Self-feedback sales prompt methods, devices, computer equipment, and storage media

Abstract

This invention relates to a self-feedback sales prompt method, apparatus, computer device, and storage medium, comprising: acquiring product type data; acquiring sales success data and product attribute data based on the product type data, and using the sales success data and corresponding product attribute data as a dataset to be recommended; acquiring sales voice data in real time; identifying customer situation data from the sales voice data; matching the product attribute data in the dataset to be recommended based on the customer situation data; identifying customer question data from the sales voice data; matching the sales success data in the dataset to be recommended based on the customer question data; and acquiring salesperson attribute data; generating sales script data based on the salesperson attribute data and the data to be recommended. This application has the effect of improving the customer conversion success rate of insurance salespersons during sales.

Description

Technical Field

[0001] This invention relates to the technical field of intelligent feedback, and in particular to a self-feedback sales prompt method, apparatus, computer device, and storage medium. Background Technology

[0002] Currently, for insurance sales personnel, when selling corresponding products to customers, the salesperson usually faces the customer, communicates and negotiates with the customer, explores the customer's actual needs, and recommends suitable insurance products to the customer.

[0003] Because each salesperson's understanding of the company's insurance products, their professional level, and personal qualities vary, their sales techniques differ, which affects the success rate of customer conversion. In order to improve the success rate of customer conversion for insurance salespeople, most insurance companies regularly conduct offline training for their salespeople to familiarize them with the company's insurance products and corresponding sales techniques.

[0004] The existing technical solutions described above have the following drawbacks:

[0005] When sales staff are trained offline, the training effect is not good, resulting in a lack of significant improvement in the conversion rate of orders during actual sales. Summary of the Invention

[0006] In order to improve the success rate of customer conversion during insurance sales, this application provides a self-feedback sales prompt method, device, computer equipment, and storage medium.

[0007] The above-mentioned objective of this application is achieved through the following technical solution:

[0008] A self-feedback sales prompting method, the self-feedback sales prompting method comprising:

[0009] Obtain product type data, and based on the product type data, obtain sales success data and product attribute data respectively, and use the sales success data and the corresponding product attribute data as the dataset to be recommended;

[0010] Real-time acquisition of sales voice data; identification of customer information data from the sales voice data; matching of product attribute data to be recommended from the product attribute data in the dataset to be recommended based on the customer information data;

[0011] Identify customer question data from the sales voice data, and based on the customer question data, match the sales success data in the dataset to be recommended with the product data to be recommended;

[0012] Obtain sales personnel attribute data, generate sales script data based on the sales personnel attribute data and the script data to be recommended, and display it on the sales personnel's client.

[0013] By adopting the above technical solution, sales personnel can receive real-time recommendations of appropriate communication prompts based on their interactions with customers during the actual sales process. This improves the success rate of customer conversion during sales. Specifically, based on product type data, successful sales data and corresponding product attributes are obtained for each product type to create a recommended dataset. This dataset allows sales personnel to collect experience on successful sales of each product type before making an actual sale, providing a data foundation for subsequent recommendations of communication prompts. After acquiring sales voice data in real time, the specific customer situation is identified, i.e., customer situation data, enabling matching based on the customer situation data. The matching product data tailored to the customer facilitates targeted sales by sales personnel. During the sales process, user problem data is identified, and appropriate sales pitches are selected from the corresponding sales success data of the product data based on the specific problems identified in the customer's user data. By acquiring sales personnel attribute data, information such as the salesperson's personality can be obtained, allowing for the creation of sales pitch data that matches the salesperson's language style. This serves as a prompt for communication and is displayed on the salesperson's client. By combining the customer's specific problems with the salesperson's personality, the sales success data of the product can be better integrated into the actual sales scenario, thereby helping to improve the salesperson's success rate in converting customer orders into sales.

[0014] In a preferred embodiment, this application can be further configured as follows: identifying customer question data from the sales voice data, and matching the sales success data in the dataset to be recommended with the product data to be recommended based on the customer question data, specifically includes:

[0015] Key points of the sales script are extracted in advance from each of the sales success data corresponding to the product data to be recommended;

[0016] Customer question statements are extracted from the customer question data through semantic recognition;

[0017] Key problem data is identified from the customer's question statements. The key problem data is then compared with the key dialogue data to calculate the recommended dialogue data.

[0018] By adopting the above technical solution, key points of the sales script are extracted from each sales success data point and used as the calculation object for key points of the problem extracted from the customer problem data. This allows for the rapid matching of recommended sales script data associated with the customer problem data from past sales success data based on the specific questions raised by the customer. This makes it easier for sales personnel to answer customer questions in a timely manner based on past successful experiences.

[0019] In a preferred embodiment, this application can be further configured as follows: identifying key question data from the customer's question statement, calculating the key question data and the key dialogue data, and obtaining the recommended dialogue data based on the calculation result, specifically includes:

[0020] The key points of the problem are compared with the key points of the sales script in each of the sales success data to obtain the comparison results, wherein the comparison results include comparison success and comparison failure;

[0021] Input the comparison results into the following formula to calculate the script recommendation score:

[0022]

[0023]

[0024]

[0025] Where n is the total number of key points in the customer problem data; u is the number of successful comparisons between the key points in the problem and each key point in the script; v is the number of unsuccessful comparisons between the key points in the problem and each key point in the script; P is the success rate of comparisons; Z is the weighting parameter; and S is the script recommendation score.

[0026] The sales success data corresponding to the highest recommended sales script score is used as the recommended sales script data.

[0027] By adopting the above technical solution and calculating the recommended speech score of each sales success data point relative to the customer problem data using the above formula algorithm, we can obtain the audience appeal of each sales success data point relative to the customer problem data. The higher the audience appeal, the higher the correlation between the sales success data point and the customer problem data, so the sales success data point with the highest audience appeal can be used as the recommended speech data.

[0028] In a preferred embodiment, this application can be further configured as follows: comparing the key points of the problem with the key points of the sales script in each of the sales success data to obtain a comparison result, wherein the comparison result includes comparison success and comparison failure, specifically including:

[0029] The similarity between each of the key points of the problem and the key points of the sales script in each of the sales success data is calculated to obtain the similarity value between each key point of the sales script and each key point of the problem in each of the sales success data.

[0030] In each sales success data point, obtain the question key point corresponding to the highest similarity value of each of the key points of the sales script and perform correlation comparison;

[0031] A preset similarity threshold is obtained. If the similarity value is greater than or equal to the similarity threshold, the comparison is successful; otherwise, the comparison fails.

[0032] By adopting the above technical solution, the similarity value between the key points of the sales pitch and the corresponding key points of the questions in each successful sales data is calculated and associated. This allows each key point of the questions to be associated with the most similar key points of the sales pitch in each successful sales data, facilitating the comparison of similarity thresholds and determining whether the comparison is successful.

[0033] In a preferred embodiment, this application can be further configured such that: the real-time acquisition of sales voice data specifically includes:

[0034] Obtain a potential user list consisting of several potential user data sets, match the product attribute data with each potential user data set, and obtain a product list to be recommended corresponding to each potential user data set;

[0035] Based on the potential user data and the corresponding list of products to be recommended, obtain the corresponding sales voice data.

[0036] By adopting the above technical solution, product attribute data can be matched and queried in the potential user list. This allows for the matching of products associated with each customer based on their basic information. As a result, the products introduced by sales personnel to customers in the initial communication stage are more in line with the actual needs of the customers, which helps to increase the success rate of continued communication between customers and sales personnel. In turn, more customer information data can be obtained, which helps to improve the sales success rate.

[0037] The second objective of this invention is achieved through the following technical solution:

[0038] A self-feedback sales prompting device, the self-feedback sales prompting device comprising:

[0039] The success case statistics module is used to obtain product type data, and based on the product type data, obtain sales success data and product attribute data respectively, and use the sales success data and the corresponding product attribute data as a dataset to be recommended.

[0040] The real-time sales data acquisition module is used to acquire sales voice data in real time, identify customer information data from the sales voice data, and match the product attribute data to be recommended from the product attribute data in the dataset to be recommended based on the customer information data.

[0041] The analysis module is used to identify customer question data from the sales voice data, and based on the customer question data, to match the sales success data in the dataset to be recommended with the product data to be recommended.

[0042] The sales script prompt module is used to obtain sales personnel attribute data, generate sales script data based on the sales personnel attribute data and the sales script data to be recommended, and display it on the sales personnel's client.

[0043] By adopting the above technical solution, sales personnel can receive real-time recommendations of appropriate communication prompts based on their interactions with customers during the actual sales process. This improves the success rate of customer conversion during sales. Specifically, based on product type data, successful sales data and corresponding product attributes are obtained for each product type to create a recommended dataset. This dataset allows sales personnel to collect experience on successful sales of each product type before making an actual sale, providing a data foundation for subsequent recommendations of communication prompts. After acquiring sales voice data in real time, the specific customer situation is identified, i.e., customer situation data, enabling matching based on the customer situation data. The matching product data tailored to the customer facilitates targeted sales by sales personnel. During the sales process, user problem data is identified, and appropriate sales pitches are selected from the corresponding sales success data of the product data based on the specific problems identified in the customer's user data. By acquiring sales personnel attribute data, information such as the salesperson's personality can be obtained, allowing for the creation of sales pitch data that matches the salesperson's language style. This serves as a prompt for communication and is displayed on the salesperson's client. By combining the customer's specific problems with the salesperson's personality, the sales success data of the product can be better integrated into the actual sales scenario, thereby helping to improve the salesperson's success rate in converting customer orders into sales.

[0044] The above-mentioned objective three of this application is achieved through the following technical solution:

[0045] A computer device includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor, when executing the computer program, implements the steps of the self-feedback sales prompting method described above.

[0046] The fourth objective of this application is achieved through the following technical solution:

[0047] A computer-readable storage medium storing a computer program that, when executed by a processor, implements the steps of the aforementioned self-feedback sales prompting method.

[0048] In summary, this application includes at least one of the following beneficial technical effects:

[0049] 1. It can recommend corresponding communication prompts in real time based on the content of communication with customers during the actual sales process, thereby improving the success rate of customer conversion during the actual sales. Specifically, based on product type data, it obtains the successful sales data corresponding to each type of product, that is, the sales success data and the corresponding product attributes, to obtain the dataset to be recommended. Before the sales staff conducts the actual sales, it can collect the experience of successful sales of each type of product, thereby providing a data foundation for subsequent recommendation of communication prompts.

[0050] 2. During the sales process, user problem data is identified, and based on the specific problems in the customer user data, appropriate sales scripts are selected from the corresponding sales success data of the product to be recommended. By obtaining salesperson attribute data, data such as the salesperson's personality can be obtained, thereby creating sales script data that matches the salesperson's language style. This data serves as a prompt for communication scripts and is displayed on the salesperson's client. This allows for a better integration of the product's sales success data into the actual sales scenario, combining the specific customer problems with the salesperson's personality, thus helping to improve the salesperson's customer conversion rate.

[0051] 3. The recommended speech score for each sales success data point relative to the customer problem data is calculated using the above formula algorithm. This allows us to determine the audience reach of each sales success data point relative to the customer problem data. The higher the audience reach, the stronger the correlation between the sales success data point and the customer problem data. Therefore, the sales success data point with the highest audience reach can be used as the recommended speech data point. Attached Figure Description

[0052] Figure 1 This is a flowchart of a self-feedback sales prompt method in one embodiment of this application;

[0053] Figure 2 This is a flowchart illustrating the implementation of step S30 in a self-feedback sales prompt method according to an embodiment of this application.

[0054] Figure 3 This is a flowchart illustrating the implementation of step S33 in a self-feedback sales prompt method according to an embodiment of this application.

[0055] Figure 4 This is a flowchart illustrating the implementation of step S331 in a self-feedback sales prompt method according to an embodiment of this application.

[0056] Figure 5 This is a flowchart illustrating the implementation of step S20 in a self-feedback sales prompt method according to an embodiment of this application.

[0057] Figure 6 This is a schematic diagram of a self-feedback sales prompt device according to an embodiment of this application;

[0058] Figure 7 This is a schematic diagram of a device according to one embodiment of this application. Detailed Implementation

[0059] The present application will be further described in detail below with reference to the accompanying drawings.

[0060] In one embodiment, if Figure 1 As shown, this application discloses a self-feedback sales prompt method, which specifically includes the following steps:

[0061] S10: Obtain product type data, and based on the product type data, obtain sales success data and product attribute data respectively, and use the sales success data and the corresponding product attribute data as the dataset to be recommended.

[0062] In this embodiment, product type data refers to the names of insurance products that insurance sales personnel can sell during telephone sales. Sales success data refers to the telephone voice recordings of successful sales for each product type, which have been converted into textual form. Product attribute data refers to the specific content data of this type of insurance product. The dataset to be recommended refers to a dataset storing recommended sales scripts for sales personnel to use when communicating with customers.

[0063] Specifically, current sales staff training focuses on standard sales scripts for each product. However, in practice, every customer has unique circumstances, and relying solely on these standard scripts is insufficient for sales staff to truly apply them in specific sales scenarios, resulting in a lack of significant improvement in customer conversion rates. Therefore, this paper proposes a product type data set by compiling a list of products that can be sold to customers. Further, after obtaining the product type data, the paper retrieves the voice recordings of successful sales for each product. These recordings are then converted into computer-readable text using speech recognition or other methods to obtain the corresponding sales success data. Additionally, the paper retrieves the product attribute data for each product type. For example, for car insurance, the paper retrieves the coverage, pricing calculation method, and other relevant information as the product attribute data for that product type.

[0064] Furthermore, taking each product type as a unit, the product attribute data corresponding to that product type and all sales success data are associated to obtain the dataset to be recommended for each product.

[0065] S20: Acquire sales voice data in real time, identify customer information data from the sales voice data, and match the product attribute data to be recommended from the product attribute data in the dataset to be recommended.

[0066] In this embodiment, sales voice data refers to the telephone voice data during actual telephone sales conversations between sales personnel and customers. Customer situation data refers to data recording the actual situation of customers collected during the communication process between sales personnel and customers. Product data to be recommended refers to the specific insurance products that need to be promoted to customers.

[0067] Specifically, during telephone sales conversations between sales personnel and customers, the recording function on the salesperson's terminal captures the sales voice data in real time. Based on the corresponding communication protocol, the system distinguishes between the salesperson's voice and the customer's voice. Furthermore, it identifies information such as the customer's location, occupation, and family situation from the customer's voice, using this information as customer profile data.

[0068] Furthermore, after obtaining customer information data, products that match the customer's actual situation are matched from a pre-set list of products to be marketed to the customer, and these products are used as data for product recommendations.

[0069] S30: Identify customer question data from sales voice data, and based on the customer question data, match the sales success data in the dataset to be recommended with the product data to be recommended.

[0070] In this embodiment, customer question data refers to the data on the questions customers ask salespeople when they are receiving product recommendations. Recommended script data refers to keywords used to prompt salespeople to answer the customer's questions.

[0071] Specifically, through semantic recognition, the system identifies the professional questions raised by customers regarding the product data to be recommended and the product suitability questions raised by customers regarding their own situation from the context of their speech, and uses these as customer question data.

[0072] Furthermore, key points of the problem are extracted from the customer's problem data, such as keywords for professional questions. Answers to the problem from past successful cases are matched from the sales success data corresponding to the product and used as data for recommended scripts.

[0073] S40: Obtain sales personnel attribute data, generate sales script data based on sales personnel attribute data and script data to be recommended, and display it on the sales personnel's client.

[0074] In this embodiment, salesperson attribute data refers to data such as the salesperson's age, gender, and personality. Sales script data refers to the specific script prompts shown to the salesperson for answering customer questions.

[0075] Specifically, starting from the time the salesperson joins the company, data such as the salesperson's age, gender, and personality traits collected from past sales and internal communications are compiled as salesperson attribute data.

[0076] Furthermore, by pre-training the corresponding model, sales script data that matches the salesperson's speaking style can be generated based on the salesperson's attribute data and the script data to be recommended. This data can then be displayed in text form on the salesperson's client, allowing the salesperson to refer to the sales script data in a timely manner to answer customer questions.

[0077] In this embodiment, during the actual sales process, corresponding communication prompts can be recommended in real time based on the content of communication with customers, thereby improving the success rate of customer conversion during actual sales. Specifically, based on product type data, successful sales data corresponding to each type of product, i.e., sales success data and corresponding product attributes, are obtained to obtain the dataset to be recommended. Before the salesperson conducts the actual sale, the experience of successful sales of each type of product can be statistically analyzed, thus providing a data foundation for subsequent recommendations of communication prompts. After acquiring sales voice data in real time, the specific situation of the customer, i.e., customer situation data, can be identified from it, thereby enabling matching of the customer with the relevant information. Customer-adapted product data allows sales staff to target their sales efforts. During the sales process, user problem data is identified, and appropriate sales pitches are selected from the corresponding sales success data of the product data based on the specific problems identified in the customer user data. By acquiring salesperson attribute data, information such as the salesperson's personality can be obtained, allowing for the creation of sales pitches that match the salesperson's language style. These pitches serve as prompts for communication and are displayed on the salesperson's client. This allows for a better integration of the product's sales success data into the actual sales scenario, taking into account both the customer's specific problems and the salesperson's personality, thereby helping to improve the salesperson's customer conversion rate.

[0078] In one embodiment, if Figure 2 As shown, in step S30, customer question data is identified from the sales voice data. Based on the customer question data, the recommended script data associated with the recommended product data is matched from the sales success data in the recommended dataset. Specifically, this includes:

[0079] S31: Extract key points of the sales script from each sales success data corresponding to the product data to be recommended in advance.

[0080] In this embodiment, the key data of the sales script refers to the data of the answers used to answer specific customer questions in each successful sales voice recording of the product to be recommended.

[0081] Specifically, data on answers to customer questions are extracted in advance from each successful sales data in the dataset to be recommended. Furthermore, based on the data of the product to be recommended, the corresponding answer data is extracted as the key point data of the sales script.

[0082] S32: Extract customer question statements from customer question data through semantic recognition.

[0083] In this embodiment, a customer question statement refers to a specific statement asked to a salesperson.

[0084] Specifically, through semantic recognition, each question is identified from the customer question data, and statements related to professional issues or suitability of the product to be recommended are selected as customer question statements.

[0085] S33: Identify key problem data from customer problem statements, calculate the key problem data and key dialogue data, and obtain recommended dialogue data based on the calculation results.

[0086] In this embodiment, the key data of the problem refers to the keywords in the customer's question statement.

[0087] Specifically, although the sales success data for the product to be recommended consists of past sales success stories, each customer's specific situation is different in the actual sales process. In order to match the success stories with the highest correlation to the current customer's question data from the dataset to be recommended, and to prompt the current sales staff to answer the customer's questions, after obtaining the customer's question statement, specific keywords are identified from the customer's question statement as question key point data. All question key point data of the customer's question statement are then calculated with the key point data of the sales script to obtain the result of the degree of correlation between the key point data of the sales script and the customer's question statement. The result with the highest result is used as the recommended sales script data.

[0088] In one embodiment, if Figure 3 As shown, in step S33, key problem data is identified from the customer's question statement, and the key problem data is calculated together with the key dialogue data. Recommended dialogue data is then obtained based on the calculation results, specifically including:

[0089] S331: Compare the key points of the problem with the key points of the sales script in each sales success data to obtain the comparison results, which include comparison success and comparison failure.

[0090] Specifically, the key points of each sales success data point are compared with the key points of the customer's question statement. If they match, or match within the error range, the comparison is considered successful; otherwise, the comparison fails.

[0091] S332: Input the comparison results into the following formula to calculate the recommended speech score:

[0092]

[0093]

[0094]

[0095] Where n is the total number of key points in the customer problem data; u is the number of successful matches between the key points in the problem and each key point in the script; v is the number of unsuccessful matches between the key points in the problem and each key point in the script; P is the success rate; Z is the weighting parameter; and S is the script recommendation score.

[0096] In this embodiment, the script recommendation score refers to the score of the relevance between each sales success data point and the customer question data corresponding to the product data to be recommended.

[0097] Specifically, the number of customer question statements in the customer question data is counted, as well as the number of key question points corresponding to each customer question statement, and then the total number of key question points n is calculated. After comparing the key question points of each corresponding sales success data with the key question points in the customer question data, the number of successful comparisons u and the number of failed comparisons v are counted. Based on past experience, a weight parameter Z is set, and the recommendation score S of the relevance of each sales success data to the customer question data is calculated.

[0098] S333: Use the sales success data corresponding to the highest recommended sales script score as the recommended sales script data.

[0099] Specifically, the highest recommended sales script score indicates that the customer's question is most closely related to the current customer question data in the corresponding sales success data, and the corresponding answer has the highest reference value. Therefore, the corresponding sales success data is used as the recommended sales script data.

[0100] In one embodiment, if Figure 4 As shown, in step S331, the key points of the problem are compared with the key points of the sales script in each sales success data to obtain the comparison result. The comparison result includes comparison success and comparison failure, specifically including:

[0101] S3311: Calculate the similarity between each key point of the question and the key points of the sales script for each sales success data point, and obtain the similarity value between each key point of the sales script and each key point of the question in each sales success data point.

[0102] Specifically, after obtaining the key points of each sales statement in the sales success data of the product to be recommended, based on each sales success data, semantic recognition or cosine similarity can be used to compare the key points of the question with the key points of each sales success data.

[0103] S3312: Obtain the key issue corresponding to the highest similarity value of each key point in the sales script in each sales success data and perform correlation comparison.

[0104] Specifically, after calculating the key points of all the sales scripts in each sales success data with the key points of the questions, the key point of the questions with the highest similarity value is associated with the key point of the sales script. That is, in each sales success data corresponding to the product data to be recommended, each key point of the sales script is associated with a key point of the questions with the highest similarity value.

[0105] S3313: Obtain the preset similarity threshold. If the similarity value is greater than or equal to the similarity threshold, the comparison is successful; otherwise, the comparison fails.

[0106] Specifically, by pre-setting the similarity threshold, for example [0.8, 1], the corresponding similarity value in the question key point data associated with the key point data of the sales script in each sales success data is compared with the similarity threshold. If the similarity value falls within the range of the similarity threshold, the comparison is successful; otherwise, the comparison fails.

[0107] In one embodiment, if Figure 5 As shown, in step S20, which involves acquiring sales voice data in real time, the specific steps include:

[0108] S21: Obtain a potential user list consisting of several potential user data sets, match the product attribute data with each potential user data set, and obtain a list of products to be recommended for each potential user data set.

[0109] Specifically, basic customer information, such as gender, age, region, and occupation, can be obtained through corresponding web crawling technology as potential user data. After obtaining a certain amount of potential user data, this potential user data can be compiled into a potential user list.

[0110] Furthermore, by initially matching product attribute data with potential user data in the potential user list, suitable insurance products for sale to the potential user are obtained, forming a product recommendation list for that customer. Within the same product recommendation list, correlation points can be marked based on corresponding product attribute data and / or potential user data. This means that when recommending a specific product to a customer based on the product recommendation list, if the customer is not interested or finds it unsuitable, the salesperson can promptly switch to recommending another product based on the customer's actual situation, making the transition more natural.

[0111] S22: Obtain the corresponding sales voice data based on potential user data and the corresponding list of products to be recommended.

[0112] Specifically, after sales personnel obtain potential user data and the corresponding list of products to be recommended, they contact the customer based on the user's contact information and the specific products to be recommended, thereby obtaining the sales voice data in real time during the contact process.

[0113] It should be understood that the sequence number of each step in the above embodiments does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this application.

[0114] In one embodiment, a self-feedback sales prompting device is provided, which corresponds one-to-one with the self-feedback sales prompting method described in the above embodiments. For example... Figure 6 As shown, this self-feedback sales prompt device includes a success case statistics module, a real-time sales data acquisition module, an analysis module, and a sales script prompt module. Detailed descriptions of each functional module are as follows:

[0115] The success case statistics module is used to obtain product type data, and then obtain sales success data and product attribute data based on the product type data. The sales success data and the corresponding product attribute data are used as the dataset to be recommended.

[0116] The real-time sales data acquisition module is used to acquire sales voice data in real time, identify customer information data from the sales voice data, and match the product attribute data to be recommended from the product attribute data in the dataset to be recommended.

[0117] The analysis module is used to identify customer question data from sales voice data, and based on the customer question data, to match the sales success data in the dataset to be recommended with the data of the products to be recommended.

[0118] The sales script prompt module is used to obtain sales personnel attribute data, generate sales script data based on the sales personnel attribute data and the sales script data to be recommended, and display it on the sales personnel's client.

[0119] Optionally, the analysis module includes:

[0120] The key point extraction submodule is used to extract key points of the sales script from each sales success data corresponding to the product data to be recommended in advance;

[0121] The semantic recognition submodule is used to extract customer question statements from customer question data through semantic recognition;

[0122] The calculation submodule is used to identify key problem data from customer question statements, calculate the key problem data and key speech data, and obtain recommended speech data based on the calculation results.

[0123] Optionally, the computation submodule includes:

[0124] The comparison unit is used to compare the key points of the problem with the key points of the sales script in each sales success data to obtain the comparison results, which include comparison success and comparison failure.

[0125] The recommendation score calculation unit is used to input the comparison results into the following formula to calculate the script recommendation score:

[0126]

[0127]

[0128]

[0129] Where n is the total number of key points in the customer problem data; u is the number of successful matches between the key points in the problem and each key point in the script; v is the number of unsuccessful matches between the key points in the problem and each key point in the script; P is the success rate; Z is the weighting parameter; and S is the script recommendation score.

[0130] The result generation unit is used to select the sales success data corresponding to the highest recommended script score as the recommended script data.

[0131] Optionally, the comparison unit includes:

[0132] The similarity calculation subunit is used to calculate the similarity between each key point of the question and the key points of the sales script in each sales success data, so as to obtain the similarity value between each key point of the sales script and each key point of the question in each sales success data.

[0133] The association sub-unit is used to obtain the question key point with the highest similarity value for each key point of the sales script in each sales success data and perform association comparison.

[0134] The threshold comparison subunit is used to obtain a preset similarity threshold. If the similarity value is greater than or equal to the similarity threshold, the comparison is successful; otherwise, the comparison fails.

[0135] Optional, the real-time sales data acquisition module includes:

[0136] The customer matching submodule is used to obtain a potential user list consisting of several potential user data, match product attribute data with each potential user data, and obtain a list of products to be recommended for each potential user data.

[0137] The targeted sales submodule is used to obtain corresponding sales voice data based on potential user data and the corresponding list of products to be recommended.

[0138] Specific limitations regarding the self-feedback sales prompt device can be found in the limitations of the self-feedback sales prompt method described above, and will not be repeated here. Each module in the aforementioned self-feedback sales prompt device can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in or independent of the processor in a computer device in hardware form, or stored in the memory of a computer device in software form, so that the processor can call and execute the operations corresponding to each module.

[0139] In one embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as follows: Figure 7 As shown, the computer device includes a processor, memory, network interface, and database connected via a system bus. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system, computer programs, and database. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage media. The database stores product type data and corresponding sales success data. The network interface communicates with external terminals via a network connection. When executed by the processor, the computer program implements a self-feedback sales prompt method.

[0140] In one embodiment, a computer device is provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to perform the following steps:

[0141] Obtain product type data, and based on the product type data, obtain sales success data and product attribute data respectively, and use the sales success data and the corresponding product attribute data as the dataset to be recommended;

[0142] Real-time acquisition of sales voice data; identification of customer information data from the sales voice data; matching of recommended product data from product attribute data in the dataset to be recommended based on the customer information data.

[0143] Identify customer question data from sales voice data, and based on the customer question data, match the sales success data in the dataset to be recommended with the product data to be recommended.

[0144] Obtain sales personnel attribute data, generate sales script data based on sales personnel attribute data and script data to be recommended, and display it on the sales personnel's client.

[0145] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon, the computer program performing the following steps when executed by a processor:

[0146] Obtain product type data, and based on the product type data, obtain sales success data and product attribute data respectively, and use the sales success data and the corresponding product attribute data as the dataset to be recommended;

[0147] Real-time acquisition of sales voice data; identification of customer information data from the sales voice data; matching of recommended product data from product attribute data in the dataset to be recommended based on the customer information data.

[0148] Identify customer question data from sales voice data, and based on the customer question data, match the sales success data in the dataset to be recommended with the product data to be recommended.

[0149] Obtain sales personnel attribute data, generate sales script data based on sales personnel attribute data and script data to be recommended, and display it on the sales personnel's client.

[0150] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium. When executed, the computer program can include the processes of the embodiments of the above methods. Any references to memory, storage, databases, or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), dual data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), RAMbus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.

[0151] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the above-described division of functional units and modules is used as an example. In practical applications, the above functions can be assigned to different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above.

[0152] The above-described embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application, and should all be included within the protection scope of this application.

Claims

1. A self-feedback sales prompting method, characterized in that, The self-feedback sales prompting methods include: Obtain product type data, and based on the product type data, obtain sales success data and product attribute data respectively, and use the sales success data and the corresponding product attribute data as the dataset to be recommended; Real-time acquisition of sales voice data; identification of customer information data from the sales voice data; matching of product attribute data to be recommended from the product attribute data in the dataset to be recommended based on the customer information data; Identifying customer question data from the sales voice data, and based on the customer question data, matching the sales success data in the dataset to be recommended with the product data to be recommended, specifically including: Key points of the sales script are extracted in advance from each of the sales success data corresponding to the product data to be recommended; Customer question statements are extracted from the customer question data through semantic recognition; The process involves identifying key question data from the customer's question statements, calculating the key question data against the key dialogue data, and obtaining the recommended dialogue data based on the calculation results. Specifically, this includes: The key points of the problem are compared with the key points of the sales script in each of the sales success data to obtain the comparison results, wherein the comparison results include comparison success and comparison failure; Input the comparison results into the following formula to calculate the script recommendation score: Where n is the total number of key points in the customer problem data; u is the number of successful comparisons between the key points in the problem and each key point in the script; v is the number of unsuccessful comparisons between the key points in the problem and each key point in the script; P is the success rate of comparisons; Z is the weighting parameter; and S is the script recommendation score. The sales success data corresponding to the highest recommended script score is used as the recommended script data; Obtain sales personnel attribute data, generate sales script data based on the sales personnel attribute data and the script data to be recommended, and display it on the sales personnel's client.

2. The self-feedback sales prompt method according to claim 1, characterized in that, The process involves comparing the key points of the problem with the key points of the sales script in each of the sales success data sets to obtain a comparison result. The comparison result includes successful and unsuccessful comparisons, specifically including: The similarity between each of the key points of the problem and the key points of the sales script in each of the sales success data is calculated to obtain the similarity value between each key point of the sales script and each key point of the problem in each of the sales success data. In each sales success data point, obtain the question key point corresponding to the highest similarity value of each of the key points of the sales script and perform correlation comparison; A preset similarity threshold is obtained. If the similarity value is greater than or equal to the similarity threshold, the comparison is successful; otherwise, the comparison fails.

3. The self-feedback sales prompting method according to any one of claims 1-2, characterized in that, The real-time acquisition of sales voice data specifically includes: Obtain a potential user list consisting of several potential user data sets, match the product attribute data with each potential user data set, and obtain a product list to be recommended corresponding to each potential user data set; Based on the potential user data and the corresponding list of products to be recommended, obtain the corresponding sales voice data.

4. A self-feedback sales prompt device, characterized in that, The self-feedback sales prompt device includes: The success case statistics module is used to obtain product type data, and based on the product type data, obtain sales success data and product attribute data respectively, and use the sales success data and the corresponding product attribute data as a dataset to be recommended. The real-time sales data acquisition module is used to acquire sales voice data in real time, identify customer information data from the sales voice data, and match the product attribute data to be recommended from the product attribute data in the dataset to be recommended based on the customer information data. An analysis module is used to identify customer question data from the sales voice data, and based on the customer question data, to match the sales success data in the dataset to be recommended with the product data to be recommended to the product data to be recommended. The analysis module includes: The key point extraction submodule is used to extract key points of the sales script from each of the sales success data corresponding to the product data to be recommended in advance; The semantic recognition submodule is used to extract customer question statements from the customer question data through semantic recognition; The calculation submodule is used to identify key question data from the customer's question statements, perform calculations on the key question data and the key dialogue data, and obtain the recommended dialogue data based on the calculation results. The calculation submodule includes: The comparison unit is used to compare the key points of the problem with the key points of the sales script in each of the sales success data to obtain a comparison result, wherein the comparison result includes comparison success and comparison failure. The recommendation value calculation unit is used to input the comparison results into the following formula to calculate the speech recommendation score: Where n is the total number of key points in the customer problem data; u is the number of successful comparisons between the key points in the problem and each key point in the script; v is the number of unsuccessful comparisons between the key points in the problem and each key point in the script; P is the success rate of comparisons; Z is the weighting parameter; and S is the script recommendation score. The result generation unit is used to take the sales success data corresponding to the highest recommended speech score as the recommended speech data. The sales script prompt module is used to obtain sales personnel attribute data, generate sales script data based on the sales personnel attribute data and the sales script data to be recommended, and display it on the sales personnel's client.

5. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the steps of the self-feedback sales prompting method as described in any one of claims 1 to 3.

6. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the self-feedback sales prompting method as described in any one of claims 1 to 3.

Images