Automatic Response Method, Terminal and Storage Medium Based on Power Trading

Abstract

The present invention relates to an automatic response method, terminal and storage medium based on power trading, which includes: S101: performing operations of merging similar questions or inserting knowledge points in a knowledge base through created questions, question keywords and user instructions; S102: setting weights for user type parameters corresponding to knowledge points, performing word segmentation on the received user question sentence and obtaining user type parameters; S103: screening and matching knowledge points from the knowledge base according to the word segmentation, and sorting the knowledge points and obtaining an optimal result through the user type parameters corresponding to the user question sentence and the weights corresponding to the user type parameters of the knowledge points; S104: replying to the user question sentence according to the recommended response corresponding to the optimal result. The present invention reduces the number of customer service staff, reduces labor costs, and can handle a large number of users simultaneously, with high reply efficiency, fast reply speed, improves service efficiency and user experience, and reduces customer acquisition costs.

Description

Technical Field

[0001] The present invention belongs to the technical field of online Q&A, and particularly relates to an automatic answering method, a terminal and a storage medium based on power trading. Background Art

[0002] The reform of the power selling side is one of the core contents of the new round of power system reform. In the new generation of power retail trading scenarios, more and more general industrial and commercial users participate in the power marketization trading. Among them, in the trading process, power selling companies often encounter the scenario of users' online consultation.

[0003] In order to reply to users' online consultation, power selling companies adopt the method of setting up artificial customer service for reply. This reply method requires setting up a large number of customer service staff, increasing the labor cost. Moreover, the manual processing method is inefficient and difficult to handle the situation where a large number of users consult at the same time, prone to problems such as low reply efficiency and long reply time, with low service efficiency and reduced user experience. Therefore, how to overcome the deficiencies of the existing technology is an urgent problem to be solved in the current technical field of online Q&A. Summary of the Invention

[0004] The purpose of the present invention is to solve the deficiencies of the existing technology and provide an automatic answering method, a terminal and a storage medium based on power trading.

[0005] To achieve the above purpose, the technical solution adopted by the present invention is as follows:

[0006] An automatic answering method based on power trading, comprising the following steps:

[0007] S101: Create a knowledge base including questions, question keywords and recommended answers according to power user tags, and perform operations of merging similar questions or inserting knowledge points in the knowledge base through the questions, question keywords and user instructions. The knowledge points are associated with the power user tags, and the questions, question keywords and recommended answers correspond to each other;

[0008] S102: Set weights for the user type parameters corresponding to the knowledge points, perform word segmentation on the received user questions, and perform user analysis to obtain user type parameters;

[0009] S103: Screen and match the knowledge points from the knowledge base according to the obtained word segmentation, and sort the knowledge points through the user type parameters corresponding to the user questions and the weights corresponding to the user type parameters of the knowledge points, and obtain the optimal result based on the sorting;

[0010] S104: Reply to the user question according to the recommended answer corresponding to the optimal result.

[0011] Further, preferably, before the step of creating a knowledge base including questions, question keywords, and recommended responses based on the power user tags, the following steps are also included:

[0012] Obtain the power user tags, find the usage frequency corresponding to each power user tag, and determine the sorting of the power user tags for creating the knowledge base according to the sorting of the usage frequency.

[0013] Further, preferably, the step of performing similar question merging or knowledge point insertion operations in the knowledge base through the questions, question keywords, and user instructions specifically includes:

[0014] Judge whether there are similar questions in the knowledge base that are repeated with the questions and question keywords;

[0015] If so, perform similar question merging or knowledge point insertion operations according to the user instructions;

[0016] If not, insert the questions, question keywords, and recommended responses into the knowledge base as new knowledge points.

[0017] Further, preferably, the step of performing similar question merging or knowledge point insertion operations according to the user instructions specifically includes:

[0018] Judge whether similar question merging operations are allowed according to the user instructions;

[0019] If so, merge the similar questions with the questions, question keywords, and recommended responses into one knowledge point;

[0020] If not, insert the questions, question keywords, and recommended responses into the knowledge base as a new knowledge point.

[0021] Further, preferably, the step of performing word segmentation on the received user question sentence and performing user analysis to obtain user type parameters specifically includes:

[0022] Obtain the user corresponding to the user question sentence, obtain user type parameters through the user analysis result, and perform word segmentation on the user question sentence through the thesaurus.

[0023] Further, preferably, the user type parameters include whether the user has an agency relationship, whether the user has an agency relationship with the current electricity selling company, the user's electricity consumption type, whether the package order in the user's delivery is approaching the expiration date, and whether the user has tags in this electricity selling company.

[0024] Further, preferably, the step of sorting the knowledge points through the user type parameters corresponding to the user question sentence and the weights corresponding to the user type parameters of the knowledge points specifically includes:

[0025] Obtain the proxy relationship weight score, the current electricity sales company proxy relationship weight score, the electricity consumption type weight score, the package expiration option weight score, the user label weight score, and the weighted score according to the user type parameter corresponding to the user question and the weight corresponding to the user type parameter of the knowledge point. Obtain the weight score of each knowledge point according to the sum of the weight scores, and sort the knowledge points based on the weight scores.

[0026] Further, preferably, the step of replying to the user question according to the recommended reply corresponding to the optimal result specifically includes:

[0027] Obtain the recommended reply corresponding to the optimal result, and determine whether an adjustment instruction is received;

[0028] If so, reply to the user question according to the adjusted answer;

[0029] If not, reply to the user question according to the recommended reply corresponding to the optimal result.

[0030] The present invention also provides an intelligent terminal, including a memory, a processor, and a computer program stored on the memory and executable on the processor. The processor, when executing the program, implements the steps of the automatic reply method based on power trading as described above.

[0031] The present invention further provides a non-transitory computer-readable storage medium, on which a computer program is stored. The computer program, when executed by a processor, implements the steps of the automatic reply method based on power trading according to any one of claims 1 to 8.

[0032] In the present invention, the power user label refers to a label manually defined by the electricity sales company according to the characteristics of the customer, such as large customer, often overusing, etc.

[0033] In the present invention, the user instruction is issued by the system administrator. The adjustment instruction is issued by the manual customer service.

[0034] In the present invention, the expiration option is preferably set to the last delivery month of the package, which is the current month.

[0035] Compared with the prior art, the beneficial effects of the present invention are:

[0036] An automatic reply method, terminal, and storage medium based on power trading according to the present invention create corresponding knowledge points in the knowledge base according to different power user labels, and reply according to the user type parameter and the knowledge points screened and matched by word segmentation after receiving the user question, which can automatically realize the effective identification and reply to the user question, reduce the number of customer services, reduce the labor cost, and can simultaneously handle a large number of users, with high reply efficiency, fast reply speed, improved service efficiency and user experience, and reduced customer acquisition cost. Brief Description of the Drawings

[0037] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required for the description of the embodiments or the prior art. Obviously, the drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0038] Figure 1 It is a flowchart of the automatic response method based on power trading of the present invention;

[0039] Figure 2 It is a flowchart of the knowledge base creation in the automatic response method based on power trading of the present invention;

[0040] Figure 3 It is a flowchart of the user consultation reply in the automatic response method based on power trading of the present invention;

[0041] Figure 4 It is a structural diagram of an embodiment of the intelligent terminal of the present invention. Detailed Description of the Embodiments

[0042] The following further describes the present invention in detail in conjunction with the embodiments.

[0043] Those skilled in the art will understand that the following embodiments are only used to illustrate the present invention and should not be construed as limiting the scope of the present invention. For those not specified in the embodiments regarding specific technologies or conditions, they shall be carried out according to the technologies or conditions described in the literature in this field or according to the product specifications. For those materials or equipment not specified with the manufacturer, they are all conventional products that can be obtained by purchase.

[0044] Those skilled in the art of this technology can understand that unless specifically stated, the singular forms "a", "an", "the" and "said" used herein may also include the plural forms. It should be further understood that the term "comprising" used in the specification of the present invention means the presence of the described features, integers, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components and / or their groups.

[0045] Those skilled in the art of this technology can understand that unless otherwise defined, all terms (including technical terms and scientific terms) used herein have the same meaning as the general understanding of those of ordinary skill in the art in the field to which the present invention belongs. It should also be understood that those terms defined in a general dictionary should be understood to have a meaning consistent with the meaning in the context of the prior art and will not be interpreted with an idealized or overly formal meaning unless defined as such here.

[0046] Please refer to Figures 1 to 3 , in which Figure 1 is a flowchart of an embodiment of the automatic response method based on power trading according to the present invention; Figure 2 is a flowchart of an embodiment of knowledge base creation in the automatic response method based on power trading according to the present invention; Figure 3 is a flowchart of an embodiment of user consultation reply in the automatic response method based on power trading according to the present invention. In combination with Figures 1 to 3 the automatic response method based on power trading according to the present invention will be described in detail.

[0047] In this embodiment, the device that executes the automatic response method based on power trading is an intelligent terminal, and the intelligent terminal can be a computer, an intelligent terminal, a tablet computer, a cloud platform, a server, and other intelligent terminals capable of creating a knowledge base and replying to user consultations.

[0048] Among them, the automatic response method based on power trading includes:

[0049] S101: Create a knowledge base including questions, question keywords, and recommended responses according to power user tags, and perform operations of merging similar questions or inserting knowledge points in the knowledge base through questions, question keywords, and user instructions. The knowledge points are associated with power user tags, and the questions, question keywords, and recommended responses correspond to each other.

[0050] In this embodiment, before the step of creating a knowledge base including questions, question keywords, and recommended responses according to power user tags, it also includes: obtaining power user tags, and searching for the usage frequency corresponding to each power user tag, and determining the sorting of the power user tags for creating the knowledge base according to the sorting of the usage frequency. The higher the usage frequency, the higher the sorting. The circuit user tags preferentially used for creating the knowledge base are determined by sorting, and the higher the sorting, the higher the priority.

[0051] Among them, power user tags include customer classifications such as VIP customers, new customers, and long-term cooperative customers, and can be set accordingly according to the needs of the power sales company.

[0052] In other embodiments, power user tags may also include residential electricity consumption, commercial electricity consumption, industrial electricity consumption, residential areas, and other classification information related to the questions raised by users.

[0053] In a specific embodiment, the intelligent terminal obtains power user tag data, puts the power user tag data into a tag pool, obtains the number of times different power user tags in the tag pool are used by users, and sorts the power user tags using the number of times as the usage frequency. Among them, the sorting uses the bubble sorting method for tag sorting.

[0054] The steps for merging similar questions or inserting knowledge points in the knowledge base based on questions, question keywords, and user instructions specifically include: determining whether there are similar questions in the knowledge base that are repeated with the questions and question keywords; if so, performing operations for merging similar questions or inserting knowledge points according to the user instructions; if not, inserting the questions, question keywords, and recommended responses as new knowledge points into the knowledge base.

[0055] Among them, the steps for performing operations for merging similar questions or inserting knowledge points according to the user instructions specifically include: determining whether the operation of merging similar questions is allowed according to the user instructions; if so, merging the similar questions with the questions, question keywords, and recommended responses into one knowledge point; if not, inserting the questions, question keywords, and recommended responses as a new knowledge point into the knowledge base.

[0056] When performing operations for merging similar questions or inserting new knowledge points, corresponding timestamps are generated to facilitate recording the operation time.

[0057] In a specific embodiment, a knowledge base is created according to power user tags, questions, question keywords, and recommended responses related to the power user tags are created in the knowledge base, and historical knowledge points are searched in the knowledge base according to the created questions and question keywords. Determine whether similar questions are found in the historical knowledge points. If similar questions are found in the historical search (that is, check whether there is a recommended response for similar questions already configured in the existing knowledge base, and if the keyword repetition rate is relatively high, it is regarded as a similar question), then display a prompt recommending to merge the similar questions with the created questions. If the user (system administrator) rejects this operation, then insert the created questions, question keywords, and recommended responses as new knowledge points into the knowledge base and generate a timestamp. If not rejected, then merge the similar questions with the created questions to form one knowledge point and update the timestamp of this knowledge point. If no similar questions are found, insert the created questions, question keywords, and recommended responses as new knowledge points into the knowledge base and generate a timestamp.

[0058] The knowledge base is a collection of all knowledge points. Each question corresponds to at least one knowledge point, and users can modify, delete, or add knowledge points according to their own needs.

[0059] S102: Set weights for the user type parameters corresponding to the knowledge points, perform word segmentation on the received user questions, and perform user analysis to obtain user type parameters.

[0060] The user type parameters include whether the user has an agency relationship, whether the user has an agency relationship with the current electricity selling company, the user's electricity consumption type, whether the package order in the user's delivery is approaching its expiration date, and whether the user has tags in this electricity selling company. Among them, different weights are set for different user type parameters according to the relevance between the knowledge points and the user type parameters, which can be set according to the actual situation, and the present invention does not limit this. Among them, the electricity consumption types include large electricity consumption users, large deviation users, and other electricity consumption types.

[0061] The steps of performing word segmentation on the received user question sentence and performing user analysis to obtain user type parameters specifically include: obtaining the user corresponding to the user question sentence, obtaining user type parameters through the user analysis result, and performing word segmentation on the user question sentence through a thesaurus.

[0062] S103: Screen for matching knowledge points from the knowledge base according to the obtained word segmentation, and sort the knowledge points through the user type parameters corresponding to the user question sentence and the weights corresponding to the user type parameters of the knowledge points, and obtain the optimal result based on the sorting.

[0063] After obtaining the word segmentation, match the word segmentation with the question keywords of the knowledge points in the knowledge base, obtain the question keywords with a matching degree greater than the preset value for the word segmentation, and determine the knowledge points corresponding to the question keywords as the matching knowledge points.

[0064] The steps of sorting the knowledge points through the user type parameters corresponding to the user question sentence and the weights corresponding to the user type parameters of the knowledge points specifically include: obtaining the agency relationship weight score, the current electricity selling company agency relationship weight score, the electricity consumption type weight score, the package approaching expiration weight score, the user tag weight score, and the weighted score according to the user type parameters corresponding to the user question sentence and the weights corresponding to the user type parameters of the knowledge points, obtaining the weight score of each knowledge point according to the sum of the weight scores, and sorting the knowledge points based on the weight scores. Among them, the weight score is the weight of the user type parameter. The weighted score is the score of this knowledge point compared to the screened knowledge points. Determine the knowledge point with the highest weight score as the optimal result.

[0065] In a specific embodiment, weight calculation and sorting are performed on the answers screened from the knowledge base according to the user type parameters, and the optimal result is recommended. The weight calculation method is that the answer weight score = agency relationship weight score + current electricity selling company agency relationship weight score + ∑ electricity consumption type weight score + package approaching expiration weight score + ∑ user tag weight score + ∑ weighted score, and the answer weight score is the weight score of the screened knowledge point. Note: The weighted score only adds weight scores to the same keywords and the same user characteristics, and is an independent additional score item, and the score is configured manually, and the present invention does not limit this.

[0066] The steps of replying to the user's question according to the recommended response corresponding to the optimal result specifically include: obtaining the recommended response corresponding to the optimal result, and determining whether an adjustment instruction is received; if so, replying to the user's question according to the adjusted answer; if not, replying to the user's question according to the recommended response corresponding to the optimal result.

[0067] Among them, after replying to the user's question according to the adjusted answer, obtain the adjustment method. If it is to reply with a knowledge point that is not the first-ranked in the selection and sorting, increase the weight score of this knowledge point, that is, set the weighted score of this knowledge point. If it is to reply after editing the reply, generate a new knowledge point according to the reply information, and use this knowledge point to replace the knowledge point before editing in the knowledge base.

[0068] In a specific embodiment, the adjustment instruction is obtained through the online intervention of the artificial customer service. After the intelligent terminal obtains the optimal result, it makes a recommendation according to the recommended response of the optimal result. The artificial customer service views the recommended answer. If the artificial customer service does not intervene online, the system makes an automatic response and the process ends. If the artificial customer service adjusts the answer and makes a response, the process ends. Among them, the adjustment methods include: 1. The customer service selects the answer with secondary sorting and makes a response, and the knowledge point corresponding to this answer increases the weight score for the user type parameter and keywords of this user (only increases the weight score for the same keywords and the same user characteristics, an independent bonus item). 2. The artificial customer service edits the answer and then makes a response, generating a new knowledge point in the knowledge base (replaces the old knowledge point with the new knowledge point in the knowledge base).

[0069] The automatic response method based on power trading according to the present invention creates corresponding knowledge points in the knowledge base according to different power user tags, and replies according to the user type parameters and the knowledge points filtered and matched by word segmentation after receiving the user's question, which can automatically realize the effective recognition and response to the user's question, reduce the number of customer services, reduce the labor cost, and can handle a large number of users at the same time, with high reply efficiency, fast reply speed, improved service efficiency and user experience, and reduced customer acquisition cost.

[0070] For example:

[0071] The user asks a question: Hello, my order is about to expire.

[0072] Keywords "order" and "expired" are matched. Two answers matching the keywords are retrieved from the knowledge base. Answer 1 is "Hello, please take a look at the latest package in our store. The link address is http: / / xxxxxx.", and Answer 2 is "Hello, would you like to renew the order?". The current proxy relationship weight score of Answer 1 for the electricity selling company is -2 points, and the current proxy relationship weight score of Answer 2 for the electricity selling company is 5 points. For the sake of convenience, assume that the weight scores corresponding to other attributes are all 0. At this time, the total weight score of Answer 1 is -2, and the total weight score of Answer 2 is 5 points. The terminal automatically matches Answer 2 as the most recommended answer.

[0073] Figure 4 Schematic diagram of the electronic device structure provided by the embodiment of the present invention. Refer to Figure 4 The electronic device may include: a processor 201, a communications interface 202, a memory 203, and a communication bus 204. Among them, the processor 201, the communications interface 202, and the memory 203 communicate with each other through the communication bus 204. The processor 201 can call the logical instructions in the memory 203 to execute the following method:

[0074] S101: Create a knowledge base including questions, question keywords, and recommended responses according to the electricity user tags, and perform operations of merging similar questions or inserting knowledge points in the knowledge base through the questions, question keywords, and user instructions. The knowledge points are associated with the electricity user tags, and the questions, question keywords, and recommended responses correspond to each other;

[0075] S102: Set weights for the user type parameters corresponding to the knowledge points, perform word segmentation on the received user question, and perform user analysis to obtain user type parameters;

[0076] S103: Screen and match the knowledge points from the knowledge base according to the obtained word segmentation, and sort the knowledge points through the user type parameters corresponding to the user question and the weights corresponding to the user type parameters of the knowledge points, and obtain the optimal result based on the sorting;

[0077] S104: Reply to the user question according to the recommended response corresponding to the optimal result.

[0078] In addition, when the logical instructions in the above-mentioned memory 203 are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on such an understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in various embodiments of the present invention. The foregoing storage medium includes: various media such as USB flash drives, mobile hard disks, read-only memories (ROM, Read-Only Memory), random access memories (RAM, Random Access Memory), magnetic disks, or optical discs that can store program codes.

[0079] In this embodiment, the processor 201 is the control center of the retail price prediction device for electricity packages, connecting various parts of the entire retail price prediction device for electricity packages through various interfaces and lines. By running or executing the software programs and / or modules stored in the memory 203, and by invoking the data stored in the memory 203, it executes various functions of the retail price prediction device for electricity packages and processes data, thereby monitoring the entire retail price prediction device for electricity packages. Optionally, the processor 201 may include one or more processing units; preferably, the processor 201 may integrate an application processor and a modem processor. Among them, the application processor mainly processes the operating system, user interface, and application programs, etc., and the modem processor mainly processes wireless communications. It can be understood that the above-mentioned modem processor may not be integrated into the processor.

[0080] The retail price prediction device for electricity packages further includes a power source (such as a battery) for supplying power to each component. Preferably, the power source can be logically connected to the processor 201 through a power management system, so as to realize functions such as management of charging, discharging, and power consumption management through the power management system.

[0081] The memory 203 can be used to store software programs and modules. The processor 201 executes various functional applications and data processing of the retail price prediction device for electricity packages by running the software programs and modules stored in the memory. The memory 203 mainly includes a program storage area and a data storage area. Among them, the program storage area can store an operating system, application programs required for at least one function, etc.; the data storage area can store data created according to the use of the retail price prediction device for electricity packages. In addition, the memory may include a high-speed random access memory, and may also include a non-volatile memory, such as at least one magnetic disk storage device, a flash memory device, or other volatile solid-state storage devices.

[0082] On the other hand, an embodiment of the present invention further provides a non-transitory computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, it is configured to execute the automatic response method based on power trading provided in the above embodiments. For example, it includes:

[0083] S101: Create a knowledge base including questions, question keywords, and recommended responses according to power user tags, and perform operations of merging similar questions or inserting knowledge points in the knowledge base through the questions, question keywords, and user instructions. The knowledge points are associated with the power user tags, and the questions, question keywords, and recommended responses correspond to each other;

[0084] S102: Set weights for the user type parameters corresponding to the knowledge points, perform word segmentation on the received user questions, and perform user analysis to obtain user type parameters;

[0085] S103: Screen for matching knowledge points from the knowledge base according to the obtained word segmentation, and sort the knowledge points through the user type parameters corresponding to the user questions and the weights corresponding to the user type parameters of the knowledge points, and obtain the optimal result based on the sorting;

[0086] S104: Reply to the user question according to the recommended response corresponding to the optimal result.

[0087] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place, or may be distributed to multiple network units. Some or all of the modules can be selected according to actual needs to achieve the purpose of the solution of this embodiment. Those of ordinary skill in the art can understand and implement it without creative labor.

[0088] Through the description of the above embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus a necessary general hardware platform, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solution, in essence, or the part that contributes to the prior art can be embodied in the form of a software product. The computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0089] In the present specification, the various embodiments are described in a progressive manner. Each embodiment focuses on the differences from other embodiments. For the same or similar parts among the various embodiments, reference may be made to each other.

[0090] The foregoing has shown and described the basic principles, main features and advantages of the present invention. Those skilled in the art should understand that the present invention is not limited by the above embodiments. The above embodiments and the descriptions in the specification are only used to illustrate the principles of the present invention. Without departing from the spirit and scope of the present invention, the present invention will have various changes and improvements, and all these changes and improvements fall within the scope of the present invention claimed. The scope of the present invention claimed is defined by the appended claims and their equivalents.

Claims

1. An automatic response method based on electricity trading, characterized in that, It includes the following steps: S101: Create a knowledge base including questions, question keywords, and recommended responses according to power user tags, and perform operations of merging similar questions or inserting knowledge points in the knowledge base through the questions, question keywords, and user instructions. The knowledge points are associated with the power user tags, and the questions, question keywords, and recommended responses correspond to each other; S102: Set weights for the user type parameters corresponding to the knowledge points, segment the received user questions, and perform user analysis to obtain user type parameters; S103: Screen and match the knowledge points from the knowledge base according to the obtained segmented words, sort the knowledge points through the user type parameters corresponding to the user questions and the weights corresponding to the user type parameters of the knowledge points, and obtain the optimal result based on the sorting; S104: Reply to the user question according to the recommended response corresponding to the optimal result; Before the step of creating a knowledge base including questions, question keywords, and recommended responses according to power user tags, it also includes: Obtain the power user tags, find the usage frequency corresponding to each power user tag, and determine the sorting of the power user tags for creating the knowledge base according to the sorting of the usage frequency; The step of performing operations of merging similar questions or inserting knowledge points in the knowledge base through the questions, question keywords, and user instructions specifically includes: Judge whether there are similar questions in the knowledge base that are repeated with the questions and question keywords; If so, perform operations of merging similar questions or inserting knowledge points according to the user instructions; If not, insert the questions, question keywords, and recommended responses into the knowledge base as new knowledge points; The step of sorting the knowledge points through the user type parameters corresponding to the user questions and the weights corresponding to the user type parameters of the knowledge points specifically includes: Obtain the proxy relationship weight score, the current electricity sales company proxy relationship weight score, the electricity consumption type weight score, the package expiration option weight score, the user tag weight score, and the weighted score according to the user type parameters corresponding to the user questions and the weights corresponding to the user type parameters of the knowledge points. Obtain the weight score of each knowledge point according to the sum of the weight scores, and sort the knowledge points based on the weight scores; The step of replying to the user question according to the recommended response corresponding to the optimal result specifically includes: Obtain the recommended response corresponding to the optimal result, and judge whether an adjustment instruction is received; If so, reply to the user question according to the adjusted answer; If not, reply to the user question according to the recommended response corresponding to the optimal result.

2. The automatic response method based on power trading according to claim 1, wherein The step of performing operations of merging similar questions or inserting knowledge points according to the user instructions specifically includes: Judge whether the operation of merging similar questions is allowed according to the user instructions; If so, merge the similar questions with the questions, question keywords, and recommended responses into one knowledge point; If not, insert the questions, question keywords, and recommended responses into the knowledge base as a new knowledge point.

3. The automatic response method based on power trading according to claim 1, wherein The step of segmenting the received user questions and performing user analysis to obtain user type parameters specifically includes: Obtain the user corresponding to the user's question sentence, obtain the user type parameter through the user analysis result, and segment the user's question sentence through the thesaurus.

4. The automatic response method based on power trading according to claim 1, wherein The user type parameter includes whether the user has an agency relationship, whether the user has an agency relationship with the current electricity sales company, the user's electricity consumption type, whether the package order in the user's delivery is approaching its expiration date, and whether the user has a label in this electricity sales company.

5. An intelligent terminal, comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, characterized in that, When the processor executes the program, it implements the steps of the automatic response method based on power trading according to any one of claims 1 to 4.

6. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the steps of the automatic response method based on power trading according to any one of claims 1 to 4.

Images