text, multiple feature identifiers and feature information corresponding to the multiple feature identifiers, at least part of the data groups are screened out from the multiple data groups to form a data set.
[0026] The question text is used to instruct obtaining statistical results based on multiple data groups.
[0027] In a specific implementation, an input question text may be obtained, and then at least part of the data groups that are more relevant to the question text may be screened out from multiple data groups based on the question text, multiple feature identifiers, and feature information corresponding to the multiple feature identifiers to form a data set.
[0028] Step 103: Using the statistical tool corresponding to the question text, obtain the numerical value obtained by statistical processing based on the data set according to the question text.
[0029] In a specific implementation, a statistical tool corresponding to the question text can be determined from a plurality of statistical tools (such as a statistical tool for summing and a statistical tool for counting, etc.) based on the question text, and then the statistical tool is called to obtain a numerical value obtained by statistical processing based on the data set according to the question text.
[0030] For example, the above event is a vehicle after-sales event, specifically a vehicle after-sales case. Each data group includes case information of a corresponding vehicle after-sales case. The question text is "How many cases occurred for XX brand cars in March this year?", then the statistical tool corresponding to the question text is a statistical tool for counting, and the value is the number of data groups in all data groups whose corresponding dates are in March this year and whose corresponding vehicle brand is XX brand, such as 20, 15, 0, 100, etc.
[0031] Step 104: Determine the answer text corresponding to the question text according to the numerical value and the question text.
[0032] The answer text includes a numerical value. For example, based on the above example, if the numerical value is 30, the answer text may be "30 cases occurred in XX brand cars in March this year.".
[0033] In a specific implementation, numerical values and question texts may be input into a large language model to obtain answer texts output by the large language model. Thus, statistical methods may be combined with the large language model to fully utilize the capabilities of the large language model.
[0034] In an embodiment of the present application, multiple data groups can be obtained, and according to the question text for indicating the acquisition of the statistical results based on the multiple data groups, multiple feature identifiers and the feature information corresponding to the multiple feature identifiers, at least part of the data groups can be screened out from the multiple data groups to form a data set, and then the numerical value obtained by statistical processing based on the data set can be obtained according to the question text through the statistical tool corresponding to the question text, and then the answer text including the numerical value can be determined according to the numerical value and the question text. Therefore, compared with manually counting one by one according to the actual statistical conditions to realize statistical event information, the present application automatically realizes statistical event information according to the question text and the constructed multiple data groups, and the statistical processing is performed based on the data set obtained after screening the multiple data groups. Compared with the multiple data groups, the data set has less data, which can speed up the processing process of statistical processing, thereby improving the efficiency of statistical event information.
[0035] Furthermore, in this application, statistics on event information can be completed through question-and-answer dialogue, which is more convenient, faster and saves manpower.
[0036] In addition, this answer generation method can be extended to different vertical fields. By building databases corresponding to different fields, it can quickly adapt to different application scenarios.
[0037] In a possible implementation, the event is a vehicle after-sales event; the multiple feature identifiers are at least two of an identifier corresponding to a case number, an identifier corresponding to a vehicle identification code, an identifier corresponding to whether the problem has been solved, an identifier corresponding to a brand, an identifier corresponding to a vehicle model, an identifier corresponding to a date, an identifier corresponding to a problem description, an identifier corresponding to a cause, an identifier corresponding to a solution, and an identifier corresponding to a person recording the event;
[0038] Based on this, the identifier corresponding to the case number, the identifier corresponding to the vehicle identification code, the identifier corresponding to whether the problem has been resolved, the identifier corresponding to the brand, the identifier corresponding to the vehicle model, and the identifier corresponding to the date among the multiple feature identifiers are all target identifiers, and the identifier corresponding to the problem description, the identifier corresponding to the cause, the identifier corresponding to the solution, and the identifier corresponding to the person recording the event among the multiple feature identifiers are all non-target identifiers.
[0039] Among them, the feature identifier can be text or numbers, etc., which is not limited in the embodiments of the present application.
[0040] For instance, as in the above example, the multiple feature identifiers are respectively an identifier corresponding to the case number, an identifier corresponding to the vehicle identification code, an identifier corresponding to whether the problem has been solved, an identifier corresponding to the brand, an identifier corresponding to the vehicle model, an identifier corresponding to the date, an identifier corresponding to the problem description, an identifier corresponding to the cause, an identifier corresponding to the solution, and an identifier corresponding to the person who recorded the event. Among them, the identifier corresponding to the case number, the identifier corresponding to the vehicle identification code, an identifier corresponding to whether the problem has been solved, an identifier corresponding to the brand, an identifier corresponding to the vehicle model, and an identifier corresponding to the date are all target identifiers, and the identifier corresponding to the problem description, the identifier corresponding to the cause, the identifier corresponding to the solution, and the identifier corresponding to the person who recorded the event are all non-target identifiers.
[0041] In a possible implementation, the above step 102 includes the following specific processing: based on the input question text, and the feature information in the multiple data groups corresponding to the target identifier in the multiple feature identifiers, at least one first target data group is screened out from the multiple data groups; based on the question text, and the feature information in the above at least one first target data group corresponding to the non-target identifier in the multiple feature identifiers, at least one second target data group is screened out from the above at least one first target data group to form a data set.
[0042] Among them, the characteristic information corresponding to the target identifier is the characteristic identifier of any preset information corresponding to the target identifier, and the non-target identifier is a characteristic identifier that is not a target identifier; for example, the characteristic information corresponding to the characteristic identifier "Has it been resolved" is any one of the preset information "yes" corresponding to the characteristic identifier and the preset information "no" corresponding to the characteristic identifier, so the characteristic identifier "Has it been resolved" is the target identifier; for another example, the characteristic information corresponding to the characteristic identifier "VIN code" is any one of the VIN codes of all sold vehicles (the VIN code of each sold vehicle is the preset information corresponding to the characteristic information), so the characteristic identifier "VIN code" is the target identifier; for another example, the characteristic information corresponding to the characteristic identifier "problem description" is relatively diverse, and the characteristic identifier has no corresponding preset information, so the characteristic identifier "problem description" is a non-target identifier.
[0043] In the embodiment of the present application, in the process of screening multiple data groups to obtain a data set, screening can be performed first according to the characteristic information corresponding to the target identifier in the multiple data groups, and then screening can be performed according to the characteristic information corresponding to the non-target identifier in at least one first target data group obtained after this screening, and the at least one second target data group obtained after this screening forms a data set. Thus, since the characteristic information corresponding to the target identifier is the characteristic identifier of any preset information corresponding to the target identifier, the format and / or content of the characteristic information corresponding to the target identifier is relatively fixed than the characteristic information corresponding to the characteristic identifier that is not the target identifier, that is, the result of screening according to the characteristic information corresponding to the target identifier is more accurate than the result of screening according to the characteristic information corresponding to the non-target identifier, and then, under the premise of ensuring that the characteristic information is fully screened as much as possible, compared with screening according to all the characteristic information without distinguishing between the non-target identifier and the target identifier, the present application first screens according to the characteristic information corresponding to the target identifier, so that the result of screening according to the characteristic information corresponding to the target identifier can be more accurate, so that the second target data group included in the data set has a higher degree of relevance to the question text.
[0044] In a possible implementation, the answer generation method further includes:
[0045] The question text is split to obtain text information corresponding to at least some of the feature identifiers among the multiple feature identifiers, and logical relationships between at least some of the text information.
[0046] In a specific implementation, the question text can be split and processed according to the question body (referring to the statistical target indicated by the question text, such as the number of vehicles, the number of cases, the number of people, etc.), the question conditions (referring to the statistical conditions indicated by the question text, such as XX brand, XX model, etc.), the logical relationship between the conditions, and the matching column names. The question body includes text information corresponding to at least one feature identifier, the question conditions include text information corresponding to at least one feature identifier, the logical relationship between the conditions includes the logical relationship between different text information in the question conditions, and the matching column names include the feature identifiers corresponding to each text information.
[0047] For example, if the question text is "How many cases of XX brand cars occurred in March this year?", the split results after splitting the question text are as follows:
[0048] Question body: Case
[0049] Question conditions: March this year, XX brand
[0050] The logical relationship between the conditions: (March of this year) ∩ (XX brand)
[0051] Matching column names: Case: Case number, March of this year: Date, XX brand: Brand
[0052] Among them, "Case" is the text information corresponding to the feature identifier "Case number", "XX brand" is the text information corresponding to the feature identifier "brand", "March this year" is the text information corresponding to the feature identifier "date", and "(March this year) ∩(XX brand)" is the logical relationship between the text information "March this year" and the text information "XX brand" in the above problem conditions.
[0053] Optionally, the above-mentioned splitting process can be implemented by a large language model. Specifically, the corresponding prompt words (prompt) and sample library (query shot library) can be designed, and the large language model can be used to split the question text through a few sample prompts (few shots). The embodiments of the present application are not limited here.
[0054] Based on this:
[0055] The above-mentioned method of screening out at least one first target data group from multiple data groups based on the input question text and the feature information in multiple data groups corresponding to the target identifier in multiple feature identifiers includes the following specific processing: determining the target identifier in at least part of the above-mentioned feature identifiers as the first identifier; according to the logical relationship, among the feature information corresponding to the first identifier in the multiple data groups, determining the data group where at least part of the feature information matching the corresponding text information is located as the first target data group, wherein the text information corresponding to the feature information corresponding to the first identifier is the text information corresponding to the first identifier corresponding to the feature information.
[0056] In a specific embodiment, after obtaining the split results of the question text, the feature identifiers corresponding to the text information in the question body and the question conditions can be obtained according to the matching column names in the split results, and then each target identifier in this part of the feature identifiers is determined as the first identifier, and then for each first identifier, it is determined whether each feature information corresponding to the first identifier matches the text information corresponding to the first identifier, and according to the logical relationship, the data group containing at least part of the feature information corresponding to the first identifier that matches the text information corresponding to the first identifier is used as the first target data group.
[0057] The above process of taking the data group containing at least part of the characteristic information corresponding to the first identifier that matches the text information corresponding to the first identifier as the first target data group based on the logical relationship can be divided into three stages, and each stage processes a different first identifier, wherein the first identifier in the first stage has its corresponding characteristic information obtained by a direct input method, and the format of the characteristic information is unique; the first identifier in the second stage has its corresponding characteristic information obtained by a selected input method; the first identifier in the third stage has its corresponding characteristic information obtained by a direct input method, and the format of the characteristic information is not unique.
[0058] For example, after obtaining the split result after splitting the problem text, 6 first identifiers can be obtained, which are respectively an identifier corresponding to the case number, an identifier corresponding to the vehicle identification code, an identifier corresponding to whether it has been solved, an identifier corresponding to the brand, an identifier corresponding to the vehicle model, and an identifier corresponding to the date; then, for each of the two first identifiers, the identifier corresponding to the case number and the identifier corresponding to the vehicle identification code, a regular matching method can be used to determine whether each feature information corresponding to the first identifier in all data groups matches the text information corresponding to the first identifier, and according to the logical relationship, the data group containing at least part of the feature information corresponding to the first identifier that matches the text information corresponding to the first identifier is taken as the first data group; then, for each of the three first identifiers, the identifier corresponding to whether it has been solved, the identifier corresponding to the brand, and the identifier corresponding to the vehicle model, a string matching method can be used to determine whether each feature information corresponding to the first identifier in all first data groups matches the text information corresponding to the first identifier. According to the logical relationship, all first data groups where at least part of the feature information corresponding to the first identifier that matches the text information corresponding to the first identifier is located are taken as second data groups; then for the first identifier corresponding to the date, the text information corresponding to the first identifier is first converted into the same format as the feature information corresponding to the first identifier, for example, the text information about the date in the question condition is converted into a format in which the start and end dates are given in the format of YYYY-MM-DD by using a large language model (LLM), and then a string matching method is used to determine whether each feature information corresponding to the first identifier in all the second data groups matches the text information corresponding to the first identifier after the format conversion (if the feature information corresponding to the first identifier is within the date specified by the text information corresponding to the first identifier after the format conversion, the two match, otherwise the two do not match), and according to the logical relationship, all second data groups where at least part of the feature information corresponding to the first identifier that matches the text information corresponding to the first identifier after the format conversion is located are taken as first target data groups.
[0059] It should be noted that, in the above example, when determining the first data group according to the logical relationship, the first data group is specifically determined according to the specific logical relationship between the text information corresponding to the identifier corresponding to the case number and the identifier corresponding to the vehicle identification code; when determining the second data group according to the logical relationship, the second data group is specifically determined according to the specific logical relationship between the text information corresponding to any two first identifiers among the identifier corresponding to the case number, the identifier corresponding to the vehicle identification code, the identifier corresponding to whether the problem has been solved, the identifier corresponding to the brand, and the identifier corresponding to the vehicle model; when determining the first target data group according to the logical relationship, the second data group is specifically determined according to the specific logical relationship between the text information corresponding to any two first identifiers among the identifier corresponding to the case number, the identifier corresponding to the vehicle identification code, the identifier corresponding to whether the problem has been solved, the identifier corresponding to the brand, the identifier corresponding to the vehicle model, and the identifier corresponding to the date; for example, when determining the second data group according to the logical relationship, if the identifier corresponding to the case number (recorded as the first identifier a) and the identifier corresponding to whether the problem has been solved (recorded as the first identifier b) in the logical relationship are in an and relationship, then A first data group may be determined as a second data group only if there is feature information corresponding to the first identifier a that matches the text information corresponding to the first identifier a, and there is feature information corresponding to the first identifier b that matches the text information corresponding to the first identifier b (whether it will be determined as the second data group depends on the specific logical relationship with other first identifiers). A first data group that only has one of these two feature information will not be determined as a second data group. However, if the identifier corresponding to the case number (recorded as the first identifier a) and the identifier corresponding to whether it has been resolved (recorded as the first identifier b) are in an or relationship in the logical relationship, then a first data group that has feature information corresponding to the first identifier a that matches the text information corresponding to the first identifier a, or a first data group that has feature information corresponding to the first identifier b that matches the text information corresponding to the first identifier b may be determined as a second data group, that is, a first data group that only has one of these two feature information may be determined as a second data group. The specific process of determining the first data group and the first target data group according to the logical relationship is similar, and the embodiments of the present application will not be repeated here.
[0060] Therefore, when determining the first target data group, not only the text information included in the question text will be taken into consideration, but also the logical relationship between at least part of the text information included in the question text will be taken into consideration, so that the number of the first target data group is smaller and the first target data group is more highly relevant to the question text. Furthermore, since the data set is obtained based on the first target data group and the statistical processing is performed based on the data set, the data set has less data, which can speed up the statistical processing process, improve the efficiency of statistical event information, and improve the accuracy of statistical event information.
[0061] In a possible implementation, based on the above-mentioned scheme for splitting the question text, at least one second target data group is screened out from the at least one first target data group based on the question text and the feature information corresponding to the non-target identifier in the multiple feature identifiers in the at least one first target data group, including the following specific processing: determining the non-target identifier in at least part of the feature identifiers as the second identifier; according to a logical relationship, in the feature information corresponding to the second identifier in the at least one first target data group, determining the first target data group where at least part of the feature information matching the corresponding text information is located as the second target data group, wherein the text information corresponding to the feature information corresponding to the second identifier is the text information corresponding to the second identifier corresponding to the feature information.
[0062] In a specific embodiment, after obtaining the first target data group, the feature identifiers corresponding to the text information in the question body and the question conditions can be obtained according to the matching column names in the splitting results, and then each non-target identifier in this part of the feature identifiers is determined as a second identifier, and then for each second identifier, it is determined whether each feature information corresponding to the second identifier matches the text information corresponding to the second identifier, and according to the logical relationship, the first target data group containing at least part of the feature information corresponding to the second identifier that matches the text information corresponding to the second identifier is used as the second target data group.
[0063] For example, after obtaining the first target data group, three second identifiers can be obtained, which are respectively an identifier corresponding to the problem description, an identifier corresponding to the cause, and an identifier corresponding to the solution; then, for each of the three second identifiers, a natural language processing (NLP) method (specifically, a method based on text similarity and setting an appropriate similarity threshold) can be used to determine whether each feature information corresponding to the second identifier in all the first target data groups matches the text information corresponding to the second identifier, and according to a logical relationship, all of the first target data groups containing at least part of the feature information corresponding to the second identifier that matches the text information corresponding to the second identifier are used as second target data groups.
[0064] It should be noted that, in the above example, when determining the second target data group based on the logical relationship, the second target data group is specifically determined based on the specific logical relationship between the text information corresponding to any two identifiers including the second identifier among all the first identifiers and all the second identifiers; for example, when determining the second target data group based on the logical relationship, if the identifier corresponding to the case number (recorded as the first identifier c) and the identifier corresponding to the cause (recorded as the second identifier d) in the logical relationship are in an and relationship, then the first target data group may be determined as the second target data group (specifically, the first target data group) only if there is feature information corresponding to the first identifier c that matches the text information corresponding to the first identifier c and there is feature information corresponding to the second identifier d that matches the text information corresponding to the second identifier d. Whether the body will be determined as the second target data group also needs to consider the specific logical relationship with other identifiers). The first target data group with only one of these two characteristic information will not be determined as the second target data group, but if the identifier corresponding to the case number (recorded as the first identifier c) and the identifier corresponding to the reason (recorded as the second identifier d) are in an or relationship in the logical relationship, then the first target data group with the characteristic information corresponding to the first identifier c that matches the text information corresponding to the first identifier c, or the first target data group with the characteristic information corresponding to the second identifier d that matches the text information corresponding to the second identifier d may be determined as the second target data group, that is, the first target data group with only one of these two characteristic information may be determined as the second target data group.
[0065] Therefore, when determining the second target data group, not only the text information included in the question text will be taken into consideration, but also the logical relationship between at least part of the text information included in the question text will be taken into consideration, so that the number of the second target data group is smaller and the second target data group is more highly relevant to the question text. Furthermore, since the data set is composed of the second target data group and the statistical processing is performed based on the data set, the data set has less data, which can speed up the statistical processing process, improve the efficiency of statistical event information, and improve the accuracy of statistical event information.
[0066] In a possible implementation, the answer generation method also includes the following specific processing: inputting the question text and multiple alternative statistical tool identifiers into the target model; and determining the alternative statistical tool corresponding to the alternative statistical tool identifier output by the target model as the statistical tool corresponding to the question text.
[0067] Among them, the target model can be LLM, etc., the alternative statistical tools corresponding to multiple alternative statistical tool identifiers can be statistical tools such as a statistical tool for summation and a statistical tool for counting, and the alternative statistical tool identifier can be the name of the statistical tool, etc.
[0068] In a specific implementation, the question text and multiple alternative statistical tool identifiers can be input into the target model so that the target model determines the alternative statistical tool identifier corresponding to the question text from the multiple alternative statistical tool identifiers and outputs the alternative statistical tool identifier. Then, the alternative statistical tool corresponding to the alternative statistical tool identifier output by the target model can be directly determined as the statistical tool corresponding to the question text.
[0069] Therefore, the target model can be used to directly determine the alternative statistical tools corresponding to the question text, without the need to select based on manual experience, which is more accurate and quick.
[0070] Optionally, each module used to execute the answer generation method of the present application is deployed in the cloud, so that each module can be improved differently according to different actual application scenarios, flexibly adapted to the actual scenarios, and has less impact on actual online applications.
[0071] Answer Generator
[0072] Corresponding to the above method embodiment, Figure 2 A schematic diagram of an answer generation device according to an embodiment of the present application is shown. Figure 2 As shown, the answer generating device 200 comprises:
[0073] An acquisition unit 201 is used to acquire multiple data groups, wherein the data groups include feature information corresponding to multiple feature identifiers, the feature information is information about events corresponding to the data groups where the feature information is located, and different data groups correspond to different events;
[0074] A screening unit 202, configured to screen out at least some of the data groups from the multiple data groups to form a data set according to an input question text, the multiple feature identifiers, and feature information corresponding to the multiple feature identifiers, wherein the question text is used to indicate obtaining statistical results based on the multiple data groups;
[0075] A statistical unit 203, configured to obtain a numerical value obtained by statistical processing based on the data set according to the question text by using a statistical tool corresponding to the question text;
[0076] The determination unit 204 is used to determine the answer text corresponding to the question text according to the numerical value and the question text, wherein the answer text includes the numerical value.
[0077] It should be noted that the answer generation device of this embodiment is used to implement the corresponding answer generation method in the aforementioned method embodiment, and has the beneficial effects of the corresponding method embodiment, which will not be described in detail here.
[0078] Electronic devices
[0079] Figure 3 This is a schematic block diagram of an electronic device provided in an embodiment of the present application. The specific embodiment of the present application does not limit the specific implementation of the electronic device. Figure 3 As shown, the electronic device may include: a processor 302, a communications interface 304, a memory 306, and a communications bus 308. Among them:
[0080] The processor 302 , the communication interface 304 , and the memory 306 communicate with each other via the communication bus 308 .
[0081] The communication interface 304 is used to communicate with other electronic devices or servers.
[0082] The processor 302 is used to execute the program 310, and specifically can execute the relevant steps in any of the aforementioned answer generation method embodiments.
[0083] Specifically, the program 310 may include program codes, which include computer operation instructions.
[0084] The processor 302 may be a CPU, or an application specific integrated circuit ASIC (Application Specific Integrated Circuit), or one or more integrated circuits configured to implement the embodiments of the present application. The one or more processors included in the smart device may be processors of the same type, such as one or more CPUs; or processors of different types, such as one or more CPUs and one or more ASICs.
[0085] RISC-V is an open source instruction set architecture based on the Reduced Instruction Set (RISC) principle. It can be applied to various aspects such as single-chip microcomputers and FPGA chips. Specifically, it can be applied to the fields of IoT security, industrial control, mobile phones, personal computers, etc., and because it is designed with small, fast, and low-power realities in mind, it is particularly suitable for modern computing devices such as warehouse-scale cloud computers, high-end mobile phones, and tiny embedded systems. With the rise of artificial intelligence Internet of Things (AIoT), the RISC-V instruction set architecture has also received more and more attention and support, and is expected to become the next generation of widely used CPU architecture.
[0086] The computer operation instructions in the embodiment of the present application may be computer operation instructions based on the RISC-V instruction set architecture, and correspondingly, the processor 302 may be designed based on the RISC-V instruction set. Specifically, the processor chip in the electronic device provided in the embodiment of the present application may be a chip designed using the RISC-V instruction set, and the chip may execute executable code based on the configured instructions, thereby implementing the answer generation method in the above embodiment.
[0087] The memory 306 is used to store the program 310. The memory 306 may include a high-speed RAM memory, and may also include a non-volatile memory (non-volatile memory), such as at least one disk memory.
[0088] The program 310 may be specifically configured to enable the processor 302 to execute the answer generation method in any of the aforementioned embodiments.
[0089] The specific implementation of each step in program 310 can refer to the corresponding description of the corresponding steps and units in any of the above-mentioned answer generation method embodiments, which will not be repeated here. Those skilled in the art can clearly understand that for the convenience and simplicity of description, the specific working process of the above-described devices and modules can refer to the corresponding process description in the above-mentioned method embodiments, which will not be repeated here.
[0090] Through the electronic device of the embodiment of the present application, multiple data groups can be obtained, and according to the question text for indicating the acquisition of the statistical results based on the multiple data groups, multiple feature identifiers and the feature information corresponding to the multiple feature identifiers, at least part of the data groups can be screened out from the multiple data groups to form a data set, and then the numerical value obtained by statistical processing based on the data set can be obtained according to the question text through the statistical tool corresponding to the question text, and then the answer text including the numerical value can be determined according to the numerical value and the question text. Therefore, compared with manually counting one by one according to the actual statistical conditions to realize statistical event information, the present application automatically realizes statistical event information according to the question text and the constructed multiple data groups, and the statistical processing is performed based on the data set obtained after screening the multiple data groups. Compared with the multiple data groups, the data set has less data, which can speed up the processing process of statistical processing, thereby improving the efficiency of statistical event information.
[0091] Computer storage media
[0092] The present application also provides a computer-readable storage medium storing instructions for causing a machine to execute the answer generation method as described herein. Specifically, a system or device equipped with a storage medium can be provided, on which a software program code implementing the functions of any of the above embodiments is stored, and a computer (or CPU or MPU) of the system or device reads and executes the program code stored in the storage medium.
[0093] In this case, the program code read from the storage medium itself can implement the function of any one of the above embodiments, so the program code and the storage medium storing the program code constitute part of the present application.
[0094] The storage medium embodiments for providing the program code include a floppy disk, a hard disk, a magneto-optical disk, an optical disk (such as CD-ROM, CD-R, CD-RW, DVD-ROM, DVD-RAM, DVD-RW, DVD+RW), a magnetic tape, a non-volatile memory card, and a ROM. Alternatively, the program code can be downloaded from a server computer by a communication network.
[0095] Computer program product
[0096] An embodiment of the present application also provides a computer program product, including computer instructions, which instruct a computing device to perform any corresponding operation in the above-mentioned multiple method embodiments.
[0097] It should be noted that the user-related information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to sample data used to train the model, data used for analysis, stored data, displayed data, etc.) involved in the embodiments of the present application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data need to comply with relevant laws, regulations and standards of relevant countries and regions, and provide corresponding operation entrances for users to choose to authorize or refuse.
[0098] It should be pointed out that, according to the needs of implementation, the various components / steps described in the embodiments of the present application can be split into more components / steps, or two or more components / steps or partial operations of components / steps can be combined into new components / steps to achieve the purpose of the embodiments of the present application.
[0099] The above-mentioned method according to the embodiment of the present application can be implemented in hardware, firmware, or implemented as software or computer code that can be stored in a recording medium (such as a CD ROM, RAM, floppy disk, hard disk or magneto-optical disk), or implemented as a computer code originally stored in a remote recording medium or a non-temporary machine-readable medium downloaded through a network and to be stored in a local recording medium, so that the method described herein can be stored in such software processing on a recording medium using a general-purpose computer, a special-purpose processor or programmable or special-purpose hardware (such as an ASIC or FPGA). It can be understood that a computer, a processor, a microprocessor controller or programmable hardware includes a storage component (e.g., RAM, ROM, flash memory, etc.) that can store or receive software or computer code, and when the software or computer code is accessed and executed by a computer, a processor or hardware, the method described herein is implemented. In addition, when a general-purpose computer accesses the code for implementing the method shown here, the execution of the code converts the general-purpose computer into a special-purpose computer for executing the method shown here.
[0100] It should be noted that the user-related information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to sample data used to train the model, data used for analysis, stored data, displayed data, etc.) involved in the embodiments of the present application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data need to comply with relevant laws, regulations and standards of relevant countries and regions, and provide corresponding operation entrances for users to choose to authorize or refuse.
[0101] Those of ordinary skill in the art will appreciate that the units and method 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 specific applications, but such implementation should not be considered to be beyond the scope of the embodiments of the present application.
[0102] The above implementation methods are only used to illustrate the embodiments of the present application, and are not limitations on the embodiments of the present application. Ordinary technicians in the relevant technical field can make various changes and modifications without departing from the spirit and scope of the embodiments of the present application. Therefore, all equivalent technical solutions also belong to the scope of the embodiments of the present application. The scope of patent protection of the embodiments of the present application should be limited by the claims.
Claims
1. A method for generating an answer, characterized in that: include: Acquire multiple data groups, wherein the data groups include feature information corresponding to multiple feature identifiers, the feature information is information about events corresponding to the data groups where the feature information is located, and different data groups correspond to different events; According to the input question text, the multiple feature identifiers and the feature information corresponding to the multiple feature identifiers, at least part of the data groups are screened out from the multiple data groups to form a data set, wherein the question text is used to indicate obtaining statistical results based on the multiple data groups; Obtaining, by means of a statistical tool corresponding to the question text, a numerical value obtained by statistical processing based on the data set according to the question text; According to the numerical value and the question text, an answer text corresponding to the question text is determined, wherein the answer text includes the numerical value.
2. The method according to claim 1, characterized in that The step of selecting at least part of the data groups from the plurality of data groups according to the input question text, the plurality of feature identifiers and the feature information corresponding to the plurality of feature identifiers to form a data set includes: Filtering at least one first target data group from the multiple data groups according to the input question text and the feature information corresponding to the target identifier in the multiple feature identifiers in the multiple data groups, wherein the feature information corresponding to the target identifier is the feature identifier of any preset information corresponding to the target identifier; Based on the question text and the feature information in the at least one first target data group corresponding to the non-target identifier among the multiple feature identifiers, at least one second target data group is screened out from the at least one first target data group to form the data set, wherein the non-target identifier is the feature identifier that is not the target identifier.
3. The method according to claim 2, characterized in that The method further comprises: Splitting the question text to obtain text information corresponding to at least some of the feature identifiers, and logical relationships between at least some of the text information; The step of selecting at least one first target data group from the multiple data groups based on the input question text and the feature information in the multiple data groups corresponding to the target identifier in the multiple feature identifiers includes: Determine the target identifier in the at least part of the feature identifiers as a first identifier; According to the logical relationship, among the feature information corresponding to the first identifier in the multiple data groups, the data group where at least part of the feature information matching the corresponding text information is located is determined as the first target data group, wherein the text information corresponding to the feature information corresponding to the first identifier is the text information corresponding to the first identifier corresponding to the feature information.
4. The method according to claim 2, characterized in that: The method further comprises: Splitting the question text to obtain text information corresponding to at least some of the feature identifiers, and logical relationships between at least some of the text information; The step of selecting at least one second target data group from the at least one first target data group according to the question text and feature information corresponding to the non-target identifiers in the plurality of feature identifiers in the at least one first target data group comprises: Determining the non-target identifier in the at least part of the feature identifiers as a second identifier; According to the logical relationship, in the feature information corresponding to the second identifier in the at least one first target data group, the first target data group where at least part of the feature information matching the corresponding text information is located is determined as the second target data group, wherein the text information corresponding to the feature information corresponding to the second identifier is the text information corresponding to the second identifier corresponding to the feature information.
5. The method according to claim 1, characterized in that The method further comprises: inputting the question text and multiple candidate statistical tool identifiers into a target model; The alternative statistical tool corresponding to the alternative statistical tool identifier output by the target model is determined as the statistical tool corresponding to the question text.
6. The method according to any one of claims 1 to 5, characterized in that The incident described is a post-sale vehicle incident; The multiple feature identifiers are at least two of an identifier corresponding to the case number, an identifier corresponding to the vehicle identification code, an identifier corresponding to whether the problem has been solved, an identifier corresponding to the brand, an identifier corresponding to the vehicle model, an identifier corresponding to the date, an identifier corresponding to the problem description, an identifier corresponding to the cause, an identifier corresponding to the solution, and an identifier corresponding to the person who recorded the event.
7. An answer generation device, characterized in that: include: An acquisition unit, used for acquiring a plurality of data groups, wherein the data groups include characteristic information corresponding to a plurality of characteristic identifiers, the characteristic information is information of an event corresponding to the data group where the characteristic information is located, and different data groups correspond to different events; a screening unit, configured to screen out at least part of the data groups from the multiple data groups to form a data set according to an input question text, the multiple feature identifiers, and feature information corresponding to the multiple feature identifiers, wherein the question text is used to indicate obtaining statistical results based on the multiple data groups; A statistical unit, configured to obtain, according to the question text, a numerical value obtained by statistical processing based on the data set, using a statistical tool corresponding to the question text; A determination unit is used to determine an answer text corresponding to the question text based on the numerical value and the question text, wherein the answer text includes the numerical value.
8. An electronic device, characterized in that: include: A processor, a memory, a communication interface and a communication bus, wherein the processor, the memory and the communication interface communicate with each other via the communication bus; The memory is used to store at least one executable instruction, and the executable instruction enables the processor to execute an operation corresponding to the method according to any one of claims 1 to 6.
9. A computer storage medium, characterized in that A computer program is stored thereon, and when the program is executed by a processor, the method according to any one of claims 1 to 6 is implemented.
10. A computer program product, characterized in that The method comprises computer instructions for instructing a computing device to execute the method according to any one of claims 1 to 6.