Recommendation method and device and electronic equipment
Through data classification and probability calculation, the number of recommended positions and solutions for vehicle models is provided, which solves the problem of inaccurate reply by vehicle service personnel when there is a lack of model information, and improves the accuracy and user experience of recommendation results.
Patent Information
- Application Number
- CN202310799085.3
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2023-06-30
- Publication Date
- 2024-12-31
AI Technical Summary
When answering user questions, the lack of vehicle model information leads to inaccurate responses and requires multiple questions to get the correct answer.
By obtaining the data of pending problems, classifying data, combining the delivery ratio of the vehicle model and the probability of data categories in the historical problem data, the number of recommended digits for each vehicle model is calculated, and the solution is selected in the corresponding data category as the recommended solution .
It improves the accuracy of recommended results of pending problem data that does not contain vehicle model information, reduces the user's need to ask multiple times, and improves the user experience.
Smart Images
Figure CN119226348A_ABST
Abstract
Description
Technical Field
[0001] The present disclosure relates to the technical field of automobile data mining, and in particular to a recommendation method, device and electronic device. Background Art
[0002] At present, when vehicle service personnel (such as employees of 4S stores) answer various questions raised by users, they mostly give responses based on their own experience. Generally, when the questions raised by users include the model of the car, the vehicle service personnel can give a roughly corresponding response to the question corresponding to the model. However, when the questions raised by users do not include the model of the car, the responses that are not what the users need often appear. Therefore, it often takes multiple questions to get the response that the users need.
[0003] Therefore, when the question raised by the user does not include the car model, how to provide the vehicle service personnel with a recommended response or directly generate a recommended response for the user becomes an urgent problem to be solved. Summary of the invention
[0004] In order to solve the above technical problems, the present disclosure provides a recommendation method, device and electronic device.
[0005] In order to achieve the above objectives, the present invention adopts the following technical solutions:
[0006] In a first aspect, the present disclosure provides a recommendation method, comprising: obtaining problem data to be processed; wherein the problem data to be processed does not contain vehicle model information; classifying the problem data to be processed to obtain data categories corresponding to the problem data to be processed; based on the total number of recommended positions, the delivery ratio of each vehicle model, and the probability of occurrence of data categories in historical problem data corresponding to each vehicle model, respectively obtain the number of recommended positions for each vehicle model; among the solutions corresponding to the vehicle model in the data category, screening solutions with the number of recommended positions corresponding to the vehicle model as recommended solutions; generating recommendation results based on the recommended solutions corresponding to each vehicle model.
[0007] In some feasible examples, data classification is performed on the problem data to be processed to obtain data categories corresponding to the problem data to be processed, including: preprocessing the problem data to be processed to obtain preprocessed target data; wherein the preprocessing includes: removing stop words, removing punctuation marks, and converting uppercase and lowercase characters into one or more items; data classification is performed on the target data to obtain data categories corresponding to the target data; based on the data categories corresponding to the target data, determining that the data category corresponding to the problem data to be processed is the data category corresponding to the target data.
[0008] In some feasible examples, the number of recommended positions for each model is obtained based on the total number of recommended positions, the delivery ratio of each model, and the probability of occurrence of data categories in the historical problem data corresponding to each model, including: obtaining the delivery ratio of each model based on the ratio of the delivery data of each model to the total delivery data; obtaining the number of recommended positions for each model based on the total number of recommended positions, the delivery ratio and the probability of occurrence of data categories in the historical problem data corresponding to each model.
[0009] In some feasible examples, the number of recommended positions for a vehicle model is obtained based on the total number of recommended positions, the delivery ratio, and the probability of occurrence of data categories in the historical problem data corresponding to each vehicle model, including: obtaining the matching probability of each vehicle model based on the product of the delivery ratio and the probability of occurrence of data categories in the historical problem data corresponding to each vehicle model; obtaining the number of recommended positions for each vehicle model based on the product of the matching probability and the total number of recommended positions.
[0010] In some feasible examples, in the solutions corresponding to the vehicle model in the data category, the solutions with the number of recommended positions corresponding to the vehicle model are selected as the recommended solutions, including: when the total number of solutions corresponding to the vehicle model in the data category is greater than the number of recommended positions corresponding to the vehicle model, the solutions with the number of recommended positions are selected as the recommended solutions in the solution according to the target method; wherein the target method includes: any one of: randomly, or sorting the number of recommended positions of the solutions in descending order;
[0011] In some feasible examples, among the solutions corresponding to the vehicle model in the data category, solutions with the number of recommended positions corresponding to the vehicle model are screened as recommended solutions, including: when the total number of solutions corresponding to the vehicle model in the data category is less than or equal to the number of recommended positions corresponding to the vehicle model, the solution is recommended.
[0012] In a second aspect, the present disclosure provides a recommendation device, comprising: an acquisition unit, for acquiring problem data to be processed; wherein the problem data to be processed does not contain vehicle model information; a processing unit, for performing data classification on the problem data to be processed acquired by the acquisition unit, and obtaining data categories corresponding to the problem data to be processed; the processing unit is also used to obtain the number of recommended positions for each vehicle model based on the total number of recommended positions, the delivery ratio of each vehicle model, and the probability of occurrence of data categories in historical problem data corresponding to each vehicle model; the processing unit is also used to filter out solutions with the number of recommended positions corresponding to the vehicle model in the solutions corresponding to the data category as recommended solutions; the processing unit is also used to generate recommendation results based on the recommended solutions corresponding to each vehicle model.
[0013] In some implementable examples, the processing unit is specifically used to preprocess the problem data to be processed acquired by the acquisition unit to obtain preprocessed target data; wherein the preprocessing includes: removing stop words, removing punctuation marks, and one or more of uppercase and lowercase conversion; the processing unit is specifically used to classify the target data to obtain the data category corresponding to the target data; the processing unit is specifically used to determine that the data category corresponding to the problem data to be processed is the data category corresponding to the target data based on the data category corresponding to the target data.
[0014] In some feasible examples, the processing unit is specifically used to obtain the delivery ratio of each model based on the ratio of the delivery data of each model to the total delivery data; the processing unit is specifically used to obtain the number of recommended positions for each model based on the total number of recommended positions, the delivery ratio and the probability of occurrence of data categories in the historical problem data corresponding to the model.
[0015] In some feasible examples, the processing unit is specifically used to obtain the matching probability of each vehicle model based on the product of the delivery ratio and the occurrence probability of the data category in the historical problem data corresponding to each vehicle model; the processing unit is specifically used to obtain the number of recommended positions for each vehicle model based on the product of the matching probability and the total number of recommended positions.
[0016] In some feasible examples, the processing unit is specifically used to select a solution with the same number of recommended positions as a recommended solution in a target manner when the total number of solutions corresponding to the vehicle model in the data category is greater than the number of recommended positions corresponding to the vehicle model; wherein the target manner includes any one of: randomly, or sorting the number of recommended positions of the solution in order from large to small.
[0017] In some feasible examples, the processing unit is specifically used to use a solution as a recommended solution when the total number of solutions corresponding to the vehicle model in the data category is less than or equal to the number of recommended positions corresponding to the vehicle model.
[0018] In a third aspect, the present disclosure provides an electronic device, comprising: a memory and a processor, wherein the memory is used to store a computer program; and the processor is used to enable the electronic device to implement the recommendation method provided in the first aspect when executing the computer program.
[0019] In a fourth aspect, the present disclosure provides a computer-readable storage medium, comprising: a computer program is stored on the computer-readable storage medium, and when the computer program is executed by a computing device, the computing device implements the recommendation method provided in the first aspect above.
[0020] In a fifth aspect, the present disclosure provides a vehicle, comprising any one of the recommended devices provided in the second aspect.
[0021] In the present disclosure, the names of the above-mentioned recommended devices do not limit the devices or functional modules themselves. In actual implementation, these devices or functional modules may appear with other names. As long as the functions of each device or functional module are similar to those of the present disclosure, they fall within the scope of the claims of the present disclosure and their equivalent technologies.
[0022] These and other aspects of the present disclosure will become more apparent from the following description.
[0023] Compared with the prior art, the technical solution provided by the present invention has the following advantages:
[0024] In order to improve the accuracy of the recommendation results corresponding to the pending problem data that does not contain vehicle model information, the recommendation method provided by the present disclosure combines the total number of recommendation positions, the delivery ratio of each vehicle model, and the probability of occurrence of data categories in the historical problem data corresponding to each vehicle model, so as to determine the number of recommendation positions for each vehicle model. Afterwards, based on the number of recommendation positions for each vehicle model, solutions with the corresponding number of recommendation positions are found in the same data category corresponding to each vehicle model as recommendation solutions, and recommendation results are generated based on the recommendation solutions. Therefore, users can find recommendation solutions for the required vehicle models based on the recommendation results. Since the recommendation results include the recommendation solutions for each vehicle model in the same data category, the problem that the user needs to ask questions multiple times due to the lack of comprehensiveness of the recommended solutions provided is avoided. While improving the accuracy of the recommendation results, the user experience is improved. The problem of how to provide recommended response solutions to vehicle service personnel or directly generate recommended response solutions for users is solved. BRIEF DESCRIPTION OF THE DRAWINGS
[0025] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present disclosure and, together with the description, serve to explain the principles of the present disclosure.
[0026] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.
[0027] Figure 1 One of the flowcharts of the recommended method provided in the embodiment of the present disclosure;
[0028] Figure 2 A second flowchart of a recommended method provided in an embodiment of the present disclosure;
[0029] Figure 3 The third flowchart of the recommended method provided by the embodiment of the present disclosure;
[0030] Figure 4 A fourth flowchart of a recommended method provided in an embodiment of the present disclosure;
[0031] Figure 5 A fifth flowchart of a recommended method provided in an embodiment of the present disclosure;
[0032] Figure 6 A schematic diagram of the structure of a recommended device provided by an embodiment of the present disclosure;
[0033] Figure 7 A schematic diagram of the structure of a vehicle-mounted terminal provided in an embodiment of the present disclosure;
[0034] Figure 8 A schematic diagram of the structure of a computer program product provided in an embodiment of the present disclosure. DETAILED DESCRIPTION
[0035] In order to more clearly understand the above-mentioned objectives, features and advantages of the present disclosure, the scheme of the present disclosure will be further described below. It should be noted that the embodiments of the present disclosure and the features in the embodiments can be combined with each other without conflict.
[0036] In the following description, many specific details are set forth to facilitate a full understanding of the present disclosure, but the present disclosure may also be implemented in other ways different from those described herein; it is obvious that the embodiments in the specification are only part of the embodiments of the present disclosure, rather than all of the embodiments.
[0037] It should be noted that, in this article, relational terms such as "first" and "second" are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the existence of other identical elements in the process, method, article or device including the elements.
[0038] GPT in the embodiments of the present disclosure refers to Generative Pre-Trained Transformer (generative pre-trained Transformer model), which is an Internet-based deep learning model for text generation that can be trained with available data.
[0039] Ada in the disclosed embodiment is the latest model launched by OpenAI. It is a large-scale, multi-task language model that can perform a variety of natural language tasks, such as question answering, generation, classification, etc.
[0040] Davinci in the disclosed embodiment is the largest language model launched by OpenAI. It consists of 17.5 billion parameters and is one of the most advanced and powerful language models currently available.
[0041] Babbage in the disclosed embodiment is a medium-sized language model launched by OpenAI, which consists of 600 million parameters and can be used for generating text, answering questions and classification tasks, etc.
[0042] Curie in the disclosed embodiment is a medium-to-large language model launched by OpenAI. It consists of 1.3 billion parameters and can be used for tasks such as natural language generation, question answering and text classification.
[0043] The jsonl file in the embodiment of the present disclosure refers to a jsonlines file, which is a format that is convenient for storing structured data and can process one record at a time.
[0044] The log in the disclosed embodiment is a log, which is usually a record of a certain processing that has been completed by the system or some software for future reference. It does not have a fixed format and is usually a text file that can be opened with Notepad to view the content. Of course, it may be in other formats, and garbled characters will be displayed when opened directly.
[0045] Exemplarily, the recommendation method provided by the embodiment of the present disclosure is introduced by taking the execution subject of the recommendation method provided by the embodiment of the present disclosure as a server as an example.
[0046] S11, obtaining problem data to be processed, wherein the problem data to be processed does not include vehicle model information.
[0047] In some examples, when a user asks a salesperson or after-sales person, the salesperson can fill in the questions raised by the user (such as vehicle failure, body damage, maintenance, etc.) into a document, thereby obtaining data on pending issues.
[0048] Alternatively, when a user raises a question on the client, the user needs to fill in the corresponding data based on the document format provided by the client, so as to obtain the data of the question to be processed.
[0049] S12. Classify the problem data to be processed to obtain data categories corresponding to the problem data to be processed.
[0050] In some examples, in order to quickly find a solution to the problem data to be processed, it is necessary to classify the problem data to be processed, so as to obtain the data category corresponding to the problem data to be processed. For example, the problem data to be processed is input into the classification model for classification, and the data category corresponding to the problem data to be processed is obtained. The training process of the classification model is as follows:
[0051] The training data and the labeling results of the training data are obtained. The training data includes the log data of the customer service system (such as the system built by the automobile manufacturer for users to provide customer service), and the labeling results include the classification results of the problem data.
[0052] The training data is preprocessed (such as removing stop words, removing punctuation marks, converting uppercase and lowercase letters, etc.) to obtain the preprocessed target data.
[0053] Convert the target data into a target file.
[0054] Using the labeling results of the target file and the training file, the deep learning model (such as the Davinci model under the GPT framework, the Curie model under the GPT framework, the Babbage model under the GPT framework, or any of the Ada models under the GPT framework) is fine-tuned (prediction accuracy) to obtain a classification model.
[0055] It should be noted that when using the Davinci model under the GPT framework, the target file is a jsonl file. When using other models, the target file is in the file format specified by the other model.
[0056] In some examples, users can set data categories according to their needs, such as defining data categories into four data categories, namely major categories → minor categories → problem areas → specific problems, and save them in a classification dictionary. In this way, when classifying the problem data to be processed, the data classification corresponding to the problem data to be processed can be obtained by querying the classification dictionary. For example, the problem data to be processed is segmented to obtain at least one actual segmentation. The similarity between the actual segmentation and the theoretical segmentation corresponding to the data classification is calculated. Afterwards, the data classification corresponding to the theoretical segmentation with the highest similarity is used as the data classification of the problem data to be processed.
[0057] For example, the major category includes mechanical and electrical appliances, the minor category includes mechanical and electrical appliance repair, the problem areas include engine failure, vehicle compartment electrical appliances and vehicle body maintenance, and the specific problems include "poor starting", "oil leakage", "cylinder explosion", "flame failure", "headlights not on", "air conditioning not cooling", "audio failure", and "scratches", "grooves", "glass breakage" as examples, and the following classification dictionary is established:
[0058]
[0059] At this time, the theoretical segmentation includes one or more of mechanical and electrical appliances, mechanical and electrical appliance maintenance, engine failure, car electrical appliances, body maintenance, poor start, oil leakage, cylinder explosion, flameout, headlights not working, air conditioning not cooling, audio failure, scratches, grooves and glass damage.
[0060] For example, the major category includes parts, the minor category includes parts replacement, the problem areas include tire replacement, brake replacement and oil replacement, and the specific problems include "wear", "leakage", "breakdown", "bad brakes", "abnormal noise", "deterioration and expiration", and "low oil level". The following classification dictionary is established:
[0061]
[0062] At this time, the theoretical participles include: one or more of the following: parts, parts replacement, tire replacement, brake replacement, oil replacement, wear, leakage, breakage, poor braking, abnormal noise, deterioration and expiration, and low oil level.
[0063] S13. Based on the total number of recommended positions, the delivery ratio of each model, and the probability of occurrence of data categories in the historical problem data corresponding to each model, the number of recommended positions for each model is obtained.
[0064] In some examples, for a certain model among all the models currently delivered, the probability of occurrence of a data category in the historical problem data corresponding to a certain model is equal to the ratio of the total number of occurrences of data category A in the historical problem data corresponding to the model to the total number of occurrences of the historical problem data corresponding to the model. Wherein, data category A is the data category corresponding to the problem data to be processed in S12; after calculating separately for each model, the probability of occurrence of the data category in the historical problem data of each model can be obtained.
[0065] In some examples, the delivery ratio of each model can be obtained by taking the ratio of the delivery data of each model to the total delivery data. Then, based on the total number of recommended positions, the delivery ratio corresponding to each model, and the probability of occurrence of the data category in the historical problem data, the number of recommended positions for each model is obtained. For example, based on the product of the delivery ratio corresponding to the model and the probability of occurrence of the data category in the historical problem data corresponding to each model, the matching probability of each model is obtained. Based on the product of the matching probability and the total number of recommended positions, the number of recommended positions for each model is obtained.
[0066] Among them, the number of recommended positions
[0067] Among them, N(v i) represents the current delivery data of model A, Nvtotal) represents the sum of the delivery data of all models currently delivered, w(v si ) represents the probability of occurrence of the data category corresponding to the problem data in the historical problem data corresponding to vehicle model A, wvtotal) represents the total number of recommended positions, w(v i ) indicates the number of recommended positions.
[0068] It should be noted that when the product of the matching probability and the total number of recommended positions is not an integer, it is rounded up according to the principle of rounding.
[0069] For example, assume that there are 10 recommendation positions, and manufacturer A has 3 models on sale, namely model 1, model 2 and model 3. After calculating the delivery ratio, appearance probability, matching probability and number of recommendations of model 1, model 2 and model 3, respectively, they are shown in Table 1.
[0070] Table 1
[0071] Model Model 1 Model 2 Model 3 total Delivery ratio 1000 / 5000＝0.2 3000 / 5000＝0.6 1000 / 5000＝0.2 1 Probability 30％ 40％ 30％ 1 Matching probability 0.2×0.3＝0.06 0.6×0.4＝0.24 0.2*0.3＝0.06 0.36 Number of recommended positions 1(0.06×10) 2(0.24×10) 1(0.06*10) 4
[0072] In this way, the number of recommended positions corresponding to each type of vehicle can be obtained.
[0073] In some examples, the total number of recommended positions, the delivery ratio of each model, and the probability of occurrence of data categories in historical problem data corresponding to each model can be input into the recommendation model to obtain the number of recommended positions for each model.
[0074] Among them, the training process of the recommendation model is as follows:
[0075] Obtain training sample data and labeling results of the training sample data; wherein the training sample data includes historical delivery data of each vehicle model of manufacturer A and the occurrence probability of data categories in historical problem data corresponding to each vehicle model, and the labeling results include the number of recommended positions for the vehicle model.
[0076] The training sample data is input into the neural network model for learning, and the prediction results of the neural network model for the training sample data are obtained.
[0077] Based on the prediction results and labeling results, the network parameters of the neural network model are adjusted until the neural network model converges to obtain the recommendation model.
[0078] S14. Among the solutions corresponding to the vehicle type in the data category, select the solution with the number of recommended positions corresponding to the vehicle type as the recommended solution.
[0079] In some exemplary embodiments, different vehicle models correspond to the same data classification, but when different vehicle models correspond to the same data classification, their corresponding solutions may be the same or different. For ease of management, the recommended solution provided in the embodiment of the present disclosure allocates at least one solution for each vehicle model in each data classification.
[0080] In some examples, when the total number of solutions corresponding to the vehicle model in data category A is greater than the number of recommended positions corresponding to the vehicle model, the solution with the number of recommended positions is selected as the recommended solution in the solution in a target manner. The target manner includes any one of: randomly, or sorting the number of recommended times of the solution in descending order.
[0081] In some examples, when the total number of solutions corresponding to the vehicle type in the data category is less than or equal to the number of recommended positions corresponding to the vehicle type, the solution is used as a recommended solution.
[0082] For example, assume that the total number of solutions corresponding to vehicle type A in data category A is 3, namely solution 1, solution 2 and solution 3. The number of recommendations for solution 1 is greater than the number of recommendations for solution 2, and the number of recommendations for solution 2 is greater than the number of solutions for solution 3.
[0083] When the number of recommended positions for vehicle type A is 2, since the total number of solutions 3 is greater than the number of recommended positions 2, 2 solutions can be randomly selected from solution 1, solution 2, and solution 3 as the recommended solutions for vehicle type A. Alternatively, the solutions can be sorted by the number of recommendations, and then 2 solutions can be selected in order from high to low, such as solution 1 and solution 2 as the recommended solutions for vehicle type A.
[0084] When the number of recommended positions corresponding to vehicle type A is 4, since the total number of solutions 3 is less than the number of recommended positions 4, solution 1, solution 2 and solution 3 can all be used as recommended solutions for vehicle type A.
[0085] S15. Generate recommendation results based on the recommendation solutions corresponding to each vehicle model.
[0086] From the above, it can be seen that the recommendation method provided by the present disclosure can determine the number of recommendation positions for each model by combining the total number of recommendation positions, the delivery ratio of each model currently delivered, and the probability of occurrence of the data category in the historical problem data corresponding to the model. Afterwards, based on the number of recommendation positions for each model, a solution with a corresponding number of recommendation positions is found in the same data category corresponding to each model as a recommendation solution, and a recommendation result is generated based on the recommendation solution. Therefore, the user can find the recommendation solution for the required model based on the recommendation results. Since the recommendation results include the recommendation solution for each model in the same data category, it avoids the problem that the user needs to ask questions multiple times because the provided recommendation solution is not comprehensive enough, thereby improving the accuracy of the recommendation results and improving the user experience.
[0087] In some possible implementation examples, combined with Figure 1 ,like Figure 2 As shown, the above S12 can be specifically implemented through the following S120-S122.
[0088] S120, preprocessing the problem data to be processed to obtain preprocessed target data, wherein the preprocessing includes: removing stop words, removing punctuation marks, and converting uppercase and lowercase letters.
[0089] S121. Classify the target data to obtain the data category corresponding to the target data.
[0090] S122. Based on the data category corresponding to the target data, determine that the data category corresponding to the problem data to be processed is the data category corresponding to the target data.
[0091] It can be seen from the above that the recommendation method provided by the embodiment of the present disclosure can remove useless data in the problem data to be processed by preprocessing the problem data to be processed, so as to improve the accuracy of the data category of the problem data to be processed.
[0092] In some possible implementation examples, combined with Figure 1 ,like Figure 3 As shown, the above S13 can be specifically implemented through the following S130 and S131.
[0093] S130. Based on the ratio of the delivery data of each vehicle model to the total delivery data, obtain the delivery ratio of each vehicle model.
[0094] S131. Based on the total number of recommended positions, the delivery ratio, and the probability of occurrence of data categories in the historical problem data corresponding to each vehicle model, the number of recommended positions for each vehicle model is obtained respectively.
[0095] From the above, it can be seen that the recommendation method provided by the embodiment of the present disclosure, by combining the delivery data of the vehicle model and the data category of the problem data to be processed, can provide users with a full range of recommendation solutions, thereby avoiding the need for users to make multiple inquiries due to the recommendation solutions provided being not comprehensive enough, thereby improving the user experience.
[0096] In some possible implementation examples, combined with Figure 3 ,like Figure 4 As shown, the above S131 can be specifically implemented through the following S1310 and S1311.
[0097] S1310. Based on the product of the delivery ratio and the occurrence probability of the data category in the historical problem data corresponding to each model, the matching probability of each model is obtained.
[0098] S1311. Based on the product of the matching probability and the total number of recommended positions, the number of recommended positions for each vehicle type is obtained.
[0099] As can be seen from the above, the recommendation method provided by the embodiment of the present disclosure, since the problem data to be processed does not contain vehicle model information, can find the recommendation schemes for different vehicle models of the same data category by combining the delivery data of the vehicle model and the data category of the problem data to be processed, and generate recommendation results based on the recommendation schemes. Then, the user can find the recommendation schemes for the required vehicle models based on the recommendation results, avoiding the need for the user to make multiple inquiries due to the lack of comprehensiveness of the recommended schemes provided, thereby improving the user experience.
[0100] In some possible implementation examples, combined with Figure 1 ,like Figure 5 As shown, the above S14 can be specifically implemented through the following S140.
[0101] S140: When the total number of solutions corresponding to the vehicle model in the data category is greater than the number of recommended positions corresponding to the vehicle model, a solution with the number of recommended positions is selected as a recommended solution in the solution in accordance with a target method. The target method includes any one of: randomly, or sorting the number of recommended times of the solution in descending order.
[0102] From the above, it can be seen that the recommendation method provided by the embodiment of the present disclosure, since the problem data to be processed does not contain vehicle model information, can find the recommendation schemes for the same data category in different vehicle models by combining the delivery data of the vehicle model and the data category of the problem data to be processed, and generate recommendation results based on the recommendation schemes. Since there is a difference between the total number of solutions corresponding to different data categories and the number of recommendation positions corresponding to the vehicle model. Therefore, it is necessary to select a suitable solution as the recommended scheme based on the total number of solutions corresponding to different data categories and the number of recommendation positions corresponding to the vehicle model. Then, a recommendation result is generated based on the recommendation scheme. In this way, users can find the recommended scheme for the required vehicle model based on the recommendation results, avoiding the need for users to ask multiple times due to the lack of comprehensiveness of the recommended scheme provided, thereby improving the user experience.
[0103] In some possible implementation examples, combined with Figure 1 ,like Figure 5 As shown, the above S14 can be specifically implemented through the following S141.
[0104] S141. When the total number of solutions corresponding to the vehicle type in the data category is less than or equal to the number of recommended positions corresponding to the vehicle type, the solution is used as a recommended solution.
[0105] From the above, it can be seen that the recommendation method provided by the embodiment of the present disclosure, since the problem data to be processed does not contain vehicle model information, can find the recommendation schemes for the same data category in different vehicle models by combining the delivery data of the vehicle model and the data category of the problem data to be processed, and generate recommendation results based on the recommendation schemes. Since there is a difference between the total number of solutions corresponding to different data categories and the number of recommendation positions corresponding to the vehicle model. Therefore, it is necessary to select a suitable solution as the recommended scheme based on the total number of solutions corresponding to different data categories and the number of recommendation positions corresponding to the vehicle model. Then, a recommendation result is generated based on the recommendation scheme. In this way, users can find the recommended scheme for the required vehicle model based on the recommendation results, avoiding the need for users to ask multiple times due to the lack of comprehensiveness of the recommended scheme provided, thereby improving the user experience.
[0106] The above mainly introduces the solution provided by the embodiment of the present disclosure from the perspective of the method. In order to achieve the above functions, it includes hardware structures and / or software modules corresponding to the execution of each function. Those skilled in the art should easily realize that, in combination with the units and algorithm steps of each example described in the embodiments disclosed herein, the present disclosure can be implemented in the form of hardware or a combination of hardware and computer software. Whether a function is executed in the form of hardware or computer software driving hardware 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 to exceed the scope of the present disclosure.
[0107] The embodiments of the present disclosure may divide the functional modules of the recommendation device according to the above method examples. For example, each functional module may be divided according to each function, or two or more functions may be integrated into one processing module. The above integrated modules may be implemented in the form of hardware or in the form of software functional modules. It should be noted that the division of modules in the embodiments of the present disclosure is schematic and is only a logical functional division. There may be other division methods in actual implementation.
[0108] like Figure 6 , which is a schematic diagram of the structure of a recommendation device 10 provided in an embodiment of the present disclosure, includes an acquisition unit 101 and a processing unit 102 .
[0109] The acquisition unit 101 is used to acquire the problem data to be processed; wherein the problem data to be processed does not contain vehicle model information; the processing unit 102 is used to classify the problem data to be processed acquired by the acquisition unit 101 to obtain the data category corresponding to the problem data to be processed; the processing unit 102 is also used to obtain the number of recommended positions for each vehicle model based on the total number of recommended positions, the delivery ratio of each vehicle model, and the probability of occurrence of the data category in the historical problem data corresponding to each vehicle model; the processing unit 102 is also used to select the solution with the number of recommended positions corresponding to the vehicle model in the solution corresponding to the data category as the recommended solution; the processing unit 102 is also used to generate a recommendation result based on the recommended solution corresponding to each vehicle model.
[0110] In some implementable examples, the processing unit 102 is specifically used to preprocess the problem data to be processed obtained by the acquisition unit 101 to obtain preprocessed target data; wherein the preprocessing includes: removing stop words, removing punctuation marks, and one or more of uppercase and lowercase conversion; the processing unit 102 is specifically used to classify the target data to obtain a data category corresponding to the target data; the processing unit 102 is specifically used to determine, based on the data category corresponding to the target data, that the data category corresponding to the problem data to be processed is the data category corresponding to the target data.
[0111] In some feasible examples, the processing unit 102 is specifically used to obtain the delivery ratio of each model based on the ratio of the delivery data of each model to the total delivery data; the processing unit 102 is specifically used to obtain the number of recommended positions for each model based on the total number of recommended positions, the delivery ratio and the occurrence probability of the data category in the historical problem data corresponding to each model.
[0112] In some feasible examples, the processing unit 102 is specifically used to obtain the matching probability of each vehicle model based on the product of the delivery ratio and the occurrence probability of the data category in the historical problem data corresponding to each vehicle model; the processing unit 102 is specifically used to obtain the number of recommended positions for each vehicle model based on the product of the matching probability and the total number of recommended positions.
[0113] In some feasible examples, the processing unit 102 is specifically used to select a solution with the same number of recommended positions as a recommended solution in a target manner when the total number of solutions corresponding to the vehicle type in the data category is greater than the number of recommended positions corresponding to the vehicle type; wherein the target manner includes any one of: randomly, or sorting the number of recommended positions of the solution in order from large to small.
[0114] In some feasible examples, the processing unit 102 is specifically configured to use a solution as a recommended solution when the total number of solutions corresponding to the vehicle type in the data category is less than or equal to the number of recommended positions corresponding to the vehicle type.
[0115] Among them, all relevant contents of each step involved in the above method embodiment can be referred to the functional description of the corresponding functional module, and its role will not be repeated here.
[0116] Of course, the recommendation device 10 provided in the embodiment of the present disclosure includes but is not limited to the above modules, for example, the recommendation device 10 may also include a storage unit 103. The storage unit 103 may be used to store the program code of the recommendation device 10, and may also be used to store data generated by the recommendation device 10 during operation, such as data in a write request.
[0117] Figure 7 A schematic diagram of the structure of a vehicle-mounted terminal provided in an embodiment of the present disclosure is shown in FIG. Figure 7 As shown, the vehicle-mounted terminal may include: at least one processor 51 , a memory 52 , a communication interface 53 and a communication bus 54 .
[0118] Combine the following Figure 7 The following is a detailed introduction to the various components of the vehicle terminal:
[0119] The processor 51 is the control center of the electronic device 10, and may be a processor or a general term for multiple processing elements. For example, the processor 51 is a central processing unit (CPU), or an application specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of the present disclosure, such as one or more DSPs, or one or more field programmable gate arrays (FPGAs).
[0120] In a specific implementation, as an embodiment, the processor 51 may include one or more CPUs, such as Figure 7 Also, as an embodiment, the electronic device may include multiple processors, such as Figure 7 51 and 55 are shown in FIG. Each of these processors may be a single-core processor (Single-CPU) or a multi-core processor (Multi-CPU). The processor here may refer to one or more devices, circuits, and / or processing cores for processing data (e.g., computer program instructions).
[0121] The memory 52 may be a read-only memory (ROM) or other types of static storage devices that can store static information and instructions, a random access memory (RAM) or other types of dynamic storage devices that can store information and instructions, or an electrically erasable programmable read-only memory (EEPROM), a compact disc read-only memory (CD-ROM) or other optical disc storage, optical disc storage (including compressed optical disc, laser disc, optical disc, digital versatile disc, Blu-ray disc, etc.), a magnetic disk storage medium or other magnetic storage device, or any other medium that can be used to carry or store the desired program code in the form of instructions or data structures and can be accessed by a computer, but is not limited thereto. The memory 52 may exist independently and be connected to the processor 51 via a communication bus 54. The memory 52 may also be integrated with the processor 51.
[0122] In a specific implementation, the memory 52 is used to store the data in the present disclosure and execute the software program in the present disclosure. The processor 51 can execute various functions of the air conditioner by running or executing the software program stored in the memory 52 and calling the data stored in the memory 52.
[0123] The communication interface 53 uses any transceiver-like device to communicate with other devices or communication networks, such as Radio Access Network (RAN), Wireless Local Area Networks (WLAN), terminals, the cloud, etc. The communication interface 53 may include an acquisition unit to implement the acquisition function.
[0124] The communication bus 54 may be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. The bus may be divided into an address bus, a data bus, a control bus, etc.
[0125] For ease of representation, Figure 7 Only one thick line is used in the diagram, but this does not mean that there is only one bus or only one type of bus.
[0126] As an example, combining Figure 6 The function implemented by the acquisition unit 101 in the recommendation device 10 is similar to Figure 7 The function of the communication interface 53 in the recommendation device 10 is the same as that of the processing unit 102 in the recommendation device 10. Figure 7 The function of the processor 51 in the recommendation device 10 is the same as that of the storage unit 103 in the recommendation device 10. Figure 7 The function of the memory 52 in is the same.
[0127] Another embodiment of the present disclosure further provides a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a computing device, the computing device executes the vehicle collision avoidance method shown in the above method embodiment.
[0128] In some embodiments, the disclosed methods may be implemented as computer program instructions encoded in a machine-readable format on a computer-readable storage medium or on other non-transitory media or articles of manufacture.
[0129] Figure 8A conceptual partial view of a computer program product provided by an embodiment of the present disclosure is schematically shown, wherein the computer program product includes a computer program for executing a computer process on a computing device.
[0130] In one embodiment, the computer program product is provided using a signal bearing medium 410. The signal bearing medium 410 may include one or more program instructions, which when executed by one or more processors may provide the above-mentioned Figure 1 Thus, for example, reference Figure 1 In the embodiment shown in , one or more features of S11-S15 can be undertaken by one or more instructions associated with the signal bearing medium 410. In addition, Figure 8 The program instructions in also describe example instructions.
[0131] In some examples, signal bearing medium 410 may include computer readable medium 411, such as, but not limited to, a hard drive, a compact disk (CD), a digital video disk (DVD), a digital tape, a memory, a read-only memory (ROM), or a random access memory (RAM), and the like.
[0132] In some implementations, signal bearing medium 410 may include computer recordable medium 412 such as, but not limited to, memory, read / write (R / W) CD, R / W DVD, and the like.
[0133] In some implementations, signal bearing medium 410 may include communication medium 413 such as, but not limited to, digital and / or analog communication media (eg, fiber optic cables, waveguides, wired communication links, wireless communication links, etc.).
[0134] Signal bearing medium 410 may be communicated by a wireless form of communication medium 413 (eg, wireless communication medium complying with IEEE 802.41 standard or other transmission protocol). The one or more program instructions may be, for example, computing device executable instructions or logic implementing instructions.
[0135] In some examples, such as for Figure 6 The described recommendation apparatus 10 may be configured to provide various operations, functions, or actions in response to one or more program instructions via the computer-readable medium 411 , the computer-recordable medium 412 , and / or the communication medium 413 .
[0136] Through the description of the above implementation methods, technical personnel in the relevant field can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional modules is used as an example. In actual applications, the above-mentioned functions can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above.
[0137] In the several embodiments provided in the present disclosure, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the modules or units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another device, 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, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.
[0138] The units described as separate components may or may not be physically separated, and the components shown as units may be one physical unit or multiple physical units, that is, they may be located in one place or distributed in multiple different places. Some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.
[0139] In addition, each functional unit in each embodiment of the present disclosure may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.
[0140] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a readable storage medium. Based on this understanding, the technical solution of the embodiment of the present disclosure is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for a device (which can be a single-chip microcomputer, chip, etc.) or a processor (processor) to perform all or part of the steps of the method described in each embodiment of the present disclosure. The aforementioned storage medium includes: various media that can store program codes, such as USB flash drives, mobile hard drives, ROM, RAM, magnetic disks or optical disks.
[0141] The above description is only a specific embodiment of the present disclosure, so that those skilled in the art can understand or implement the present disclosure. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present disclosure. Therefore, the present disclosure will not be limited to the embodiments described herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.
Claims
1. A recommendation method, characterized in that: include: Obtaining problem data to be processed; wherein the problem data to be processed does not include vehicle model information; Classifying the problem data to be processed to obtain data categories corresponding to the problem data to be processed; Based on the total number of recommended positions, the delivery ratio of each model, and the probability of occurrence of the data category described in the historical problem data corresponding to each model, the number of recommended positions for each model is obtained respectively; Among the solutions corresponding to the data category, the solution with the number of recommended positions corresponding to the vehicle type is selected as the recommended solution; Based on the recommendation scheme corresponding to each of the vehicle models, a recommendation result is generated.
2. The recommendation method according to claim 1, characterized in that: The step of classifying the problem data to be processed to obtain the data category corresponding to the problem data to be processed includes: Preprocessing the problem data to be processed to obtain preprocessed target data; wherein the preprocessing includes: removing stop words, removing punctuation marks, and converting uppercase and lowercase letters; Classifying the target data to obtain a data category corresponding to the target data; Based on the data category corresponding to the target data, the data category corresponding to the to-be-processed problem data is determined to be the data category corresponding to the target data.
3. The recommendation method according to claim 1, characterized in that: The number of recommended positions for each model is obtained based on the total number of recommended positions, the delivery ratio of each model, and the occurrence probability of the data category in the historical problem data corresponding to each model, including: Based on the ratio of the delivery data of each vehicle model to the sum of the delivery data, respectively obtaining the delivery ratio of each vehicle model; Based on the total number of recommended positions, the delivery ratio and the occurrence probability of the data category in the historical problem data corresponding to each model, the number of recommended positions for each model is obtained respectively.
4. The recommendation method according to claim 3, characterized in that: The number of recommended positions for each vehicle model is obtained based on the total number of recommended positions, the delivery ratio, and the occurrence probability of the data category in the historical problem data corresponding to each vehicle model, including: Based on the product of the delivery ratio and the occurrence probability of the data category in the historical problem data corresponding to each model, the matching probability of each model is obtained respectively; Based on the product of the matching probability and the total number of recommended positions, the number of recommended positions for each vehicle type is obtained respectively.
5. The recommendation method according to claim 1, characterized in that: The step of selecting, from among the solutions corresponding to the data category for the vehicle type, a solution having a number of recommended positions corresponding to the vehicle type as a recommended solution includes: When the total number of solutions corresponding to the vehicle type in the data category is greater than the number of recommended positions corresponding to the vehicle type, solutions with the number of recommended positions are selected as recommended solutions from the solutions in a target manner; wherein the target manner includes any one of: randomly, or sorting the number of recommendations of the solutions in order from large to small.
6. The recommendation method according to claim 1, characterized in that: The step of selecting, from among the solutions corresponding to the data category for the vehicle type, a solution having a number of recommended positions corresponding to the vehicle type as a recommended solution includes: When the total number of solutions corresponding to the vehicle type in the data category is less than or equal to the number of recommended positions corresponding to the vehicle type, the solution is used as a recommended solution.
7. A recommendation device, characterized in that: include: An acquisition unit, used for acquiring problem data to be processed; wherein the problem data to be processed does not include vehicle model information; A processing unit, configured to classify the problem data to be processed acquired by the acquisition unit to obtain a data category corresponding to the problem data to be processed; The processing unit is further configured to obtain the number of recommended positions for each vehicle model based on the total number of recommended positions, the delivery ratio of each vehicle model, and the occurrence probability of the data category in the historical problem data corresponding to each vehicle model; The processing unit is further used to select a solution with a number of recommended positions corresponding to the vehicle model from among the solutions corresponding to the data category, as a recommended solution; The processing unit is further used to generate a recommendation result based on the recommendation solution corresponding to each of the vehicle models.
8. An electronic device, characterized in that: include: A memory and a processor, wherein the memory is used to store a computer program; and the processor is used to enable the electronic device to implement the recommendation method described in any one of claims 1 to 6 when executing the computer program.
9. A computer-readable storage medium, characterized in that: include: The computer-readable storage medium stores a computer program, and when the computer program is executed by a computing device, the computing device implements the recommendation method according to any one of claims 1 to 6.