WO2019127845A1 - 一种录音推荐方法、装置、设备及计算机可读存储介质 - Google Patents

一种录音推荐方法、装置、设备及计算机可读存储介质 Download PDF

Info

Publication number
WO2019127845A1
WO2019127845A1 PCT/CN2018/075053 CN2018075053W WO2019127845A1 WO 2019127845 A1 WO2019127845 A1 WO 2019127845A1 CN 2018075053 W CN2018075053 W CN 2018075053W WO 2019127845 A1 WO2019127845 A1 WO 2019127845A1
Authority
WO
WIPO (PCT)
Prior art keywords
call
record
recommended
preset
recording
Prior art date
Application number
PCT/CN2018/075053
Other languages
English (en)
French (fr)
Inventor
胡超
Original Assignee
平安科技（深圳）有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 平安科技（深圳）有限公司 filed Critical 平安科技（深圳）有限公司
Priority to US16/097,835 priority Critical patent/US20190333176A1/en
Priority to SG11201809602WA priority patent/SG11201809602WA/en
Publication of WO2019127845A1 publication Critical patent/WO2019127845A1/zh

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q30/00—Commerce
    • G06Q30/02—Marketing; Price estimation or determination; Fundraising
    • G06Q30/0201—Market modelling; Market analysis; Collecting market data
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
    • G06Q50/10—Services
    • G06Q50/20—Education
    • G06Q50/205—Education administration or guidance
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/60—Information retrieval; Database structures therefor; File system structures therefor of audio data
    • G06F16/63—Querying
    • G06F16/635—Filtering based on additional data, e.g. user or group profiles
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/60—Information retrieval; Database structures therefor; File system structures therefor of audio data
    • G06F16/63—Querying
    • G06F16/638—Presentation of query results
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/60—Information retrieval; Database structures therefor; File system structures therefor of audio data
    • G06F16/68—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/10—Office automation; Time management
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04M—TELEPHONIC COMMUNICATION
    • H04M2203/00—Aspects of automatic or semi-automatic exchanges
    • H04M2203/40—Aspects of automatic or semi-automatic exchanges related to call centers
    • H04M2203/403—Agent or workforce training

Definitions

  • the present application relates to the field of information processing technologies, and in particular, to a recording recommendation method, apparatus, device, and computer readable storage medium.
  • Call records include call recordings, and call recordings are a reflection of agent sales experience.
  • the products sold are not the same, and the sales experience is different. Many users cannot get the call recordings that they are really interested in, resulting in a low user experience.
  • the embodiment of the present application provides a recording recommendation method, device, device, and computer readable storage medium, which can recommend different call recordings for different users, improve the accuracy of recording recommendation, and improve the user experience.
  • an embodiment of the present application provides a recording recommendation method, where the method includes:
  • the current user is instructed to view the sales call recording, it is determined whether the current user is a new user; if the current user is a new user, the corresponding call record is selected from the sales call recording record as the call record to be recommended according to the first preset rule.
  • the call record includes a call record; if the current user is not a new user, the call record that satisfies the preset condition is obtained from the sales call recording record; and the call record that meets the preset condition is selected according to the second preset rule.
  • the corresponding call record is used as the call record to be recommended; the call record to be recommended is displayed to the current user.
  • an embodiment of the present application provides a recording recommendation device, where the device includes a unit for performing the recording recommendation method described in the first aspect above.
  • the embodiment of the present application further provides a computer device, where the computer device includes a memory, and a processor connected to the memory;
  • the memory is for storing a computer program that implements a recording recommendation
  • the processor is configured to execute a computer program stored in the memory to perform the recording recommendation method of the first aspect described above.
  • an embodiment of the present application provides a computer readable storage medium, where the computer readable storage medium stores a computer program, where the computer program includes program instructions, when the program instructions are executed by a processor, The recording recommendation method described in the above first aspect.
  • the embodiment of the present application determines whether the current user is a new user by receiving an instruction of the current user to view the sales call recording; if the current user is a new user, selecting a corresponding call record from the sales call recording record according to the first preset rule.
  • the call record to be recommended wherein the call record includes a call recording; if the current user is not a new user, the call record that satisfies the preset condition is obtained from the sales call recording record; and the preset condition is met according to the second preset rule.
  • the corresponding call record is selected as the call record to be recommended in the call record; the call record to be recommended is displayed to the current user.
  • the embodiment of the invention can recommend different call recordings for different users, improve the accuracy of the recording recommendation, and improve the user experience.
  • FIG. 1 is a schematic flowchart of a recording recommendation method according to an embodiment of the present application
  • FIG. 2 is a schematic diagram of a sub-flow of a recording recommendation method according to an embodiment of the present application
  • FIG. 3 is a schematic diagram of a sub-flow of a recording recommendation method according to another embodiment of the present application.
  • FIG. 4 is a schematic diagram of a sub-flow of a recording recommendation method according to another embodiment of the present application.
  • FIG. 5 is a schematic block diagram of a recording recommendation apparatus provided by an embodiment of the present application.
  • Figure 6 is a schematic block diagram of a first selection unit provided by an embodiment of the present application.
  • Figure 7 is a schematic block diagram of a second selection unit provided by an embodiment of the present application.
  • FIG. 8 is a schematic block diagram of a second selection unit according to another embodiment of the present application.
  • FIG. 9 is a schematic block diagram of a computer device according to an embodiment of the present application.
  • FIG. 1 is a schematic flowchart of a recording recommendation method according to an embodiment of the present application.
  • the method includes S101-S105.
  • the call recording sharing platform when the user opens the recording recommendation page or clicks the button for viewing the recording recommendation, it is regarded as receiving an instruction to view the sales call recording.
  • the new user includes the user who logs in to the call recording sharing platform for the first time, and can also be understood as including the user who uses the recording sharing platform but has not logged in. If the current user uses the platform but does not log in, the system assigns a random number, which is used to identify the user.
  • the current user is determined to be a new user; otherwise, the current user is determined not to be a new user.
  • the identifier corresponding to the current user includes a user name and password or a mobile phone number or a QR code that can identify the user.
  • the new user may also include the same user who logged in from a period of time after the first login started. The same user who logs in within 7 days after the first login starts is a new user.
  • the sales call recording record may include a plurality of tables, including a call list, a sales table, a sales call list, and the like. From the sales call recording record, know what kind of product is sold, the sales team (seller) who sells the product, whether the final sale is successful, the sales amount, the total number of calls, the number of calls, the length of each call, Talk time, specific call recording, etc.
  • the sales call recording record also includes the recommended call list. In the call record of the recommended call list, the corresponding call recording score, comment, number of likes, number of shares, and the like are saved.
  • Call records include products, sales teams (sellers), sales, talk time, call duration, specific call recordings, and more.
  • Obtaining the corresponding call record from the sales call recording record refers to obtaining the corresponding call record from the multiple tables of the sales call recording record.
  • the preset number may be 10 or other numbers.
  • the preset number can be set according to the user's setting. For example, the receiving user inputs a specific quantity in the input box, and sets the quantity to a preset quantity; the preset quantity can also be set to a fixed quantity. It can be understood that, for new users, the call recordings in all the call records on the call recording sharing platform are not viewed by the user, and are all new recordings, so the quality of the recording is good when recommending new users. Bad recommendations are made so that new users can view high quality call recordings. It should be noted that if a new user logs in to the platform, the call recording in the sales call recording is not rated and has not been praised and has not been praised and has not been shared. You can use the recommended call list.
  • the preset number of call records are randomly recommended in the call record, and the call record may be recommended in the manner of steps S103-S104.
  • the preset condition includes: the call time is within a preset time period, the call duration is within a preset time period, and the call is The first call in which the total number of times is within the preset total number of times and the sales amount reaches the preset sales amount.
  • the talk time refers to the local time at which the call starts, and the preset time period refers to a time period in which the current time is the end point. For the talk time within the preset time period, it can be understood that the talk time is recent, such as within one week, in order to update the recommended call recording in time so that the user can see the new call recording.
  • a multi-pass call record is usually generated during the successful sale of a product. For example, according to the sequence of talk time, it is called a first call record, a second call record, a third call record, and the like. Among them, the first call is the most difficult, and has a great influence on the success of the final sale, so it is recommended to recommend the call recording corresponding to the first call record.
  • the preset duration may be: 30-60 minutes
  • the preset total number of times may be 3 times
  • the preset sales amount may be the weight* the highest sales amount corresponding to the product, wherein the weight value may be 0.8.
  • the sales call recording record is obtained within one week
  • the call duration is within 30-60 minutes
  • the total number of calls is within three times
  • the sales amount reaches the first of the preset sales. Call history.
  • the call record matching the user's authority may be selected as the call record to be recommended from the call record satisfying the preset condition according to the user's authority, or may be selected from the call record satisfying the preset condition according to the personalized feature of the user.
  • the corresponding call record is used as the call record to be recommended.
  • the corresponding call record can also be obtained in other ways as the call record to be recommended. It should be noted that the number of fields corresponding to each record in the call record to be recommended may be less than the number of fields in the call record satisfying the preset condition, or may be the same.
  • the corresponding fields include: product, recommendation team (recommended person), sales, call duration, specific call recording, etc.; the fields in the call record that meet the preset conditions include: product, Recommended team (recommended person), sales, talk time, call duration, specific call recording, etc.
  • the call record to be recommended is displayed to the current user according to a preset format.
  • the preset format includes displaying corresponding call records according to different products, and includes the number of call records displayed under each product, each call record according to the same description rule and/or naming rules.
  • the description rules and/or naming rules can be: product + recommendation team (recommended person) + sales + call duration + specific call recording.
  • the foregoing embodiment can recommend different call recordings for different users, improve the accuracy of the recording recommendation, and improve the user experience.
  • FIG. 2 is a schematic diagram of a sub-flow of a recording recommendation method according to an embodiment of the present application.
  • the corresponding call record is selected from the sales call recording record as the call record to be recommended according to the first preset rule, that is, step S102 includes S201-S203.
  • S201 Obtain a score, a comment, a number of praises, and a share quantity of the call recording corresponding to the recommended call record from the sales call recording record.
  • the call recording can be evaluated, such as ratings, comments, likes, and sharing, and each user can evaluate the recorded call recording in one of the ways. Evaluation can also be carried out in a variety of ways, and of course, no evaluation can be made. If the recommended call list is saved in the sales call recording record, the relevant call recording information is saved in the call list, and the related call recording information includes the recording score, the comment content, the number of likes and the number of shares. Specifically, each user's rating of the recording may be a star rating, such as a total score of 10 points, and a star indicates one point.
  • the comment is to enter the evaluation of the user after listening to the recording in the input box, such as calling the rich text editing plug-in of ckeditor to edit the evaluation.
  • There are many channels to share when sharing recordings including mainstream social tools such as WeChat, Weibo, etc., which can be shared to groups when sharing, or individuals, such as friends on the call recording sharing platform, etc. Share on the current user's personal social page.
  • mainstream social tools such as WeChat, Weibo, etc.
  • the number of praises here also includes the number of color reductions.
  • the thumb-up mark indicates the like, and the thumb-down mark indicates the color.
  • M is the recommended score
  • A represents the score normalization value
  • B represents the favorable rate
  • C represents The rating rate
  • D indicates the number of shares to be equalized.
  • Scoring normalized value the obtained recording score/recording total score. If the obtained recording score is 8, and the total score is 10, then the score is normalized to 0.8.
  • Positive rate number of comments / total number of comments.
  • a keyword of each comment in the comment is extracted, if one of the extracted keywords is a preset keyword, such as an emotional word of the user to the recording object, such as “great”, “very good”, etc. , make sure the review is good.
  • Like rate number of likes / (number of likes + number of inverted colors).
  • Share quantity to one value number of shares / maximum number of shares shared. The maximum number of shares shared is the maximum number of calls recorded in the call recording of the product corresponding to the call recording object.
  • the number of shares is 20, and the maximum number of shares recorded in the A product is 50, then the number of shares is 0.4.
  • the value of the corresponding item is empty, then the zero is treated as zero. If there is no sharing in the call recording, then the corresponding number of shares will be zero.
  • the call record includes a call recording.
  • This embodiment further defines how the call recording to be recommended is obtained for a new user.
  • FIG. 3 is a schematic diagram of a sub-flow of a recording recommendation method according to an embodiment of the present application.
  • the corresponding call record is selected as the call record to be recommended from the call recording that meets the preset condition according to the second preset rule, that is, step S104 includes S301-S304.
  • Obtain the call record of the current user history view and obtain the characteristics of the call record, such as the characteristics including sales, call duration, recommendation team, and the like.
  • Correlation can also be understood as similarity, and similarity can be calculated by cosine similarity and the like.
  • Cosine similarity is the degree of similarity evaluated by calculating the cosine of the two vectors. Specifically, the features such as sales, call duration, recommendation team, etc. are quantified, such as uniformly expressing the duration of the call in seconds to form a specific number; forming the quantized data into a vector; and calculating the vector between the vectors according to the cosine similarity Similarity value. The larger the similarity value is calculated, the higher the similarity between the two vectors, and the smaller the similarity value, indicating that the similarity between the two vectors is smaller.
  • S304 Sort the selected call records according to a preset sorting rule, and obtain a preset number of call recordings from the sorted call records as the call recordings to be recommended.
  • the default sorting rules include: for different products, in order of relevance from large to small, sales from high to low, talk time from near to far, and total number of calls from small to large. It can be understood that, firstly, the order is sorted according to the correlation from large to small, and the same correlation is sorted according to the order of sales from high to low, and for the same sales, the call time is sorted from near to far. For the same call time, the total number of calls is sorted in ascending order. The preset number of call records ranked first is obtained from the sorted call records as the call record to be recommended.
  • the embodiment further defines that, for an old user, viewing the recording record information according to the history of the current user, obtaining a call record to be recommended from the call record satisfying the preset condition, to recommend the call recording according to the personalized requirement of the current user. Improve the accuracy of recording recommendations while enhancing the user experience.
  • FIG. 4 is a schematic diagram of a sub-flow of a recording recommendation method according to an embodiment of the present application.
  • the corresponding call recording is selected as the call recording to be recommended from the call recording that meets the preset condition according to the second preset rule, that is, step S104 includes S401-S403.
  • the current user's rights include the current user's identity, the team in which it is located, the products being sold, and the like.
  • the current user's identity includes the manager and the general employee, among which the manager is divided into different levels, and the different levels correspond to
  • the permissions for viewing call recordings are different. Different management levels and permissions corresponding to ordinary employees can be preset. For managers, their relevant work experience is generally rich, and the novice recordings of the novices have little meaning for them. Therefore, it is possible to preset for such users, and the call recordings of the novices do not match their needs.
  • S403 Sort the selected call records according to a preset sorting rule, and obtain a preset number of call records from the sorted call records as the call record to be recommended.
  • the default sorting rule can be: order of sales from high to low, talk time from near to far, and total number of calls from small to large. Among them, it can be understood that the order is sorted according to the order of sales from high to low. For the same sales, the call time is sorted from near to far. For the same talk time, the total number of calls is less. Sort in order. The preset number of call records ranked first is obtained from the sorted call records as the call record to be recommended.
  • the foregoing embodiment further defines that, for an old user, obtaining a call record to be recommended from a call record that meets a preset condition according to the current user's authority may be understood as a recommendation with the identity of the current user and the current user's team.
  • the internal or related team's call recording, and / or the same product or similar call recording, improve the accuracy of the recording recommendation and enhance the user experience.
  • the user can further screen the call records of interest according to his own needs.
  • the current user's screening instruction is obtained, and the call record related to the current user's screening instruction is obtained from the displayed call record for display.
  • the screening conditions entered by the user in the input box and/or selected include: the call duration is 45 minutes to one hour, and the recommended team is the call record of the A team.
  • FIG. 5 is a schematic block diagram of a recording recommendation apparatus according to an embodiment of the present application.
  • the apparatus 50 includes a judging unit 501, a first selecting unit 502, an obtaining unit 503, a second selecting unit 504, and a display unit 505.
  • the determining unit 501 is configured to determine whether the current user is a new user if receiving an instruction of the current user to view the sales call recording.
  • the first selection unit 502 is configured to obtain a corresponding call record from the sales call recording record as the call record to be recommended according to the first preset rule, if the current user is a new user.
  • the obtaining unit 503 is configured to: if the current user is not a new user, obtain a call record that meets a preset condition from the sales call recording record, where the preset condition includes: the call time is within a preset time period, and the call duration is at a preset duration The first call in which the total number of calls and calls is within the preset total number of times and the sales amount reaches the preset sales amount.
  • the second selecting unit 504 is configured to select, according to the second preset rule, a corresponding call record from the call records that meet the preset condition as the call record to be recommended.
  • the display unit 505 displays the call record to be recommended to the current user
  • FIG. 6 is a schematic block diagram of a first selection unit 502 provided by an embodiment of the present application.
  • the first selecting unit is configured to select a corresponding call record from the sales call recording record as the call record to be recommended according to the first preset rule, and the first selecting unit 502 includes an evaluation obtaining unit 601, a recommendation point calculating unit 602, and a first A sort acquisition unit 603.
  • the evaluation obtaining unit 601 is configured to obtain, from the sales call recording record, the score, the comment, the number of the likes, and the number of shares of the call recording corresponding to the recommended call record.
  • M is the recommended score
  • ⁇ 1 , ⁇ 2 , ⁇ 3 , and ⁇ 4 are weight coefficients
  • ⁇ 1 + ⁇ 2 + ⁇ 3 + ⁇ 4 1
  • A represents the score normalization value
  • B represents the favorable rate
  • C represents The rating rate
  • D indicates the number of shares to be equalized.
  • the first sort acquisition unit 603 acquires a preset number of call records as the call record to be recommended from the recommended call records in descending order of recommendation.
  • the call record includes a call recording.
  • FIG. 7 is a schematic block diagram of a second selection unit 504 provided by an embodiment of the present application.
  • the second selection unit is configured to select a corresponding call record from the call records that meet the preset condition according to the second preset rule as the call record to be recommended.
  • the second selection unit 504 includes an extraction unit 701, a correlation calculation unit 702, a correlation selection unit 703, and a second order acquisition unit 704.
  • the extracting unit 701 is configured to extract features of the call record viewed by the current user history.
  • the correlation calculation unit 702 is configured to calculate a correlation between a feature and a feature in a call record that satisfies a preset condition.
  • the correlation selection unit 703 is configured to select a corresponding call recording whose correlation is greater than the correlation threshold.
  • the second sorting obtaining unit 704 is configured to sort the selected call records according to a preset sorting rule, and obtain a preset number of call records from the sorted call records as the call records to be recommended.
  • the default sorting rules include: for different products, in order of relevance from large to small, sales from high to low, talk time from near to far, and total number of calls from small to large.
  • FIG. 8 is a schematic block diagram of a second selection unit 504 according to another embodiment of the present application.
  • the second selection unit is configured to select a corresponding call recording from the call recording that meets the preset condition according to the second preset rule as the call recording to be recommended.
  • the second selection unit 504 includes a rights acquisition unit 801, a matching selection unit 802, and a third order acquisition unit 803.
  • the authority obtaining unit 801 is configured to acquire the authority of the current user.
  • the matching selection unit 802 is configured to select a call record that matches the current user right from the call records that satisfy the preset condition.
  • the third sort obtaining unit 803 sorts the selected call records according to a preset sorting rule, and uses the sorted call records as the call records to be recommended.
  • the default sorting rule can be: order of sales from high to low, talk time from near to far, and total number of calls from small to large.
  • the recording recommendation device further includes an instruction acquisition unit and a screening display unit.
  • the instruction acquisition unit is configured to obtain a screening instruction of the current user
  • the screening display unit is configured to obtain, from the displayed call record, a call record related to the current user's screening instruction for display.
  • the recording recommendation device described above can be implemented in the form of a computer program that can be run on a computer device as shown in FIG.
  • FIG. 9 is a schematic block diagram of a computer device according to an embodiment of the present application.
  • the computer device 90 can be a terminal.
  • the device 90 includes a processor 902, a memory, and a network interface 903 connected by a system bus 901, wherein the memory can include a non-volatile storage medium 904 and an internal memory 905.
  • the non-volatile storage medium 904 can store an operating system 9041 and a computer program 9042.
  • the processor 902 can be caused to perform a recording recommendation method.
  • the processor 902 is used to provide computing and control capabilities to support the operation of the entire device 90.
  • the internal memory 905 provides an environment for the operation of a computer program in a non-volatile storage medium that, when executed by the processor 902, causes the processor 902 to perform a recording recommendation method.
  • the network interface 903 is used for network communication, such as receiving instructions and the like. It will be understood by those skilled in the art that the structure shown in FIG. 90 is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation of the device 90 to which the solution of the present application is applied.
  • the specific device 90 may be It includes more or fewer components than those shown in the figures, or some components are combined, or have different component arrangements.
  • the processor 902 is configured to run a computer program stored in the memory to implement the following steps:
  • the current user is instructed to view the sales call recording, it is determined whether the current user is a new user; if the current user is a new user, the corresponding call record is selected from the sales call recording record as the call record to be recommended according to the first preset rule.
  • the call record includes a call recording; if the current user is not a new user, the call record that satisfies the preset condition is obtained from the sales call recording record; and the corresponding call record from the preset condition is selected according to the second preset rule.
  • the call record is used as the call record to be recommended; the call record to be recommended is displayed to the current user.
  • the processor 902 when the processor 902 performs the process of obtaining the corresponding call record from the sales call recording record as the to-be-recommended call record according to the first preset rule, the following steps are specifically performed:
  • the preset number of call records are sequentially acquired as the call record to be recommended.
  • the processor 902 when the processor 902 performs the selection of the corresponding call record from the call record that meets the preset condition according to the second preset rule, the following steps are performed:
  • the records are sorted according to a preset sorting rule, and a preset number of call records are obtained from the sorted call records as a call record to be recommended.
  • the processor 902 when the processor 902 performs the selection of the corresponding call record from the call record that meets the preset condition according to the second preset rule, the following steps are performed:
  • the processor 902 also performs the following steps:
  • Obtain a current user's screening instruction obtain a call record related to the current user's screening instruction from the displayed call record for display.
  • the embodiment of the present application further provides a computer readable storage medium storing a computer program, the computer program comprising program instructions, when executed by a processor, implementing the following steps:
  • the current user is instructed to view the sales call recording, it is determined whether the current user is a new user; if the current user is a new user, the corresponding call record is selected from the sales call recording record as the call record to be recommended according to the first preset rule.
  • the call record includes a call recording; if the current user is not a new user, the call record that satisfies the preset condition is obtained from the sales call recording record; and the corresponding call record from the preset condition is selected according to the second preset rule.
  • the call record is used as the call record to be recommended; the call record to be recommended is displayed to the current user.
  • the specific implementation is:
  • the preset number of call records are sequentially acquired as the call record to be recommended.
  • the program instruction is executed by the processor to select a corresponding call record from the call record that meets the preset condition according to the second preset rule, and the specific call record is to be recommended.
  • the records are sorted according to a preset sorting rule, and a preset number of call records are obtained from the sorted call records as a call record to be recommended.
  • the program instruction is executed by the processor to select a corresponding call record from the call record that meets the preset condition according to the second preset rule, and the specific call record is to be recommended.
  • Obtain a current user's screening instruction obtain a call record related to the current user's screening instruction from the displayed call record for display.

Landscapes

  • Engineering & Computer Science (AREA)
  • Business, Economics & Management (AREA)
  • Theoretical Computer Science (AREA)
  • Strategic Management (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Data Mining & Analysis (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Tourism & Hospitality (AREA)
  • Human Resources & Organizations (AREA)
  • Economics (AREA)
  • Marketing (AREA)
  • General Business, Economics & Management (AREA)
  • Finance (AREA)
  • Development Economics (AREA)
  • Accounting & Taxation (AREA)
  • Multimedia (AREA)
  • General Engineering & Computer Science (AREA)
  • Databases & Information Systems (AREA)
  • Educational Technology (AREA)
  • Educational Administration (AREA)
  • Health & Medical Sciences (AREA)
  • Library & Information Science (AREA)
  • Quality & Reliability (AREA)
  • Operations Research (AREA)
  • Primary Health Care (AREA)
  • General Health & Medical Sciences (AREA)
  • Game Theory and Decision Science (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)
  • Information Retrieval, Db Structures And Fs Structures Therefor (AREA)

Abstract

本申请实施例提供一种录音推荐方法、装置、设备及计算机可读存储介质。所述方法包括：若接收到当前用户查看销售通话录音的指令，判断当前用户是否为新用户；若当前用户为新用户，根据第一预设规则从销售通话录音记录中选择相应的通话记录作为待推荐的通话记录，其中，通话记录中包括有通话录音；若当前用户不为新用户，从销售通话录音记录中获取满足预设条件的通话记录；根据第二预设规则从满足预设条件的通话记录中选择相应的通话记录作为待推荐的通话记录；向当前用户显示待推荐的通话记录。本申请实施例可针对不同的用户推荐不同的通话录音，提高录音推荐的精确度，提升用户的体验。

Description

一种录音推荐方法、装置、设备及计算机可读存储介质
本申请要求于2017年12月28日提交中国专利局、申请号为201711460485.2、发明名称为“一种录音推荐方法、装置、设备及计算机可读存储介质”的中国专利申请的优先权，其全部内容通过引用结合在本申请中。
技术领域
本申请涉及信息处理技术领域，尤其涉及一种录音推荐方法、装置、设备及计算机可读存储介质。
背景技术
电话销售的销售坐席每天产生几百万的通话记录，通话记录中包括有通话录音，通话录音是坐席销售经验的体现。另一方面，团队内部坐席经验分享，新人培养，需要实践经验参考。因此可搭建一个通话录音分享平台，将电话销售的坐席产生的通话记录对应的通话录音分享给该平台中的用户，以供他们学习。若将每天产生的通话记录对应的通话录音不加选择都推荐给该平台中的用户学习，那么查看众多的通话录音中的无价值通话录音既会浪费时间，也不能起到经验参考的作用。另外，由于该平台中的用户不同，销售的产品不尽相同，销售经验也不一样，很多用户无法得到自己真正感兴趣的通话录音，导致用户的体验不高。
发明内容
本申请实施例提供了一种录音推荐方法、装置、设备及计算机可读存储介质，可以针对不同的用户推荐不同的通话录音，提高录音推荐的精确度，提升用户的体验。
第一方面，本申请实施例提供了一种录音推荐方法，该方法包括：
若接收到当前用户查看销售通话录音的指令，判断当前用户是否为新用户；若 当前用户为新用户，根据第一预设规则从销售通话录音记录中选择相应的通话记录作为待推荐的通话记录，其中，通话记录中包括有通话录音；若当前用户不为新用户，从销售通话录音记录中获取满足预设条件的通话记录；根据第二预设规则从满足预设条件的通话记录中选择相应的通话记录作为待推荐的通话记录；向当前用户显示待推荐的通话记录。
第二方面，本申请实施例提供了一种录音推荐装置，该装置包括用于执行上述第一方面所述的录音推荐方法的单元。
第三方面，本申请实施例还提供了一种计算机设备，所述计算机设备包括存储器，以及与所述存储器相连的处理器；
所述存储器用于存储实现录音推荐的计算机程序，所述处理器用于运行所述存储器中存储的计算机程序，以执行上述第一方面所述的录音推荐方法。
第四方面，本申请实施例提供了一种计算机可读存储介质，所述计算机可读存储介质存储有计算机程序，所述计算机程序包括程序指令，所述程序指令当被处理器执行时，实现上述第一方面所述的录音推荐方法。
本申请实施例通过若接收到当前用户查看销售通话录音的指令，判断当前用户是否为新用户；若当前用户为新用户，根据第一预设规则从销售通话录音记录中选择相应的通话记录作为待推荐的通话记录，其中，通话记录中包括有通话录音；若当前用户不为新用户，从销售通话录音记录中获取满足预设条件的通话记录；根据第二预设规则从满足预设条件的通话记录中选择相应的通话记录作为待推荐的通话记录；向当前用户显示待推荐的通话记录。该发明实施例可针对不同的用户推荐不同的通话录音，提高录音推荐的精确度，提升用户的体验。
附图说明
图1是本申请实施例提供的一种录音推荐方法的流程示意图；
图2是本申请实施例提供的一种录音推荐方法的子流程示意图；
图3是本申请另一实施例提供的一种录音推荐方法的子流程示意图；
图4是本申请又一实施例提供的一种录音推荐方法的子流程示意图；
图5是本申请实施例提供的录音推荐装置的示意性框图；
图6是本申请实施例提供的第一选择单元的示意性框图；
图7本申请实施例提供的第二选择单元的示意性框图；
图8是另一本申请实施例提供的第二选择单元的示意性框图；
图9是本申请实施例一种计算机设备的示意性框图。
具体实施方式
图1是本申请实施例提供的一种录音推荐方法的流程示意图。该方法包括S101-S105。
S101，若接收到当前用户查看销售通话录音的指令，判断当前用户是否为新用户。
在通话录音分享平台中，当用户打开录音推荐页面或者点击查看录音推荐的按钮时，则视为接收到查看销售通话录音的指令。接收到当前用户查看销售通话录音的指令时，判断当前用户是否为新用户。其中，新用户包括第一次登陆该通话录音分享平台的用户，也可以理解为包括使用了该录音分享平台，但是未登录的用户。若当前用户使用了该平台，但没有登陆，那么系统会分配一个随机数，用该随机数来标识该用户。若在该平台的数据库中没有检索到当前用户的对应的标识，或者检测到当前用户的标识是随机数，那么判定当前用户为新用户，否则，判定当前用户不为新用户。其中，当前用户对应的标识包括用户名和密码或者手机号码或者能标识用户的二维码等。在其他实施例中，新用户也可以包括从第一次登陆开始后的一段时间内登陆的同一用户。如从第一次登陆开始后的7天内登陆的同一用户都属于新用户。
S102，若当前用户为新用户，根据第一预设规则从销售通话录音记录中获取相应的通话记录作为待推荐的通话记录。
在销售通话录音记录中保存有所有的销售录音情况，包括通话的相关情况与销售业务的销售情况。具体地，销售通话录音记录中可以包括多张表，其中包括通话表、销售表、销售通话表等。从销售通话录音记录中知道销售的是何种产品、销售该产品的销售团队(销售人)、最终销售是否成功、销售额、通话总次数、是第几通的通话、每一通的通话时长、通话时间、具体的通话录音等。销售通话录音记录中还包括已推荐过的通话表，在已推荐过的通话表的通 话记录中，保存有对应的通话录音的评分、评论、点赞数量、分享数量等。通话记录包括产品、销售团队(销售人)、销售额、通话时间、通话时长、具体的通话录音等。从销售通话录音记录中获取相应的通话记录指的是从销售通话录音记录的多张表中获取相应的通话记录。根据第一预设规则从销售通话录音记录中获取相应的通话记录作为待推荐的通话记录，包括：按照通话录音评分从高到低的顺序、或者按照通话录音评论数从高到低的顺序、或者按照通话录音点赞数量从高到低的顺序、或者按照通话录音分享数量从高到低的顺序从销售通话录音记录中获取预设数量的通话记录作为待推荐的通话记录。在其他实施例中，也可以多个相结合的方式。其中，预设数量可以为10个，也可以为其他的数量。预设数量可以根据用户的设定进行设置，如接收用户在输入框中输入具体的数量，将该数量设置为预设数量；预设数量也可以设置为固定的数量。可以理解为，对于新用户来说，该通话录音分享平台上的所有通话记录中的通话录音都没有被该用户查看过，都是新的录音，因此对新用户进行推荐时按照录音质量的好坏进行推荐，以让新用户可以查看到高质量的通话录音。需要注意的是，若新用户登陆该平台后，销售通话录音记录中的通话录音没有被评分过且没有被好评过且没有被点赞过且没有被分享过，可以从已推荐过的通话表的通话记录中随机推荐预设数量的通话记录，也可以按照步骤S103-S104中的方式推荐通话记录。
S103，若当前用户不为新用户，从销售通话录音记录中获取满足预设条件的通话记录，其中，预设条件包括：通话时间在预设时间段内、通话时长在预设时长内、通话总次数在预设总次数内且销售额达到预设销售额的第一通通话。其中，通话时间指的是通话开始的本地时间，预设时间段指的是以当前时间为终点的一个时间段。对于通话时间在预设时间段内，可以理解为，通话时间是近期的，如一个星期之内，以便及时更新推荐的通话录音，以让用户能看到新的通话录音。从另一方面理解，用户并不想每次看到的都是推荐的同样的通话录音，因为这些录音用户可能已经看到过了。由于一般对于电话销售的坐席来说，在某个产品成功销售的过程中，通常会产生多通通话记录。如按照通话时间先后顺序分别称为第一通通话记录、第二通通话记录、第三通通话记录等。其中，第一通通话是难度最大，且对最终销售是否成功有很大影响，因此选择 推荐第一通通话记录对应的通话录音。譬如，预设时长可以为：30-60分钟，预设总次数可以为3次，预设销售额可以为权重*该产品对应的最高销售额，其中权重的值可以为0.8。具体地，若当前用户不为新用户，从销售通话录音记录中获取一个星期之内、通话时长在30-60分钟内，通话总次数在3次内，销售额达到预设销售额的第一通通话记录。
S104，根据第二预设规则从满足预设条件的通话记录中选择相应的通话记录作为待推荐的通话记录。
可以按照用户的权限从满足预设条件的通话记录中选择与用户的权限相匹配的通话记录作为待推荐的通话记录，也可以是根据用户的个性化特征从满足预设条件的通话记录中选择相应的通话记录作为待推荐的通话记录。也可以按照其他的方式来获取相应的通话记录作为待推荐的通话记录。需要注意的是，待推荐的通话记录中每一条记录对应的字段个数可以少于满足预设条件的通话记录中的字段个数，也可以相同。如待推荐的通话记录中每一条记录对应的字段包括：产品、推荐团队(推荐人)、销售额、通话时长、具体的通话录音等；满足预设条件的通话记录中的字段包括：产品、推荐团队(推荐人)、销售额、通话时间、通话时长、具体的通话录音等。
S105，向当前用户显示待推荐的通话记录。
其中，按照预设格式向当前用户显示待推荐的通话记录。预设格式包括按照不同的产品来显示对应的通话记录，同时包括每个产品下显示的通话记录的个数，每个通话记录按照相同的描述规则和/或命名规则等。如描述规则和/或命名规则可以为：产品+推荐团队(推荐人)+销售额+通话时长+具体的通话录音。通过描述规则和/或命名规则，以方便当前用户简单快速的了解通话录音，以确定是否要查看该通话录音。点击通话记录对应的通话录音就可以查看具体的通话录音。预设格式也可以为其他的格式，在此不做限定。
上述实施例可针对不同的用户推荐不同的通话录音，提高录音推荐的精确度，提升用户的体验。
图2是本申请实施例提供的一种录音推荐方法的子流程示意图。如图2所示，根据第一预设规则从销售通话录音记录中选择相应的通话记录作为待推荐的通话记录，即步骤S102包括S201-S203。
S201，从销售通话录音记录中获取已推荐过的通话记录对应的通话录音的评分、评论、点赞数量和分享数量。
可以理解地，每个用户查看具体的通话录音后，可以对通话录音进行评价，如评分、评论、点赞和分享等，每个用户可以使用其中一种方式对查看过的通话录音进行评价，也可以使用多种方式进行评价，当然也可以不进行任何评价。如在销售通话录音记录中保存有已推荐过的通话表，在该通话表中保存有相关的通话录音信息，相关的通话录音信息包括录音评分、评论内容、点赞数量和分享数量等。具体地，每个用户对录音的评分可以是星级评分，如总分是10分，用一个星星表示一分。评论即为在输入框中输入用户听完录音后的评价，如调用ckeditor的富文本编辑插件来编辑评价。分享录音时分享的渠道有多种，包括主流的社交工具，如微信、微博等，分享时可以分享给群组，也可以是个人，如该通话录音分享平台上认识的好友等，还可以分享到当前用户个人的社交网页上。需要注意的是这里的点赞数量中也包括了倒彩数量，如拇指朝上的标识表示点赞，用拇指朝下的标识表示倒彩。
S202，根据预设公式计算通话录音的推荐分，其中，预设公式为：M＝λ 1A+λ 2B+λ 3C+λ 4D。
其中，M为推荐分，λ 1、λ 2、λ 3、λ 4为权重系数，λ 1+λ 2+λ 3+λ 4＝1，A表示评分归一值，B表示好评率，C表示点赞率，D表示分享数量归一值。其中，λ 1、λ 2、λ 3、λ 4根据对应项对推荐分的重要性程度进行确定。评分归一值＝获取到的录音评分/录音总分，如获取到的录音评分是8，录音总分是10，那么评分归一值为0.8。好评率＝好评数量/评论总数量。具体地，如提取评论中每个评论的关键词，若提取的关键词中有一个关键词是预设关键词，如用户对录音对象的情感词，如“很棒”、“很好”等，确定该评论为好评。统计该录音对象的好评数量，根据好评率＝好评数量/评论总数量，计算出好评率。点赞率＝点赞数量/(点赞数量+倒彩数量)。分享数量归一值＝分享的数量/分享的最大数量。其中，分享的最大数量为通话录音对象对应的产品的通话录音中分享的最大数量。如针对A产品中的一个通话录音，分享数量为20，A产品对应的通话录音中分享的最大数量为50，那么分享数量归一值为0.4。对于一个通话录音，若其中有对应项的值为空，那么将该零视为零。如通话录音中没有分享，那么对 应的分享数量归一值就为零。
S203，从已推荐过的通话记录中按照推荐分从高到低的顺序获取预设数量的通话记录作为待推荐的通话记录。其中，通话记录中包括有通话录音。
该实施例进一步限定了，对于新用户来说是如何获取待推荐的通话录音的。
图3是本申请实施例提供的一种录音推荐方法的子流程示意图。如图3所示，根据第二预设规则从满足预设条件的通话录音中选择相应的通话记录作为待推荐的通话记录，即步骤S104包括S301-S304。
S301，提取当前用户历史查看的通话记录的特征。
获取当前用户历史查看的通话记录，并获取该通话记录的特征，如特征包括销售额、通话时长、推荐团队等。
S302，计算特征与满足预设条件的通话记录中的特征之间的相关性。
相关性也可以理解为相似度，相似度可以通过余弦相似度等计算出来。余弦相似度，是通过计算两个向量的夹角余弦值来评估他们的相似度。具体地，将特征如销售额、通话时长、推荐团队等进行量化，如将通话时长统一用秒来表示成一个具体的数字；将量化后的数据形成向量；再根据余弦相似度计算向量之间的相似度值。计算出来的相似度值越大，表明两个向量之间的相似度越高，相似度值越小，表明两个向量之间的相似度越小。
S303，选择相关性大于相关性阈值的对应的通话录音。
可以理解为，满足预设条件的通话录音中的特征与用户历史查看的录音记录中的特征很相似，如销售额与用户历史查看的录音记录中的销售额相差不大等。
S304，将选择的通话记录按照预设排序规则进行排序，从排序后的通话记录中获取预设数量的通话录音作为待推荐的通话录音。
预设排序规则包括：对于不同的产品，按照相关性从大到小、销售额从高到低、通话时间由近到远、通话总次数由少到多的顺序。其中，可以理解为，先按照相关性从大到小的顺序排序，对于同一相关性，按照销售额从高到低的顺序排序，对于同一销售额，按照通话时间由近到远的顺序排序，对于同一通话时间的，按照通话总次数由少到多的顺序排序。从排序后的通话记录中获取排序靠前的预设数量的通话记录作为待推荐的通话记录。
该实施例进一步限定了，对于老用户来说，根据当前用户的历史查看录音记录信息从满足预设条件的通话记录中获取待推荐的通话记录，以根据当前用户的个性化需求来推荐通话录音，提高录音推荐的精确度，同时提升用户的体验。
图4是本申请实施例提供的一种录音推荐方法的子流程示意图。如图3所示，根据第二预设规则从满足预设条件的通话录音中选择相应的通话录音作为待推荐的通话录音，即步骤S104包括S401-S403。
S401，获取当前用户的权限。
其中，当前用户的权限包括当前用户的身份、所在的团队、所销售的产品等，如当前用户的身份包括管理者和普通员工等，其中，管理者分为不同的级别，不同的级别对应的查看通话录音的权限不同。不同的管理级别以及普通员工对应的权限可以预先设定。如对于管理者而言，其相关工作经验一般较为丰富，新手的通话录音对其借鉴意义不大，因此可预先设定针对这类用户，新手的通话录音则不属于与其需求匹配。
S402，从满足预设条件的通话记录中选择与当前用户权限匹配的通话记录。
从满足预设条件的通话记录中，选择与当前用户的身份以及当前用户所在的团队内部或者相关团队的通话记录，或者选择与当前用户的身份以及所销售的产品相同或者相类似的通话记录，或者选择与当前用户的身份、当前用户所在的团队内部或者相关团队、以及所销售的产品相同或者相类似的通话记录。可以理解为，对于用户来说，最希望看到的是自己团队内部或者相关团队销售成功的通话录音，以及与自己所销售的产品相同或者相类似的销售成功的通话录音，因为对自己的指导意义较大。
S403，将选择的通话记录按照预设排序规则进行排序，从排序后的通话记录中获取预设数量的通话记录作为待推荐的通话记录。
预设排序规则可以为：按照销售额从高到低、通话时间由近到远、通话总次数由少到多的顺序。其中，可以理解为，先按照按照销售额从高到低的顺序排序，对于同一销售额，按照通话时间由近到远的顺序排序，对于同一通话时间的，按照通话总次数由少到多的顺序排序。从排序后的通话记录中获取排序靠前的预设数量的通话记录作为待推荐的通话记录。
上述实施例进一步限定了，对于老用户来说，根据当前用户的权限从满足预设条件的通话记录中获取待推荐的通话记录，可以理解为，推荐与当前用户的身份以及当前用户所在的团队内部或者相关团队的通话录音、和/或所销售的产品相同或者相类似的通话录音，提高录音推荐的精确度，提升用户的体验。
在其他实施例中，可以理解为，当用户得到的待推荐的通话记录有很多时，用户可以根据自己的需求进一步筛查自己感兴趣的通话记录。具体地，获取当前用户的筛查指令，从显示的通话记录中获取与当前用户的筛查指令相关的通话记录进行显示。如获取用户在输入框中输入的和/或选择的筛查条件，如输入的和/或选择的筛查条件包括：通话时长为45分钟到一个小时，推荐团队为A团队的通话记录。
图5是本申请实施例提供的一种录音推荐装置的示意性框图。该装置50包括判断单元501、第一选择单元502、获取单元503、第二选择单元504、显示单元505。
判断单元501用于若接收到当前用户查看销售通话录音的指令，判断当前用户是否为新用户。第一选择单元502用于若当前用户为新用户，根据第一预设规则从销售通话录音记录中获取相应的通话记录作为待推荐的通话记录。获取单元503用于若当前用户不为新用户，从销售通话录音记录中获取满足预设条件的通话记录，其中，预设条件包括：通话时间在预设时间段内、通话时长在预设时长内、通话总次数在预设总次数内且销售额达到预设销售额的第一通通话。第二选择单元504用于根据第二预设规则从满足预设条件的通话记录中选择相应的通话记录作为待推荐的通话记录。显示单元505向当前用户显示待推荐的通话记录。
图6是本申请实施例提供的第一选择单元502的示意性框图。该第一选择单元用于根据第一预设规则从销售通话录音记录中选择相应的通话记录作为待推荐的通话记录，该第一选择单元502包括评价获取单元601、推荐分计算单元602、第一排序获取单元603。
评价获取单元601用于从销售通话录音记录中获取已推荐过的通话记录对应的通话录音的评分、评论、点赞数量和分享数量。推荐分计算单元602用于根据预设公式计算通话录音的推荐分，其中，预设公式为： M＝λ 1A+λ 2B+λ 3C+λ 4D。其中，M为推荐分，λ 1、λ 2、λ 3、λ 4为权重系数，λ 1+λ 2+λ 3+λ 4＝1，A表示评分归一值，B表示好评率，C表示点赞率，D表示分享数量归一值。其中，λ 1、λ 2、λ 3、λ 4根据对应项对推荐分的重要性程度进行确定。第一排序获取单元603从已推荐过的通话记录中按照推荐分从高到低的顺序获取预设数量的通话记录作为待推荐的通话记录。其中，通话记录中包括有通话录音。
图7是本申请实施例提供的第二选择单元504的示意性框图。该第二选择单元用于根据第二预设规则从满足预设条件的通话记录中选择相应的通话记录作为待推荐的通话记录。如图7所示，该第二选择单元504包括提取单元701、相关性计算单元702、相关性选择单元703、第二排序获取单元704。
提取单元701用于提取当前用户历史查看的通话记录的特征。相关性计算单元702用于计算特征与满足预设条件的通话记录中的特征之间的相关性。相关性选择单元703用于选择相关性大于相关性阈值的对应的通话录音。第二排序获取单元704用于将选择的通话记录按照预设排序规则进行排序，从排序后的通话记录中获取预设数量的通话记录作为待推荐的通话记录。预设排序规则包括：对于不同的产品，按照相关性从大到小、销售额从高到低、通话时间由近到远、通话总次数由少到多的顺序。
图8是本申请另一实施例提供的第二选择单元504的示意性框图。该第二选择单元用于根据第二预设规则从满足预设条件的通话录音中选择相应的通话录音作为待推荐的通话录音。该第二选择单元504包括权限获取单元801、匹配选择单元802、第三排序获取单元803。
权限获取单元801用于获取当前用户的权限。匹配选择单元802用于从满足预设条件的通话记录中选择与当前用户权限匹配的通话记录。第三排序获取单元803将选择的通话记录按照预设排序规则进行排序，将排序后的通话记录作为待推荐的通话记录。预设排序规则可以为：按照销售额从高到低、通话时间由近到远、通话总次数由少到多的顺序。
在其他实施例中，可以理解为，当用户得到的待推荐的通话记录有很多时，用户可以根据自己的需求进一步筛查自己感兴趣的通话记录。具体地，录音推荐装置还包括指令获取单元、筛查显示单元。指令获取单元用于获取当前用户 的筛查指令，筛查显示单元用于从显示的通话记录中获取与当前用户的筛查指令相关的通话记录进行显示。
上述描述的装置和单元的具体工作过程，可以参考前述方法实施例中的对应过程，达到的有益效果也可以参考前述方法实施例中达到的有益效果，在此不再赘述。
上述录音推荐装置可以实现为一种计算机程序的形式，该计算机程序可以在如图9所示的计算机设备上运行。
图9为本申请实施例提供的一种计算机设备的示意性框图。该计算机设备90可以是终端。该设备90包括通过系统总线901连接的处理器902、存储器和网络接口903，其中，存储器可以包括非易失性存储介质904和内存储器905。
该非易失性存储介质904可存储操作系统9041和计算机程序9042。该计算机程序9042被执行时，可使得处理器902执行一种录音推荐方法。
该处理器902用于提供计算和控制能力，支撑整个设备90的运行。
该内存储器905为非易失性存储介质中的计算机程序的运行提供环境，该计算机程序被处理器902执行时，可使得处理器902执行一种录音推荐方法。
该网络接口903用于进行网络通信，如接收指令等。本领域技术人员可以理解，图90中示出的结构，仅仅是与本申请方案相关的部分结构的框图，并不构成对本申请方案所应用于其上的设备90的限定，具体的设备90可以包括比图中所示更多或更少的部件，或者组合某些部件，或者具有不同的部件布置。
其中，处理器902用于运行存储在存储器中的计算机程序，以实现如下步骤：
若接收到当前用户查看销售通话录音的指令，判断当前用户是否为新用户；若当前用户为新用户，根据第一预设规则从销售通话录音记录中选择相应的通话记录作为待推荐的通话记录，其中，通话记录中包括通话录音；若当前用户不为新用户，从销售通话录音记录中获取满足预设条件的通话记录；根据第二预设规则从满足预设条件的通话记录中选择相应的通话记录作为待推荐的通话记录；向当前用户显示待推荐的通话记录。
在一实施例中，处理器902执行根据第一预设规则从销售通话录音记录中获取相应的通话记录作为待推荐的通话记录时，具体执行如下步骤：
从销售通话录音记录中获取已推荐过的通话记录对应的通话录音的评分、评论、点赞数量和分享数量；根据预设公式计算所述通话录音的推荐分，其中，预设公式为：M＝λ 1A+λ 2B+λ 3C+λ 4D，其中，M为推荐分，λ 1、λ 2、λ 3、λ 4为权重系数，λ 1+λ 2+λ 3+λ 4＝1，A表示评分归一值，B表示好评率，C表示点赞率，D表示分享数量归一值；从已推荐过的通话记录中按照对应的通话录音的推荐分从高到低的顺序获取预设数量的通话记录作为待推荐的通话记录。
在一实施例中，处理器902执行根据第二预设规则从满足预设条件的通话记录中选择相应的通话记录作为待推荐的通话记录时，具体执行如下步骤：
提取当前用户历史查看的通话记录的特征；计算所述特征与满足预设条件的通话记录中的特征之间的相关性；选择所述相关性大于相关性阈值对应的通话记录；将选择的通话记录按照预设排序规则进行排序，从排序后的通话记录中获取预设数量的通话记录作为待推荐的通话记录。
在一实施例中，处理器902执行根据第二预设规则从满足预设条件的通话记录中选择相应的通话记录作为待推荐的通话记录时，具体执行如下步骤：
获取当前用户的权限；从满足预设条件的通话记录中选择与当前用户权限匹配的通话记录；将选择的通话记录按照预设排序规则进行排序，从排序后的通话记录中获取预设数量的通话记录作为待推荐的通话记录。
在一实施例中，处理器902还执行如下步骤：
获取当前用户的筛查指令；从显示的通话记录中获取与当前用户的筛查指令相关的通话记录进行显示。
本申请实施例还提供一种计算机可读存储介质，所述计算机可读存储介质存储有计算机程序，所述计算机程序包括程序指令，所述程序指令当被处理器执行时，实现以下步骤：
若接收到当前用户查看销售通话录音的指令，判断当前用户是否为新用户；若当前用户为新用户，根据第一预设规则从销售通话录音记录中选择相应的通话记录作为待推荐的通话记录，其中，通话记录中包括通话录音；若当前用户不为新用户，从销售通话录音记录中获取满足预设条件的通话记录；根据第二预设规则从满足预设条件的通话记录中选择相应的通话记录作为待推荐的通话记录；向当前用户显示待推荐的通话记录。
在一实施例中，该程序指令被处理器执行根据第一预设规则从销售通话录音记录中获取相应的通话记录作为待推荐的通话记录时，具体实现：
从销售通话录音记录中获取已推荐过的通话记录对应的通话录音的评分、评论、点赞数量和分享数量；根据预设公式计算所述通话录音的推荐分，其中，预设公式为：M＝λ 1A+λ 2B+λ 3C+λ 4D，其中，M为推荐分，λ 1、λ 2、λ 3、λ 4为权重系数，λ 1+λ 2+λ 3+λ 4＝1，A表示评分归一值，B表示好评率，C表示点赞率，D表示分享数量归一值；从已推荐过的通话记录中按照对应的通话录音的推荐分从高到低的顺序获取预设数量的通话记录作为待推荐的通话记录。
在一实施例中，该程序指令被处理器执行根据第二预设规则从满足预设条件的通话记录中选择相应的通话记录作为待推荐的通话记录时，具体实现：
提取当前用户历史查看的通话记录的特征；计算所述特征与满足预设条件的通话记录中的特征之间的相关性；选择所述相关性大于相关性阈值对应的通话记录；将选择的通话记录按照预设排序规则进行排序，从排序后的通话记录中获取预设数量的通话记录作为待推荐的通话记录。
在一实施例中，该程序指令被处理器执行根据第二预设规则从满足预设条件的通话记录中选择相应的通话记录作为待推荐的通话记录时，具体实现：
获取当前用户的权限；从满足预设条件的通话记录中选择与当前用户权限匹配的通话记录；将选择的通话记录按照预设排序规则进行排序，从排序后的通话记录中获取预设数量的通话记录作为待推荐的通话记录。
在一实施例中，该程序指令被处理器执行时，具体实现：
获取当前用户的筛查指令；从显示的通话记录中获取与当前用户的筛查指令相关的通话记录进行显示。
所属领域的技术人员可以清楚地了解到，为了描述的方便和简洁，上述描述的设备、装置和单元的具体工作过程，可以参考前述方法实施例中的对应过程，在此不再赘述。以上所述，仅为本申请的具体实施方式，但本申请的保护范围并不局限于此，任何熟悉本技术领域的技术人员在本申请揭露的技术范围内，可轻易想到各种等效的修改或替换，这些修改或替换都应涵盖在本申请的保护范围之内。

Claims (20)

  1. 一种录音推荐方法，其特征在于，所述方法包括：
    若接收到当前用户查看销售通话录音的指令，判断当前用户是否为新用户；
    若当前用户为新用户，根据第一预设规则从销售通话录音记录中选择相应的通话记录作为待推荐的通话记录，其中，通话记录中包括通话录音；
    若当前用户不为新用户，从销售通话录音记录中获取满足预设条件的通话记录；
    根据第二预设规则从满足预设条件的通话记录中选择相应的通话记录作为待推荐的通话记录；
    向当前用户显示待推荐的通话记录。
  2. 如权利要求1所述的方法，其特征在于，所述根据第一预设规则从销售通话录音记录中获取相应的通话记录作为待推荐的通话记录，包括：
    从销售通话录音记录中获取已推荐过的通话记录对应的通话录音的评分、评论、点赞数量和分享数量；
    根据预设公式计算所述通话录音的推荐分，其中，预设公式为：M＝λ 1A+λ 2B+λ 3C+λ 4D，其中，M为推荐分，λ 1、λ 2、λ 3、λ 4为权重系数，λ 1+λ 2+λ 3+λ 4＝1，A表示评分归一值，B表示好评率，C表示点赞率，D表示分享数量归一值；
    从已推荐过的通话记录中按照对应的通话录音的推荐分从高到低的顺序获取预设数量的通话记录作为待推荐的通话记录。
  3. 如权利要求1所述的方法，其特征在于，所述根据第二预设规则从满足预设条件的通话录音记录中选择相应的通话记录作为待推荐的通话记录，包括：
    提取当前用户历史查看的通话记录的特征；
    计算所述特征与满足预设条件的通话记录中的特征之间的相关性；
    选择所述相关性大于相关性阈值对应的通话记录；
    将选择的通话记录按照预设排序规则进行排序，从排序后的通话记录中获取预设数量的通话记录作为待推荐的通话记录。
  4. 如权利要求1所述的方法，其特征在于，所述根据第二预设规则从满足 预设条件的通话记录中选择相应的通话记录作为待推荐的通话记录，包括：
    获取当前用户的权限；
    从满足预设条件的通话记录中选择与当前用户权限匹配的通话记录；
    将选择的通话记录按照预设排序规则进行排序，从排序后的通话记录中获取预设数量的通话记录作为待推荐的通话记录。
  5. 如权利要求1所述的方法，其特征在于，所述方法还包括：
    获取当前用户的筛查指令；
    从显示的通话记录中获取与当前用户的筛查指令相关的通话记录进行显示。
  6. 一种录音推荐装置，其特征在于，所述装置包括：
    判断单元，用于若接收到当前用户查看销售通话录音的指令，判断当前用户是否为新用户；
    第一选择单元，用于若当前用户为新用户，根据第一预设规则从销售通话录音记录中选择相应的通话记录作为待推荐的通话记录；
    获取单元，用于若当前用户不为新用户，从销售通话录音记录中获取满足预设条件的通话记录；
    第二选择单元，用于根据第二预设规则从满足预设条件的通话记录中选择相应的通话记录作为待推荐的通话记录；
    显示单元，用于向当前用户显示待推荐的通话记录。
  7. 如权利要求6所述的装置，其特征在于，所述第一选择单元包括：
    评价获取单元，用于从销售通话录音记录中获取已推荐过的通话记录对应的通话录音的评分、评论、点赞数量和分享数量；
    推荐分计算单元，用于根据预设公式计算所述通话录音的推荐分，其中，预设公式为：M＝λ 1A+λ 2B+λ 3C+λ 4D，其中，M为推荐分，λ 1、λ 2、λ 3、λ 4为权重系数，λ 1+λ 2+λ 3+λ 4＝1，A表示评分归一值，B表示好评率，C表示点赞率，D表示分享数量归一值；
    第一排序获取单元，用于从已推荐过的通话记录中按照对应的通话录音的推荐分从高到低的顺序获取预设数量的通话记录作为待推荐的通话记录。
  8. 如权利要求6所述的装置，其特征在于，所述第二选择单元，包括：
    提取单元，用于提取当前用户历史查看的通话记录的特征；
    相关性计算单元，用于计算所述特征与满足预设条件的通话记录中的特征之间的相关性；
    相关性选择单元，用于选择所述相关性大于相关性阈值对应的通话记录；
    第二排序获取单元，用于将选择的通话记录按照预设排序规则进行排序，从排序后的通话记录中获取预设数量的通话记录作为待推荐的通话记录。
  9. 如权利要求6所述的装置，其特征在于，所述第二选择单元，包括：
    权限获取单元，用于获取当前用户的权限；
    匹配选择单元，用于从满足预设条件的通话记录中选择与当前用户权限匹配的通话记录；
    第三排序获取单元，用于将选择的通话记录按照预设排序规则进行排序，从排序后的通话记录中获取预设数量的通话记录作为待推荐的通话记录。
  10. 如权利要求6所述的装置，其特征在于，所述装置还包括：
    指令获取单元，用于获取当前用户的筛查指令；
    筛查显示单元，用于从显示的通话记录中获取与当前用户的筛查指令相关的通话记录进行显示。
  11. 一种计算机设备，其特征在于，所述计算机设备包括存储器，以及与所述存储器相连的处理器；
    所述存储器用于存储实现录音推荐的计算机程序；所述处理器用于运行所述存储器中存储的计算机程序，以执行如下步骤：
    若接收到当前用户查看销售通话录音的指令，判断当前用户是否为新用户；
    若当前用户为新用户，根据第一预设规则从销售通话录音记录中选择相应的通话记录作为待推荐的通话记录，其中，通话记录中包括通话录音；
    若当前用户不为新用户，从销售通话录音记录中获取满足预设条件的通话记录；
    根据第二预设规则从满足预设条件的通话记录中选择相应的通话记录作为待推荐的通话记录；
    向当前用户显示待推荐的通话记录。
  12. 如权利要求11所述的计算机设备，其特征在于，所述处理器执行所述 根据第一预设规则从销售通话录音记录中获取相应的通话记录作为待推荐的通话记录时，具体实现：
    从销售通话录音记录中获取已推荐过的通话记录对应的通话录音的评分、评论、点赞数量和分享数量；
    根据预设公式计算所述通话录音的推荐分，其中，预设公式为：M＝λ 1A+λ 2B+λ 3C+λ 4D，其中，M为推荐分，λ 1、λ 2、λ 3、λ 4为权重系数，λ 1+λ 2+λ 3+λ 4＝1，A表示评分归一值，B表示好评率，C表示点赞率，D表示分享数量归一值；
    从已推荐过的通话记录中按照对应的通话录音的推荐分从高到低的顺序获取预设数量的通话记录作为待推荐的通话记录。
  13. 如权利要求11所述的计算机设备，其特征在于，所述根据第二预设规则从满足预设条件的通话录音记录中选择相应的通话记录作为待推荐的通话记录时，具体实现：
    提取当前用户历史查看的通话记录的特征；
    计算所述特征与满足预设条件的通话记录中的特征之间的相关性；
    选择所述相关性大于相关性阈值对应的通话记录；
    将选择的通话记录按照预设排序规则进行排序，从排序后的通话记录中获取预设数量的通话记录作为待推荐的通话记录。
  14. 如权利要求11所述的计算机设备，其特征在于，所述根据第二预设规则从满足预设条件的通话录音记录中选择相应的通话记录作为待推荐的通话记录时，具体实现：
    获取当前用户的权限；
    从满足预设条件的通话记录中选择与当前用户权限匹配的通话记录；
    将选择的通话记录按照预设排序规则进行排序，从排序后的通话记录中获取预设数量的通话记录作为待推荐的通话记录。
  15. 如权利要求11所述的计算机设备，其特征在于，所述处理器还执行如下步骤：
    获取当前用户的筛查指令；
    从显示的通话记录中获取与当前用户的筛查指令相关的通话记录进行显 示。
  16. 一种计算机可读存储介质，其特征在于，所述计算机可读存储介质存储计算机程序，所述计算机程序包括程序指令，所述程序指令当被处理器执行时，实现如下步骤：
    若接收到当前用户查看销售通话录音的指令，判断当前用户是否为新用户；
    若当前用户为新用户，根据第一预设规则从销售通话录音记录中选择相应的通话记录作为待推荐的通话记录，其中，通话记录中包括通话录音；
    若当前用户不为新用户，从销售通话录音记录中获取满足预设条件的通话记录；
    根据第二预设规则从满足预设条件的通话记录中选择相应的通话记录作为待推荐的通话记录；
    向当前用户显示待推荐的通话记录。
  17. 如权利要求16所述的计算机可读存储介质，其特征在于，所述程序指令被处理器执行所述根据第一预设规则从销售通话录音记录中选择相应的通话记录作为待推荐的通话记录时，具体实现：
    从销售通话录音记录中获取已推荐过的通话记录对应的通话录音的评分、评论、点赞数量和分享数量；
    根据预设公式计算所述通话录音的推荐分，其中，预设公式为：M＝λ 1A+λ 2B+λ 3C+λ 4D，其中，M为推荐分，λ 1、λ 2、λ 3、λ 4为权重系数，λ 1+λ 2+λ 3+λ 4＝1，A表示评分归一值，B表示好评率，C表示点赞率，D表示分享数量归一值；
    从已推荐过的通话记录中按照对应的通话录音的推荐分从高到低的顺序获取预设数量的通话记录作为待推荐的通话记录。
  18. 如权利要求16所述的计算机可读存储介质，其特征在于，所述程序指令被处理器执行所述根据第二预设规则从满足预设条件的通话录音记录中选择相应的通话记录作为待推荐的通话记录时，具体实现：
    提取当前用户历史查看的通话记录的特征；
    计算所述特征与满足预设条件的通话记录中的特征之间的相关性；
    选择所述相关性大于相关性阈值对应的通话记录；
    将选择的通话记录按照预设排序规则进行排序，从排序后的通话记录中获取预设数量的通话记录作为待推荐的通话记录。
  19. 如权利要求16所述的计算机可读存储介质，其特征在于，所述程序指令被处理器执行所述根据第二预设规则从满足预设条件的通话录音记录中选择相应的通话记录作为待推荐的通话记录时，具体实现：
    获取当前用户的权限；
    从满足预设条件的通话记录中选择与当前用户权限匹配的通话记录；
    将选择的通话记录按照预设排序规则进行排序，从排序后的通话记录中获取预设数量的通话记录作为待推荐的通话记录。
  20. 如权利要求16所述的计算机可读存储介质，其特征在于，所述步骤还包括：
    获取当前用户的筛查指令；
    从显示的通话记录中获取与当前用户的筛查指令相关的通话记录进行显示。
PCT/CN2018/075053 2017-12-28 2018-02-02 一种录音推荐方法、装置、设备及计算机可读存储介质 WO2019127845A1 (zh)

Priority Applications (2)

Application Number Priority Date Filing Date Title
US16/097,835 US20190333176A1 (en) 2017-12-28 2018-02-02 Recording recommendation method, device, apparatus and computer-readable storage medium
SG11201809602WA SG11201809602WA (en) 2017-12-28 2018-02-02 Recording recommendation method, device, apparatus and computer-readable storage medium

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201711460485.2 2017-12-28
CN201711460485.2A CN108062692B (zh) 2017-12-28 2017-12-28 一种录音推荐方法、装置、设备及计算机可读存储介质

Publications (1)

Publication Number Publication Date
WO2019127845A1 true WO2019127845A1 (zh) 2019-07-04

Family

ID=62140618

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2018/075053 WO2019127845A1 (zh) 2017-12-28 2018-02-02 一种录音推荐方法、装置、设备及计算机可读存储介质

Country Status (4)

Country Link
US (1) US20190333176A1 (zh)
CN (1) CN108062692B (zh)
SG (1) SG11201809602WA (zh)
WO (1) WO2019127845A1 (zh)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111209493A (zh) * 2020-01-09 2020-05-29 杭州中恒电气股份有限公司 充电场站推荐方法、装置、设备及介质

Families Citing this family (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109672721B (zh) * 2018-10-23 2022-07-08 平安科技（深圳）有限公司 媒体文件推送方法、装置、服务端及计算机可读存储介质
CN110060098A (zh) * 2019-04-04 2019-07-26 秒针信息技术有限公司 销售术语的获取方法及装置
CN112671983A (zh) * 2020-12-08 2021-04-16 合肥金人科技有限公司 一种呼叫中心无人值守管理系统
CN114357286A (zh) * 2021-12-24 2022-04-15 广州风腾网络科技有限公司 一种数据营销方案的推送方法、系统、设备及存储介质

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
TW201011575A (en) * 2008-09-12 2010-03-16 Univ Nat Cheng Kung Recommendation apparatus and method of integrating rough sets and multiple-characteristic exploration
CN102497383A (zh) * 2011-12-23 2012-06-13 张涛 产生和共享语音推荐记录的系统和方法
CN103870452A (zh) * 2012-12-07 2014-06-18 盛乐信息技术（上海）有限公司 数据推荐方法及系统
CN105653640A (zh) * 2015-12-25 2016-06-08 江苏东大金智信息系统有限公司 一种基于信任机制的协同过滤推荐方法
CN106339469A (zh) * 2016-08-29 2017-01-18 乐视控股（北京）有限公司 数据推荐方法及装置
CN106412796A (zh) * 2015-07-28 2017-02-15 中国移动通信集团湖北有限公司 一种推荐方法及系统

Family Cites Families (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102682761A (zh) * 2011-03-12 2012-09-19 谢津 个性化的声音处理系统和设备
CN103885987B (zh) * 2012-12-21 2018-04-10 中国移动通信集团公司 一种音乐推荐方法和系统
CN104700831B (zh) * 2013-12-05 2018-03-06 国际商业机器公司 分析音频文件的语音特征的方法和装置
CN105787069A (zh) * 2016-03-01 2016-07-20 中山大学深圳研究院 一种个性化的音乐推荐方法

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
TW201011575A (en) * 2008-09-12 2010-03-16 Univ Nat Cheng Kung Recommendation apparatus and method of integrating rough sets and multiple-characteristic exploration
CN102497383A (zh) * 2011-12-23 2012-06-13 张涛 产生和共享语音推荐记录的系统和方法
CN103870452A (zh) * 2012-12-07 2014-06-18 盛乐信息技术（上海）有限公司 数据推荐方法及系统
CN106412796A (zh) * 2015-07-28 2017-02-15 中国移动通信集团湖北有限公司 一种推荐方法及系统
CN105653640A (zh) * 2015-12-25 2016-06-08 江苏东大金智信息系统有限公司 一种基于信任机制的协同过滤推荐方法
CN106339469A (zh) * 2016-08-29 2017-01-18 乐视控股（北京）有限公司 数据推荐方法及装置

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111209493A (zh) * 2020-01-09 2020-05-29 杭州中恒电气股份有限公司 充电场站推荐方法、装置、设备及介质
CN111209493B (zh) * 2020-01-09 2023-12-12 杭州中恒电气股份有限公司 充电场站推荐方法、装置、设备及介质

Also Published As

Publication number Publication date
US20190333176A1 (en) 2019-10-31
CN108062692B (zh) 2020-03-31
SG11201809602WA (en) 2019-08-27
CN108062692A (zh) 2018-05-22

Similar Documents

Publication Publication Date Title
WO2019127845A1 (zh) 一种录音推荐方法、装置、设备及计算机可读存储介质
Freelon et al. Black trolls matter: Racial and ideological asymmetries in social media disinformation
US8060573B2 (en) Matching social network users
US20170302613A1 (en) Environment for Processing and Responding to User Submitted Posts
US10147037B1 (en) Method and system for determining a level of popularity of submission content, prior to publicizing the submission content with a question and answer support system
WO2020048084A1 (zh) 资源推荐方法、装置、计算机设备及计算机可读存储介质
US9467744B2 (en) Comment-based media classification
US10909192B2 (en) Providing information technology support
US20090327054A1 (en) Personal reputation system based on social networking
US20130238634A1 (en) Evaluating an item based on user reputation information
CN117196312A (zh) 用于为请求实体调整第二实体的信任得分的方法和系统
US20140095308A1 (en) Advertisement distribution apparatus and advertisement distribution method
EP3200113B1 (en) Password protection question setting method and device
US10719529B2 (en) Presenting a trusted tag cloud
CN110772796A (zh) 组队方法、装置及电子设备
JP6307822B2 (ja) プログラム、コンピュータおよび訓練データ作成支援方法
CN111461827A (zh) 产品评价信息的推送方法和装置
KR100901782B1 (ko) 마케팅 정보 생성 방법 및 시스템
KR101730340B1 (ko) 평가 대상에 대한 평가 결과를 정량화하는 방법
US20150358681A1 (en) Peer group evaluation program for mass distributed digital content
US10643251B1 (en) Platform for locating and engaging content generators
Stefko et al. Offline and online approaches to quality perception of Slovak university hospitals
TWI829241B (zh) 媒合系統
CN113259150B (zh) 一种数据处理方法、系统以及存储介质
KR20190104745A (ko) 이슈 관심도 기반의 뉴스 가치 평가 장치 및 방법, 이를 기록한 기록매체

Legal Events

Date Code Title Description
NENP Non-entry into the national phase

Ref country code: DE

32PN Ep: public notification in the ep bulletin as address of the adressee cannot be established

Free format text: NOTING OF LOSS OF RIGHTS PURSUANT TO RULE 112(1) EPC (EPO FORM 1205A DATED 09/10/2020)

122 Ep: pct application non-entry in european phase

Ref document number: 18894392

Country of ref document: EP

Kind code of ref document: A1